Scale Invariant Feature Transform

In digital image manipulation the images are converted into desired image by various tools. Detection of such kind of manipulation with digital images especially the cloning is the main area of this work. Earlier the cloning detection is done by either keypoint based or block based alone. In this paper we propose an integrating Adaptive segmentation which segments image into non overlapping and irregular blocks which increases the effectiveness of segment based image Copy Move Forgery Detection. To detect cloning with more accuracy while segment feature matching we have introduced an additional stage which refines the segments according to a threshold value. This Segment refining stage will increase the accuracy and detection speed since it rejects the unwanted segments so that only valid segments are matched. The experimental results are showing the increase in efficiency and accuracy in existing methods in the proposed scheme.

Human face recognition is one of the research areas in the current era of the research. It is one the widely used biometric technique for identification and verification of the human face. There are many challenges to face recognition like illumination variation, aging, pose variation and facial expressions etc., which degrade the performance of the algorithm. The illumination variation problem is one of the well-known problems in face recognition in uncontrolled environment. In this paper we are presenting a detail survey on 2D face recognition under such uncontrolled conditions. Here we have explored different techniques proposed for illumination reduction used for face recognition in general. After illumination reduction we can use any of the face recognition methods and any of the online available face database for recognition purpose. The objective of this review paper is to summarize and compare some of the well-known methods for better understanding of reader.

Avoiding false-positive recognition of objects is a topical problem for specific areas, such as detecting traffic signs for visually impaired pedestrians, fire emergency signs inside buildings, and construction safety signs. Existing solutions show that the percentage of incorrectly recognized traffic signs can reach 25 % for smart vehicles. In this study, SIFT/BRISK-keypoints are employed to design the image descriptor. An experiment with ten images of crosswalk traffic signs and 90 other images (including different traffic signs) showed that the false positive rate is zero and the false negative rate equals 50 %. The implementation is based on the Java Android application with the possibility to correct the knowledge base in case of false alarms. Image analysis was performed on smartphones Doogee S96 Pro and Samsung M31 with an execution time of less than one second. The most likely prospect for further development of this study is the design of the set of image descriptors to improve the false negative rate avoiding type I errors at the same time.

This paper presents a method for extracting distinctive invariant features from ear images that can be used to perform reliable matching between different views of an ear. It shows the extraction of features from an ear image and also the results of it are matching with other samples of both same and different subjects. Each of these feature vectors is supposed to be distinctive and invariant to any scaling, rotation or translation of the image.

We introduce and compare two algorithms related to ego-motion, applicable to a robot using a panoramic visual sensor in an unknown environment. The first method, computationally cheap, extends a family of bio-inspired navigation systems by providing an orientation estimation that previously had to be obtained from external references. The second method solves the general structurefrom-motion problem and is here adapted to the panoramic sensor case. Both methods produce good results in a test scene, though the calibrated method has a greater precision. A step-by-step comparison of the methods is included, with mobile robotics applications in mind.

IntelliVision is a production-ready platform for video analytics and face authentication supporting people counting, vehicle counting and automatic number plate recognition (ANPR), parking analysis, emergency flow detection, lobby/crowd thresholding, pothole detection, wildlife/pest monitoring, food-waste estimation, and room readiness analysis. We present a generalizable methodology-asynchronous orchestration with job queues, GPU-aware inference, model selection with resilient fallbacks, and task-specific post-processing-aimed at robustness under constrained resources. The methodology incorporates (i) depth-aware detector selection that adapts to scene structure; (ii) lifetime filtering plus hierarchical identity merging to reduce ID switches and overcounting in crowded scenes; and (iii) slot-gated admission and lazy model initialization to manage resource constraints. We discuss design trade-offs and limitations. Implementation details (APIs, deployment, developer tooling) are intentionally minimized to foreground the research contributions.

Excessive amounts of image spam cause many problems to e-mail users. Since image spam is difficult to detect using conventional text-based spam approach, various image processing techniques have been proposed. In this paper, we present an ensemble method using frequent itemset mining (FIM) for filtering image spam. Despite the fact that FIM techniques are well established in data mining, it is not commonly used in the ensemble method. In order to obtain a good filtering performance, a SIFT descriptor is used since it is widely known as effective image descriptors. K-mean clustering is applied to the SIFT keypoints which produce a visual codebook. The bag-of-word (BOW) feature vectors for each image is generated using a hard bag-of-features (HBOF) approach. FIM descriptors are obtained from the frequent itemsets of the BOW feature vectors. We combine BOW, FIM with another three different feature selections, namely Information Gain (IG), Symmetrical Uncertainty (SU) and Chi Square (CS...

We present a two-stage, geometry-aware approach for matching SIFT-like features in a fast and reliable manner. Our approach first uses a small sample of features to estimate the epipolar geometry between the images and leverages it for guided matching of the remaining features. This simple and generalized two-stage matching approach produces denser feature correspondences while allowing us to formulate an accelerated search strategy to gain significant speedup over the traditional matching. The traditional matching punitively rejects many true feature matches due to a global ratio test. The adverse effect of this is particularly visible when matching image pairs with repetitive structures. The geometry-aware approach prevents such preemptive rejection using a selective ratio-test and works effectively even on scenes with repetitive structures. We also show that the proposed algorithm is easy to parallelize and implement it on the GPU. We experimentally validate our algorithm on publicly available datasets and compare the results with state-of-the-art methods.

Vision based localization is widely investigated for the autonomous navigation and robotics. One of the basic steps of vision based localization is the extraction of interest points in images that are captured by the embedded camera. In this paper, SIFT and SURF extractors were chosen to evaluate their performance in localization. Four street view image sequences captured by a mobile mapping system, were used for the evaluation and both SIFT and SURF were tested on different image scales. Besides, the impact of the interest point distribution was also studied. We evaluated the performances from for aspects: repeatability, precision, accuracy and runtime. The local bundle adjustment method was applied to refine the pose parameters and the 3D coordinates of tie points. According to the results of our experiments, SIFT was more reliable than SURF. Apart from this, both the accuracy and the efficiency of localization can be improved if the distribution of feature points are well constrained for SIFT.

Remote sensing of the structural and spectral traits of vegetation is being transformed by structure from motion (SFM) algorithms that combine overlapping images to produce three-dimensional (3D) red-green-blue (RGB) point clouds. However, much remains unknown about how these point clouds are used to observe vegetation, limiting the understanding of the results and future applications. Here, we examine the content and quality of SFM point cloud 3D-RGB fusion observations. An SFM algorithm using the Scale Invariant Feature Transform (SIFT) feature detector was applied to create the 3D-RGB point clouds of a single tree and forest patches. The fusion quality was evaluated using targets placed within the tree and was compared to fusion measurements from terrestrial LIDAR (TLS). K-means clustering and manual classification were used to evaluate the semantic content of SIFT features. When targets were fully visible in the images, SFM assigned color in the correct place with a high accuracy (93%). The accuracy was lower when targets were shadowed or obscured (29%). Clustering and classification revealed that the SIFT features highlighted areas that were brighter or darker than their surroundings, showing little correspondence with canopy objects like leaves or branches, though the features showed some relationship to landscape context (e.g., canopy, pavement). Therefore, the results suggest that feature detectors play a critical role in determining how vegetation is sampled by SFM. Future research should consider developing feature detectors that are optimized for vegetation mapping, including extracting elements like leaves and flowers. Features should be considered the fundamental unit of SFM mapping, like the pixel in optical imaging and the laser pulse of LIDAR. Under optimal conditions, SFM fusion accuracy exceeded that of TLS, and the two systems produced similar representations of the overall tree shape. SFM is the lower-cost solution for obtaining accurate 3D-RGB fusion measurements of the outer surfaces of vegetation, the critical zone of interaction between vegetation, light, and the atmosphere from leaf to canopy scales.

The new advance in photogrammetry using the automatic procedures such as the famous algorithm which was proposed by David Lowe (Lowe, 2004) features descriptors and matching (SIFT) and then the recent development of external orientation (Nister (Stewenius et alii, 2006) or Snavely (Snavely et alii, 2010)) have changed drastically the way of measuring space with photogrammetry. The complexity of the process and the huge quantity of processed data (thousands of photographs) makes difficult validating the different process steps. We propose in this paper several theoretical model generation methods in order to validate the complete photogrammetric orientation process. A theoretical photogrammetric model generation has been developed in order to produce photographs, photo orientation, 3D points and 2D observations according to some defined camera and a parametric photograph distribution in the scene. In addition the use of synthesis image software generation as POV-Ray allow us to generate set of photographs with pre-computed internal and external orientation in order to check the whole pipeline from feature extraction to Photographs External Orientation. We apply this model generation approach to several typical geometry of photogrammetric scene, stereo, parallel triplet, parallel strip and convergent models.

Facial feature tracking is a key component of imaging ballistocardiography (BCG) where accurate quantification of the displacement of facial keypoints is needed for good heart rate estimation. Skin feature tracking enables video-based quantification of motor degradation in Parkinson's disease. Traditional computer vision algorithms include Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), and Lucas-Kanade method (LK). These have long represented the state-of-the-art in efficiency and accuracy but fail when common deformations, like affine local transformations or illumination changes, are present. Over the past five years, deep convolutional neural networks have outperformed traditional methods for most computer vision tasks. We propose a pipeline for feature tracking, that applies a convolutional stacked autoencoder to identify the most similar crop in an image to a reference crop containing the feature of interest. The autoencoder learns to represent image crops into deep feature encodings specific to the object category it is trained on. We train the autoencoder on facial images and validate its ability to track skin features in general using manually labeled face and hand videos. The tracking errors of distinctive skin features (moles) are so small that we cannot exclude that they stem from the manual labelling based on a χ 2 -test. With a mean error of 0.6-4.2 pixels, our method outperformed the other methods in all but one scenario. More importantly, our method was the only one to not diverge. We conclude that our method creates better feature descriptors for feature tracking, feature matching, and image registration than the traditional algorithms.

Detection of objects in cluttered scenes is a basic challenge that has only recently been widely undertaken by computer vision systems. This paper proposes a novel method how to detect a particular object in cluttered scenes, given a reference image of the object. This paper presents an algorithm for detecting a specific object based on finding point correspondences between the reference and the target image. It can detect objects despite a scale change or in-plane rotation. It is also robust to small amount of out-of-plane rotation. The detailed procedures are implemented using MATLAB.

We consider the image retrieval problem of finding the images in a dataset that are most similar to a query image. Our goal is to reduce the number of vector operations and memory for performing a search without sacrificing accuracy of the returned images. We adopt a group testing formulation and design the decoding architecture using either dictionary learning or eigendecomposition. The latter is a plausible option for small-to-medium sized problems with high-dimensional global image descriptors, whereas dictionary learning is applicable in large-scale scenario. We evaluate our approach both for global descriptors obtained from SIFT and CNN features. Experiments with standard image search benchmarks, including the Yahoo100M dataset comprising 100 million images, show that our method gives comparable (and sometimes superior) accuracy compared to exhaustive search while requiring only 10% of the vector operations and memory. Moreover, for the same search complexity, our method gives significantly better accuracy compared to approaches based on dimensionality reduction or locality sensitive hashing.

Distinguishing shot boundaries and Gradual shot change happens to be critical research area in the field of video retrieval, summarization and segmentation. Identification of Video shot boundaries is generally a significant and first step for ordering, retrieval, video segmentation and event based video analysis and numerous other such aspects. There has been extraordinary research to improve the accuracy of SBD calculations. An advance research on this work is reported towards interpretable highlights of edges. In this paper, we projected an identification of video shot structure dependent on Convolutional Neural Systems (CNNs). The method proposed in this paper uses RAI Dataset with the CNN network with improved results than traditional practices. We have tested the proposed system on the TRECVID IACC.3 dataset and made use of Keras and TensorFlow algorithms. Segmentation of videos in to fragment which extract video shots and separate the video shot boundary. This sort of preprocessing strategy helps in improving both the speed and precision of the SBD calculation. In the next part shots are extracted through semantic mark which is produced during shot detection. The projected algorithm performs well when compared with Adaptive algorithm in term of recall, Precision and F1 measure. The data set consist of standard videos (Movie Gods of Egypt, Tennis Sports, Bulletin news, Traffic Video playback, Krishna's Carton).

Detecting shot boundary and gradual shot change happens to the prominent research problem in the field of video retrieval or indexing. Video shot boundary detection (SBD) is commonly an important and first step for indexing, and retrieval, video data, browsing, and content-based video analysis and many other such technologies. There have been great efforts put forward to enhance the precision of SBD algorithms. But many of these works are oriented towards signal and not towards interpretable features of frames. In our paper, we put forward a video shot boundary detection structure based on Convolutional Neural Networks (CNNs). Candidate segment selection is adopted which determines the locations of shot boundaries and removes most non-boundary frames. This kind of preprocessing method helps in improving both the speed and accuracy of the SBD algorithm. Later on, features of frames in a shot are synthesized and semantic labels for the shot are generated. This modular CNN network will be superior to the state-of-art methods on RAI Dataset with better than average real-time deduction speed even on just one mediocre GPU. Randomly generated transitions using selected shots from the TRECVID IACC.3 dataset will be employed under the training process. The proposed system achieved an average precision of 0.966, recall of 0.864 and F1 score of 0.912.

Many fundamental importance questions of Internet behavior are still remained unexplored. This paper considers the basic engineering problem "on which length scale time-invariant traffic characteristics become visible, or do TCP attractor exit". The answer to the questions has important practical implication for traffic metering strategy and design of the protocols that based on inferring invariant characteristics from measurement time-series. The goal of this paper is to investigate invariant features of traffic traces collected in different types of local and global computer networks. Proposed approach investigates traffic as multiscale process over periods where stationary is a reasonable approximation and changes can be compensated by elastic dynamics of virtual connection.

We propose a contextual framework for 2D image matching and registration using an ensemble feature. Our system is beneficial for registering image pairs that have captured the same scene but have large visual discrepancies between them. It is common to encounter challenging visual variations in image sets with artistic rendering differences or in those collected over a period of time during which the lighting conditions and scene content may have changed. Differences between images may also be caused using a variety of cameras with different sensors, focal lengths, and exposure values. Local feature matching techniques cannot always handle these difficulties, so we have developed an approach that builds on traditional methods to consider linear and histogram of gradient information over a larger, more stable region. We also present a technique for using linear features to estimate corner keypoints, or pseudo corners, that can be used for matching. Our pipeline follows this unique matching stage with homography refinement methods using edge and gradient information. Our goal is to increase the size of accurate keypoint match sets and align photographs containing a combination of man-made and natural imagery. We show that incorporating contextual information can provide complimentary information for scale invariant feature transform and boost local keypoint matching performance, as well as be used to describe corner feature points.

COntains research objectives.U. S. Air Force (Electronic Systems Division) under Contract AF 19(628)-3325National Science Foundation (Grant G-16526)National Institutes of Health (Grant MH-04737-03)National Institutes of Health (Grant NB-04332-01)National Aeronautics and Space Administration (Grant NsG-496

This paper proposes an efficient approach known as F-SIFT, for unconstrained iris recognition. The acquired iris image is preprocessed to find the annular region underlying inner and outer iris boundary. From the annular iris image, keypoints are detected using traditional SIFT approach. Local features are defined for a window around every detected keypoint using Fourier transform. Finally, the keypoint descriptors are paired using Phase-Only Correlation. From the experimental results it is inferred that F-SIFT performs better in comparison to traditional SIFT approach on publicly available BATH and CASIAV3 iris databases.

Iris is the Optimum Biometric-trait present in Biometrics Security. Our emphasis on this paper is to obtain efficient, fast and robust algorithm set for iris detection. There are number of algorithms proposed for the efficient result but fails due to limitations. We tried in this paper to make, an efficient combination of the best schemes of normalization, corner detection, feature extraction and best matching algorithm available. We have used Modified-Trajkovic Operator (8neighbours) to detect the corner, in which, the iris image sample is first optimized by sector based normalization into four sectors, this decreases the iris area but the modified 8-neighbours detect the corner accurately. Fourier-SIFT is then used to determine the keypixels with enhanced threshold cutoff and finally Modified-Hausdorff distance (or Gromov-Hausdorff distance) determines the matching algorithm and measures the distance between keypixels of enrolled and scanned iris during matching. The limitations in the above algorithms are rectified in this paper. This process is rigorously checked on CASIA-V3 and MMU iris images.

This paper proposes an efficient three fold stratified SIFT matching for iris recognition. The objective is to filter wrongly paired conventional SIFT matches. In Strata I, the keypoints from gallery and probe iris images are paired using traditional SIFT approach. Due to high image similarity at different regions of iris there may be some impairments. These are detected and filtered by finding gradient of paired keypoints in Strata II. Further, the scaling factor of paired keypoints is used to remove impairments in Strata III. The pairs retained after Strata III are likely to be potential matches for iris recognition. The proposed system performs with an accuracy of 96.08% and 97.15% on publicly available CASIAV3 and BATH databases respectively. This marks significant improvement of accuracy and FAR over the existing SIFT matching for iris.

Automatic image annotation is to associate each image a set of keywords and describing the visual content of the image using an automatic system without any human intervention, many approaches have been proposed for the realization of such a system However, it is still inefficient in terms of semantic description of the image. Recent works show a frequent use of a special technique known as bag-of-key points that describes an image as a set of local descriptors using a histogram. Each bin of the histogram represents the importance of a visual pattern (called visual word) in the image. But crucial representation choices - such as the choice of local features, the steps of building the visual vocabulary - have not been thoroughly studied in existing works. In this paper, a novel approach based on Scale Invariant Features Transform (SIFT) features and treatment of the different steps of building de vocabulary are proposed. The proposed approach creates more robust signatures for images...

Facial feature tracking is a key component of imaging ballistocardiography (BCG) where accurate quantification of the displacement of facial keypoints is needed for good heart rate estimation. Skin feature tracking enables video-based quantification of motor degradation in Parkinson's disease. Traditional computer vision algorithms include Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), and Lucas-Kanade method (LK). These have long represented the state-of-the-art in efficiency and accuracy but fail when common deformations, like affine local transformations or illumination changes, are present. Over the past five years, deep convolutional neural networks have outperformed traditional methods for most computer vision tasks. We propose a pipeline for feature tracking, that applies a convolutional stacked autoencoder to identify the most similar crop in an image to a reference crop containing the feature of interest. The autoencoder learns to represent image crops into deep feature encodings specific to the object category it is trained on. We train the autoencoder on facial images and validate its ability to track skin features in general using manually labeled face and hand videos. The tracking errors of distinctive skin features (moles) are so small that we cannot exclude that they stem from the manual labelling based on a χ 2 -test. With a mean error of 0.6-4.2 pixels, our method outperformed the other methods in all but one scenario. More importantly, our method was the only one to not diverge. We conclude that our method creates better feature descriptors for feature tracking, feature matching, and image registration than the traditional algorithms.

SIFT-GSI is proposed to establish accurate SIFT feature correspondences for IR face recognition. A smooth spatial mapping function for the underlying correct matches is estimated by using GSI. The proposed method can establish accurate correspondences without hurting the correct matches.

In digital images, edges can be detected by applying mathematical techniques in order to identify the locations in which the brightness of an image unexpectedly changes. Edges are generally curved lines segmented into sharp adjustments in picture brightness. This paper proposes a technique for finding sharp and precise edges. Additionally, a deep learning method combined with a Gaussian Canny filter is used to replace the SUSAN filter of detection. This paper aims to evaluate how efficient deep learning is by combining the Canny method and the Smallest Uni value Segment Assimilating filter. Additionally, adding these SUSAN filters will eliminate image noise, and help users detect the corner of pictures for the improved canny algorithm. SUSAN performs better than traditional edge detectors, and produces more accurate edges.

Stereo vision is one of the interesting research topics in the computer vision field. Two cameras are used to generate a disparity map, resulting in the depth estimation. Camera calibration is the most important step in stereo vision. The calibration step is used to generate an intrinsic parameter of each camera to get a better disparity map. In general, the calibration process is done manually by using a chessboard pattern, but this process is an exhausting task. Self-calibration is an important ability required to overcome this problem. Self-calibration required a robust and good matching algorithm to find the key feature between images as reference. The purpose of this paper is to analyze the performance of three matching algorithms for the autocalibration process. The matching algorithms used in this research are SIFT, SURF, and ORB. The result shows that SIFT performs better than other methods.

Background: Soybean, a vital global oilseed crop, faces significant challenges from pest infestations and related damage that compromise productivity. Early and accurate detection of pest damage is critical for sustainable agriculture. This study evaluates the effectiveness of the ResNet-20 architecture in identifying and classifying soybean leaf conditions into three categories-Healthy, Caterpillar-damaged and Diabrotica speciosa-affected-and assesses its potential for practical agricultural deployment. Methods: The study utilized a dataset of 6,410 soybean leaf images sourced from the Mendeley database, categorized into three classes. The ResNet-20 model architecture incorporated convolutional layers, residual connections and global average pooling for efficient feature extraction and classification. Model performance was evaluated using metrics such as precision, recall, F1-score, accuracy and the Matthews Correlation Coefficient (MCC). Result: ResNet-20 demonstrated robust performance with an overall classification accuracy of 86.58%. High precision and recall values were observed for pest-affected categories, although a reduced recall for the "Healthy" class was noted. The MCC of 0.7728 highlighted strong predictive reliability. Misclassifications were attributed to visual similarities between pest-related symptoms and class imbalance in the dataset.

Feature analysis is the extraction and comparison of signals from multimedia data, which can subsequently be semantically analyzed. Feature analysis is the foundation of many multimedia computing tasks such as object recognition, image annotation, and multimedia information retrieval. In recent decades, considerable work has been devoted to the research of feature analysis. In this work, we use large-scale datasets to conduct a comparative study of four state-of-theart, representative feature extraction algorithms: color-texture codebook (CT), SIFT codebook, HMAX, and convolutional networks (ConvNet). Our comparative evaluation demonstrates that different feature extraction algorithms enjoy their own advantages, and excel in different image categories. We provide key observations to explain where these algorithms excel and why. Based on these observations, we recommend feature extraction principles and identify several pitfalls for researchers and practitioners to avoid. Furthermore, we determine that in a large training dataset with more than 10, 000 instances per image category, the four evaluated algorithms can converge to the same high level of category-prediction accuracy. This result supports the effectiveness of the data-driven approach. Finally, based on learned clues from each algorithm's confusion matrix, we devise a fusion algorithm to harvest synergies between these four algorithms and further improve class-prediction accuracy.

In this paper, a robust hybrid watermarking method based on discrete wavelet transform (DWT), discrete cosine transform (DCT), and scale-invariant feature transformation (SIFT) is proposed. Indeed, it is of prime interest to develop robust feature-based image watermarking schemes to withstand both image processing attacks and geometric distortions while preserving good imperceptibility. To this end, a robust watermark is embedded in the DWT-DCT domain to withstand image processing manipulations, while SIFT is used to protect the watermark from geometric attacks. First, the watermark is embedded in the middle band of the discrete cosine transform (DCT) coefficients of the HL1 band of the discrete wavelet transform (DWT). Then, the SIFT feature points are registered to be used in the extraction process to correct the geometric transformations. Extensive experiments have been conducted to assess the effectiveness of the proposed scheme. The results demonstrate its high robustness again...

Image Forgery means manipulation of digital image to conceal meaningful information of the image. The detection of forged image is driven by need of authenticity and to maintain integrity of an image. A copy move forgery detection theme victimization, adaptive over segmentation and has purpose feature matching is used. Earlier block based forgery detection is used but this algorithm has some flaws like: the host image is divided in to overlapping rectangular blocks, which would be computationally expensive, as size of the image increases. The method cannot address the significant geometrical transformations of the forgery regions and their recall rate is low because image blocking method is of regular shape. Although this method can avoid above two problems reducing the computational complexity thus successfully detect the forgery. This method integrates both traditional blocked base forgery detection method and key-point based forgery detection method. We use an image blocking meth...

The need for automatic understanding and examination of data increased with the tremendous growth of video and imaging databases. The change of identity, feelings and attitudes of a person's face always play a key role in terms of social communication. It is difficult for human beings to distinguish and identify various faces. Hence, we can say that in face recognition, the automatic computer-aided face detection system plays an important role. It also plays a significant role in determining the facial expressions and their recognition, estimation of head pose and interaction of humans and computers, etc. The size and location of the human face in a digital image are determined by face detection. For face detection in digital images, this paper brings forward a detailed and comprehensive survey of various important techniques. In this paper, different challenges and applications regarding face detection are also discussed. The standard databases for the detection of the face are...

Ahuna Mons is a 4 km particular geologic feature on the surface of Ceres, of possibly cryovolcanic origin. The special characteristics of Ahuna Mons are also interesting in regard of its surrounding area, especially for the big crater beside it. This crater possesses similarities with Ahuna Mons including diameter, age, morphology, etc. Under the cognitive psychology perspective and using current computer vision models, we analyzed these two features on Ceres for comparison and pattern-recognition similarities. Speeded up robust features (SURF), oriented features from accelerated segment test (FAST), rotated binary robust independent elementary features (BRIEF), Canny edge detector, and scale invariant feature transform (SIFT) algorithms were employed as feature-detection algorithms, avoiding human cognitive bias. The 3D analysis of images of both features' (Ahuna Mons and Crater B) characteristics is discussed. Results showed positive results for these algorithms about the similarities of both features. Canny edge resulted as the most efficient algorithm. The 3D objects of Ahuna Mons and Crater B showed good-fitting results. Discussion is provided about the results of this computer-vision-techniques experiment for Ahuna Mons. Results showed the potential for the computer vision models in combination with 3D imaging to be free of bias and to detect potential geoengineered formations in the future. This study also brings forward the potential problem of both human and cognitive bias in artificial-intelligence-based models and the risks for the task of searching for technosignatures.

Hyperspectral images can offer a lot of clarity by blending both spectral and spatial data. Details are for the researcher. A multidimensional paper in this paper, the hyperspectral image mosaic solution, was suggested to properly assemble hyperspectral images. This approach is a synthesis of texture details of the single gray picture, the hyperspectral spatial details image, and location details obtained during the purchase phase. This method is used in the world of medicine. Image and experimental findings hyperspectral suggest that this technique is useful compared to other image mosaic approaches based on the line segment function of scale-invariant feature transform (SIFT).

This paper introduces a new feature-based image registration algorithm which registers images by finding rotation and scale invariant features and matches them using an evidence accumulation process based on the Generalized Hough Transform. Once feature correspondence has been established, the transformation parameters are then estimated using Non-linear least squares (NLLS) and the standard RANSAC (Random Sample Consensus) algorithm. The algorithm is evaluated under similarity transforms -translation, rotation and scale (zoom) and also under illumination changes.

Log-phase K562 cells (2 ϫ 10 7 ) were electroporated (260 V, 960 F; Bio-Rad Gene Pulser with capacitance extender) with 50 g of ScaI linearized p␥͞GFP͞3MRE and 5 g of supercoiled pCMV͞CD20 plasmid in 0.4 ml of RPMI 1640 medium. Thirty-six hours later, cells were stained with AbCD20-phycoerythrin conjugate (Sigma); 10 5 healthy CD20 ϩ cells were fluorescence-activated cell sorter (FACS)-sorted in bulk, cultured 2 days, and then FACS-cloned into 96-well plates. GFP expression was ignored in both cell sorts. A total of 2,160 clones were expanded, and aliquots were prepared for PCR. Cells were washed with PBS, resuspended in 100 l of 1.0 mg͞ml proteinase K in PCR lysis buffer (50 mM KCl͞10 mM Tris, pH 8.3͞2.5 mM MgCl 2 ͞0.45% Nonidet P-40͞ 0.45% Tween 20), incubated at 55°C for 4 h, then at 95°C for 10 min, and then stored at Ϫ20°C. To screen for the presence of GFP in each clone, PCR was performed using 2 l of genomic DNA in 20-l reactions. Thirty-five amplification cycles were performed with annealing at 60°C, using primers within the GFP coding sequence (GFP05, 5Ј-ACATGAAGCAGCACGACTTC-3Ј; GFP06, 5Ј-TGCT-CAGGTAGTGGTTGTC-3Ј). The product was detected on agarose gel (261 of the 2,160 clones tested positive). Copy number of integrated transgenes in positive clones was determined by Southern blot analysis (24). Clones with a single transgene were used. Subcloning and Experimental Assays. Each line was subcloned by FACS-sorting single cells into 96-well plates. GFP expression was ignored, and no clone was exposed to zinc sulfate before or during subcloning. Subclones were tested by PCR for the presence of the transgene, and five from each clone were used in the assay for establishment of expression. Each was split in triplicate into medium with or without 80 M zinc sulfate, incubated for 24 h, and subjected to FACS analysis. For the expression level assay, subclones were pooled and plated into medium with 0, 20, 40, 60, and 80 M zinc sulfate added, incubated for 6 days, and FACS-scanned. For the silencing and stabilization assays, the

The automatic detection and tracking of human body parts in color images is highly sensitive to appearance features such as illumination, skin color and clothes. As a result, the use of depth images has been shown to be an attractive alternative over color images due to its invariance to lighting conditions. However, body part detection and tracking is still a challenging problem, mainly because the shape and depth of the imaged body can change depending on the perspective. We present a hybrid approach, called M5AIE, that uses both color and depth information to perform body part detection, tracking and pose classification. We have developed a modified Accumulative Geodesic Extrema (AGEX) approach for detecting body part candidates. We also have used the Affine-SIFT (ASIFT) algorithm for feature extraction, and we have adapted the conventional matching method to perform tracking and labeling of body parts in a sequence of images that has color and depth information. The results produced by our tracking system were used with the C4.5 Gain Ratio Decision Tree, the Naïve Bayes and the KNN classification algorithms for the identification of the users pose.

In Image processing, mosaicing image is the combine two or more images of the same scene into one image. Image stitching "mosaicing" is the process of assembling images of the same scene into a large image. Image mosaicing/stitching is considered as an active research various applications such as photogrammetry, computer vision, remote sensing image processing, medical image analysis ,computer graphics etc. In this paper discuss a review of different feature extraction algorithms and compare the different extraction algorithms such as Harris corner detector, SIFT SURF, FAST, MSER, ORB detector etc.

Hyperspectral images (HI) and Light Detection and Ranging (LiDAR) provide high resolution radiometric and geometric information for monitoring forests at individual tree crown (ITC) level. It has many important applications for sustainable forest management, biodiversity assessment and healthy ecosystem preservation. However, the integration of different remote sensing modalities is a challenging task for tree species classification due to different artifacts such as the lighting variability, the topographic effects and the atmospheric conditions of the data acquisition. The characterization of ITC can benefit from the extraction and selection of robust feature descriptors that solve these issues. This paper aims to investigate the integration of feature descriptors from HI and LiDAR by using the intra-set and inter-set feature importance for the semantic segmentation of forest tree species. A fusion methodology is proposed between high-density LiDAR data -(20 pulses m -2 ) and VNIR HI -(160 bands and 0.80 m spatial resolution) acquired on French temperate forests along an altitude gradient. The proposed scheme has three inputs: the field inventory information, the HI and the LiDAR data. Our approach can be described in nine stages: polygon projection, non-overlapping pixel selection, vegetation and shadow removal, LiDAR feature extraction, height mask, robust PCA (rPCA), feature reduction and classification. The overall accuracy of tree species classification at pixel-level was 68.9% by using random forest (RF) classifier. Our approach showed that 74.0% of trees were correctly assigned overall, by having conifer species such as Norway Spruce (Picea abies) with a producer's accuracy of 97.4%.

Vehicle detection and classification are the most significant and challenging activities of an intelligent traffic monitoring system. Traditional methods are highly computationally expensive and also impose restrictions when the mode of data collection changes. This research proposes a new approach for vehicle detection and classification over aerial image sequences. The proposed model consists of five stages. All of the images are preprocessed in the first stage to reduce noise and raise the brightness level. The foreground items are then extracted from these images using segmentation. The segmented images are then passed onto the YOLOv8 algorithm to detect and locate vehicles in each image. The feature extraction phase is then applied to the detected vehicles. The extracted feature involves Scale Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB), and KAZE features. For classification, we used the Deep Belief Network (DBN) classifier. Based on classification...

The proposed system is a portable camera based visual assistance prototype for blind people to identify currency notes and also helps them to read printable texts from the handheld objects. To read printable texts, an efficient algorithm that combines an Optical Character Recognition (OCR) with Hierarchical optimization is used. In Pattern Recognition OCR every character is localized and separated then the resulting character image is sent to a pre-processor to reduce noise and to perform normalization. Certain characteristics will be extracted from the character for comparison. After comparison the identified characters are grouped and reconstructed to form original text strings, then the output is given to the speech engine to perform text to voice conversion. For identification of currency notes a novel recognition system is developed using SIFT (Scale Invariant Feature Transform) to improve precision and accuracy. The input image undergoes pre-processing and thereafter the distinct features are extracted and compared with the templates from the database. The resulting outcome is given through Earphone to the blind users.

This paper proposes a novel hardware design method of scale-invariant feature transform (SIFT) algorithm for implementation on field-programmable gate array (FPGA). To reduce the computing costs, Gaussian kernels are calculated offline for use in Gaussian filters. To eliminate low-contrast points, the inverse of a Hessian matrix is required for hardware implementation, which results in poor performance because dividers are needed. To solve this problem, this paper presents a new mathematical derivation model to implement the low-contrast detection, avoiding the use of any dividers. For the implementation of the normalization module, a large number of dividers are required by traditional methods, which adversely affects the computational efficiency. This paper presents a new architecture using only one divider to implement the normalization function in hardware. Thanks to the parallel processing architecture proposed to design the image pyramid, SIFT detection, and SIFT descriptor, the computational efficiency of the SIFT algorithm is significantly improved. As a result of the proposed design method, the requirement of logic elements in the FPGA hardware is greatly reduced and system frequency is significantly increased. Experimental results show that the proposed hardware architecture outperforms existing techniques in terms of resource usage and computational efficiency for real-time image processing. INDEX TERMS Scale-invariant feature transform, field-programmable gate array, parallel processing architecture. WEI-YEN WANG (F'13) received the Diploma

Now a days sharing food related photos on social media has become a trend and people are looking for the interested food dishes and the restaurants. So detecting the food items, classifying them and analyzing have been the topic of in-depth studies for various applications related to food recognition, eating habits and dietary assessment. This paper gives a broad study of food recognition techniques. It also focuses on the various feature extraction methods as well as the classification techniques. This paper also gives a brief survey of the datasets available for the food.

We propose in this paper a novel multimodal approach to automatically predict the visual concepts of images through an effective fusion of visual and textual features. It relies on a Selective Weighted Late Fusion (SWLF) scheme which, in optimizing an overall Mean interpolated Average Precision (MiAP), learns to automatically select and weight the best experts for each visual concept to be recognized. Experiments were conducted on the MIR Flickr image collection within the ImageCLEF 2011 Photo Annotation challenge. The results have brought to the fore the effectiveness of SWLF as it achieved a MiAP of 43.69 % for the detection of the 99 visual concepts which ranked 2 nd out of the 79 submitted runs, while our new variant of SWLF allows to reach a MiAP of 43.93 %.

Synthesizing the image of a 3-D scene as it would be captured by a camera from an arbitrary viewpoint is a central problem in Computer Graphics. Given a complete 3-D model, it is possible to render the scene from any viewpoint. The construction of models is a tedious task. Here, we propose to bypass the model construction phase altogether, and to generate images of a 3-D scene from any novel viewpoint from prestored images. Unlike methods presented so far, we propose to completely avoid inferring and reasoning in 3-D by using projective invariants. These invariants are derived from corresponding points in the prestored images. The correspondences between features are established off-line in a semi-automated way. It is then possible to generate wireframe animation in real time on a standard computing platform. Well understood texture mapping methods can be applied to the wireframes to realistically render new images from the prestored ones. The method proposed here should allow the i...

In this paper we propose a method for person identification. The proposed method is invariant to illumination, scale, pose, camera exposure and translation of the head. In order to make the model illumination invariant, a linear transform is applied. Binary affine features are used to extract facial features from each image. The facial features obtained are compressed to form a vector which is then passed to a Bayesian classifier. This method was tested on three benchmark datasets to show as to how the method overcomes of all the hurdles such as variation of illumination, change of scale, motion of head, change in expression and more. The error rate obtained is in the neighbourhood of 18%.

The paper proposes an efficient and accurate model for face recognition using an attentive local feature descriptor extracted from Convolutional Neural Network referred to as DEep Local Feature (DELF). The algorithm mentioned formerly is used for extracting descriptors from the images using a fully convolutional network which are trained with weak supervision and using image level classes, neglecting the usage of patch and object level annotations. The physical characteristics such as colour, texture, etc are represented in the form of 40 dimensional vectors using DELF. Further, such descriptors are quantized to represent them into the compact form using Vector of Locally Aggregated Descriptors and Fisher kernels. Subsequently, such vectors are used for multiclass image classification using ensemble learning methods including Rotation Forest and Random Forests. Comparative study between both the classifiers and feature aggregation methods are performed and tabulated in the paper.