Palmprint Recognition

This paper presents a design of PC-based multimodal biometric system, where palm blood vessels and palm prints are used as the biometric parameters. Image acquisition is based on dual spectrum illumination of the palm. By using near infrared light the image of blood vessels can be obtained and using the visible light the pattern of palm print can be captured. Images are processed using gradient filtering and complex matched filtering. After filtering, most significant features from the image are extracted as a vector set, and compared later in the recognition stage. Database of palm print and blood vessel images of 50 persons have been developed for experimental evaluation. The fusion approach of the two parameters is discussed and experimental results are presented.

Hand-based biometrics such as fingerprint and palmprint had been widely accepted because of their convenience and ease in usage without intruding much to one's privacy such as face. The aim of this work is to develop a new point-based algorithm for palmprint feature extraction and perform reliable verification based on the extracted features. This point-based recognition system is next used as part of a bimodal palmprint recognition system combining with a DCT-based (Discrete Cosine Transform) algorithm for identity verification. The performance of the integrated system is evaluated using physical palmprint images.

Several researchers have used image enhancement methods to reduce detection errors and increase verification accuracy in palmprint identification. Divergent opinions exist among experts regarding the best method of image filtering to improve image palmprint recognition. Because of the unique characteristics of palmprints and the difficulties in preventing counterfeiting, image-filtering techniques are the subject of this current research. Researchers hope to create the best biometric system possible by utilizing various techniques. These techniques include image enhancement, Gabor orientation scales, dimension reduction techniques, and appropriate matching strategies. This study investigates how different filtering approaches might be combined to improve images. The palmprint identification system uses a 3W filter, which combines wavelet, Wiener, and weighted filters. Optimizing results entails coordinating the 3W filter with Gabor orientation scales, matching processes, and dimension reduction methods. The research shows that accuracy may be considerably increased using a 3W filter with a Gabor orientation scale of [8 × 7], the kernel principal component analysis (KPCA) dimension reduction methodology, and a cosine matching method. Specifically, a value of 99.722% can be achieved. These results highlight the importance of selecting appropriate settings and techniques for palmprint recognition systems.

Amateur drones are enjoying great popularity in recent years due to the wide commercial diffusion of small, rather low-cost devices. More and more user-friendly, easy-to-pilot aerial and terrestrial drones are available off the shelf, and people can even remotely pilot them using their smartphones. This situation brings up the problem of keeping unauthorized drones away from private or sensitive areas, where they can represent a personal or public threat. With this motivation, after a survey of the existing solutions, we propose a WiFi-based approach aimed at detecting nearby aerial or terrestrial devices by performing statistical fingerprint analysis on wireless traffic. This novel detection technique, tested in a variety of real-life scenarios, proved able to efficiently detect and identify intruder drones in all the considered experimental setups, making it a promising unmanned aerial vehicle detection approach in the framework of amateur drone surveillance.

Palmprint is one of the main biometric features that has gained a lot of attention recently due to its commercial applications. Palmprint is more flexible in identifying an individual based on wrinkles, ridges and Principal lines. These features do not change during the lifetime of a person and no two individuals have similar palmprints. Most of the conventional methods use edge detection operators to detect lines in the palm which produce too many trivial lines. In this paper, a novel technique has been proposed to extract principal lines in two phases without using edge detection. The first phase involves some preprocessing operations and the second phase consists of morphological operations and elimination of undesirable components. The experimental results show that the proposed technique is more effective than existing techniques.

One of the most popular and legally recognized behavioral biometrics is the individual's signature, which is used for verification and identification in many different industries, including business, law, and finance. The purpose of the signature verification method is to distinguish genuine from forged signatures, a task complicated by cultural and personal variances. Analysis, comparison, and evaluation of handwriting features are performed in forensic handwriting analysis to establish whether or not the writing was produced by a known writer. In contrast to other languages, Arabic makes use of diacritics, ligatures, and overlaps that are unique to it. Due to the absence of dynamic information in the writing of Arabic signatures, it will be more difficult to attain greater verification accuracy. On the other hand, the characteristics of Arabic signatures are not very clear and are subject to a great deal of variation (features’ uncertainty). To address this issue, the suggested work offers a novel method of verifying offline Arabic signatures that employs two layers of verification, as opposed to the one level employed by prior attempts or the many classifiers based on statistical learning theory. A static set of signature features is used for layer one verification. The output of a neutrosophic logic module is used for layer two verification, with the accuracy depending on the signature characteristics used in the training dataset and on three membership functions that are unique to each signer based on the degree of truthiness, indeterminacy, and falsity of the signature features. The three memberships of the neutrosophic set are more expressive for decision-making than those of the fuzzy sets. The purpose of the developed model is to account for several kinds of uncertainty in describing Arabic signatures, including ambiguity, inconsistency, redundancy, and incompleteness. The experimental results show that the verification system works as intended and can successfully reduce the FAR and FRR.

Several researchers have used image enhancement methods to reduce detection errors and increase verification accuracy in palmprint identification. Divergent opinions exist among experts regarding the best method of image filtering to improve image palmprint recognition. Because of the unique characteristics of palmprints and the difficulties in preventing counterfeiting, image-filtering techniques are the subject of this current research. Researchers hope to create the best biometric system possible by utilizing various techniques. These techniques include image enhancement, Gabor orientation scales, dimension reduction techniques, and appropriate matching strategies. This study investigates how different filtering approaches might be combined to improve images. The palmprint identification system uses a 3W filter, which combines wavelet, Wiener, and weighted filters. Optimizing results entails coordinating the 3W filter with Gabor orientation scales, matching processes, and dimension reduction methods. The research shows that accuracy may be considerably increased using a 3W filter with a Gabor orientation scale of [8 × 7], the kernel principal component analysis (KPCA) dimension reduction methodology, and a cosine matching method. Specifically, a value of 99.722% can be achieved. These results highlight the importance of selecting appropriate settings and techniques for palmprint recognition systems. This is an open access article under the CC BY-SA license.

Bu çalışmada, örüntü tanımanın en önemli kısmı olan özellik çıkarma için geliştirilmiş etkili bir yöntem sunulmuştur. Darbeli radarlarda hedef sınıflama için AR modelinin güç spektrumu ve yapay sinir ağı temelli, yeni bir özellik çıkarma yöntemi geliştirilmiştir. Bu yöntemle ölçülen darbeli radar işaretlerinin AR modeli güç spektrumundan elde edilen 512 adet özellik kullanılarak sınıflama yapılmaktadır. Özelliklerin frekans bölgesinden elde edilmesi ve özellik sayısının fazla oluşu yöntemin güvenirliğini ve etkinliğini yükseltmektedir. Sınıflama yapısı ileri beslemeli ve geri yayınım öğrenme algoritmalı yapay sinir ağı üzerine kurulmuştur. Böylelikle akıllı ve otomatik bir sınıflama gerçekleşmesi sağlanmıştır.

The most common secure personal authentication in biometrics is handwritten signature. It's widely used in many felids as banks , business transactions , and documents which are being authorized via signatures. The main challenging problem in design offline signature verification system is the phase of extracting features that distinguish between forged and genuine signatures. In this paper, a novel feature of extraction method based on static image splitting is proposed. The center of density of the signature image is used for the splitting. In the proposed system, a new feature called Pixel Length (F4)is suggested. This feature is used in combination with other three features: Pixel Density (F1), Cell Angle (F2), and Pixel Angle (F3) which are common features in the offline verification signature process. Euclidean distance measure was used for classification. The proposed system is implemented and tested using GPDS database. The performance of the proposed system is measured and the experimental results show the usefulness and effectiveness of the proposed system.

Chaos game mechanism is a procedure for creating fractal phenomena from another fractal using a polygon and random walk. Here, the authors propose a novel identification approach and efficient application of Chaos Game theory towards signature identification. In fact, a signature is produced with hand scripting with a special rhythm that belongs to a specific person. Although a signature is a behavioural feature among the human biometric features, this behavioural feature expresses a chaotic property and can be analysed with chaotic systems and fractal theory. With authors' technique, by using a Chaos Game theory, a new fractal is created for each signature instance and, during the creation of the fractal, new features are extracted. These features express the fractal properties of the signature and are unique. In addition, by using fractal theory, this technique benefits from the advantages of fractal phenomena such as stability against rotation, losing some parts of the signature and scale that is desirable for biometrics applications. Authors' approach for offline signature analysis can segregate and identify many signature instances with a desirable time complexity. The authors name the technique that the authors present here the chaos game signature identification (CGSI).

Bu calismasinda, ECoG kayitlari kullanilarak parmak hareketlerinin siniflandirilmasi amaclanmistir. Calismada BCI Competition IV yarismasinda sunulan Data set IV isimli veri kumesi kullanilmistir. Veri kumesinde uc epilepsi hastasina iliskin ECoG kayitlari ve parmak hareketlerini gosteren elektronik eldiven kayitlari yer almaktadir. Eldiven kayitlari referans alinarak, parmak hareketlerinin yer aldigi ECoG bolutleri belirlenmistir. Farkli uzunluklardaki belirlenen bolutlerin oznitelik vektorleri, ozbaglanimli (AR) modelleme ile elde edilmistir. Oznitelik vektorleri kNN ve DVM yontemleri ile siniflandirilmistir. Siniflandirici acisindan bakildiginda, DVM yonteminin kNN siniflandiricisina gore daha iyi bir performans sergiledigi gorulmektedir. DVM ile yapilan siniflandirilma isleminde, her uc denek icin iki parmagin siniflandirma basari ortalamasi %87.35, uc parmagin siniflandirma basari ortalamasi %66.97, dort parmagin siniflandirma basari ortalamasi %50.06 ve tum parmaklarin sinifla...

Encounter-type haptic interfaces are used to interact physically with virtual environments. They allow controlling the position of an avatar in the simulation while perceiving the forces applied on it when it interacts with the surrounding objects. Contrary to usual force feedback devices, the interface tracks the real user's finger without touching it when the user's finger avatar moves in free space. Only when a contact occurs in the virtual environment, the interface comes in contact with the user to display the mechanical properties of the encountered objects. This way, the device's behaviour is more natural as simulated contacts really occur in the real world. Existing control laws for such devices exhibit however limitations, especially when contacts occur at high speed. In such cases, the device tends to bounce against the user's finger, which decreases the realism of the interaction. In this paper, we propose a new control strategy where the interface is first stabilized against the obstacles before the user touches its end-effector. This way, contacts appear more natural, even at high speeds, as confirmed by preliminary user-tests made with an existing 2 DoF encounter type haptic interface at different speeds with the state of the art control law and the novel approach we propose here.

Haptic interfaces are proposed for enhancing human-computer interfaces through the rendering of interaction forces. Among them, encounter-type haptic displays feature an original way to provide the user with an improved transparency: their end effectors remotely track the fingers of the operator and encounter them only when force rendering is required. These interfaces call for the development of specific position tracking systems. In this paper, a 2-D hollow instrumentation for remote and marker-free close-range finger tracking is proposed. It encloses 16 infrared proximity sensors. Its design specifications are based on a literature review of finger motion and a simulation of the tracking dynamics. Some calibration methods, organized as a function of their complexity level, are also described. The instrumentation performances are experimentally evaluated to assess its adequacy with the targeted application. This design accounts for the demonstration that infrared proximity sensing is a viable solution for close-range sensing of targets as changing as human body parts.

This paper introduced some new techniques to extract the palmprint features based on fractal codes and fractal dimension. Four new techniques based on fractal, namely FDFC (fractal dimension from fractal codes), FDIFC (fractal dimension image from fractal code), DIFC (distance image from fractal code), and AIFC (Angle image from fractal code) are proposed.. The main idea of these methods is the forming palmprint image representation by using fractal code parameters. There are three parameters of fractal codes are used namely position of range block, position of domain block, and size of range block. Those methods have been applied for palmprint verification system. The system has been tested by using database of 1050 palmprint images, are generated from 5 samples from each of the 210 persons randomly selected. Experiment results show that our proposed methods can achieve an acceptable accuracy rate.

A successful design, deployment and operation of biometric systems depends highly on the results for existing biometrical technologies and components. These existing technologies as well as new solutions need to be evaluated on their performance. However it is often forgotten that the biometric (iris, finger, face e.g.) is only one part of a fully deployed application. As biometric (sub)systems are often not designed with security and or privacy in mind, system integrators will need to address the requirements of the deployed application in this light. The fears and concerns of a significant segment of the user population need to be addressed as early as possible in the design process, to ensure that appropriate mechanisms are in place to reassure such users. These concerns may relate to privacy or to safety issues, which may be addressed in part through legal and regulatory measures. This article discusses the requirements, design and application scenario's of biometrical systems in general and the introduction of a new biometrical passport in The Netherlands in particular. On the one hand it is based on one of the authors' (BS) lecture notes of the Second International Summer School on ''Biometrics for Secure Authentication", Alghero (IT), Summer 2005 (The summer school is co-organized by the BioSecure network of Excellence in Biometrics and supported by the European Biometrics Forum). On the other hand it is based on the other authors' (BJ) experiences as external advisor of the Ministry of Internal Affairs in The Netherlands-which is responsible for the introduction of the new passport.

Palmprint recognition systems are dependent on feature extraction. A method of feature extraction using higher discrimination information was developed to characterize palmprint images. In this method, two individual feature extraction techniques are applied to a discrete wavelet transform of a palmprint image, and their outputs are fused. The two techniques used in the fusion are the histogram of gradient and the binarized statistical image features. They are then evaluated using an extreme learning machine classifier before selecting a feature based on principal component analysis. Three palmprint databases,

Breast cancer is the most common malignancy of women and is the second most common and leading cause of cancer deaths among them. At present, there are no effective ways to prevent breast cancer, because its cause is not yet fully known. Early detection is an effective way to diagnose and manage breast cancer can give a better chance of full recovery. Therefore, early detection of breast cancer can play an important role in reducing the associated morbidity and mortality rates. In this paper, using contourlet transform that can capture the intrinsic geometrical structure that is key in visual information. The contourlet expansion is composed of basis images oriented in various directions in multiple scales, with flexible aspect ratios. The basic idea of this paper is to design and implement a proposed system that can aid the physician in reading a mammogram image by study the usage of wavelet and contourlet transform based on various operations on mammogram images and classifies them as normal, benign or malignant based on the decision tree ID3 algorithm. The experimental results show that the ID3 classifier achieves accuracy of 81% in the case of wavelet transform and 95% with contourlet transform for the same number of the test set.

Breast cancer is the most common malignancy of women and is the second most common and leading cause of cancer deaths among them. At present, there are no effective ways to prevent breast cancer, because its cause is not yet fully known. Early detection is an effective way to diagnose and manage breast cancer can give a better chance of full recovery. Therefore, early detection of breast cancer can play an important role in reducing the associated morbidity and mortality rates. In this paper, using contourlet transform that can capture the intrinsic geometrical structure that is key in visual information. The contourlet expansion is composed of basis images oriented in various directions in multiple scales, with flexible aspect ratios. The basic idea of this thesis is to design and implement a proposed system that can aid the physician in reading a mammogram image by study the usage of wavelet and contourlet transform based on various operations on mammogram images and classifies them as normal, benign or malignant based on the decision tree ID3 algorithm. The experimental results show that the ID3 classifier achieves accuracy of 81% in the case of wavelet transform and 95% with contourlet transform for the same number of the test set.

Recently, a considerable amount of research has been focused on inverse biometrics, that is, regenerating the original biometric sample from its template. In this work, the first reconstruction approach to recover hand geometry samples from their feature vectors is proposed. Experiments are carried out on the publicly available GPDS Hand DB, where the method has shown a remarkable performance, after reconstructing a very high percentage of the hands included in the dataset. Furthermore, the proposed technique is general, being able to successfully reproduce the original hand shape sample regardless of the information and format of the template used.

I. INTRODUCTION HIS paper investigates the application of face recognition biometrics in travel documents for validation, verification and prevention with regards to international security. Post 9/11 incident, the United States of America (US) passed the PATRIOT Act and the ...

This paper introduced some new techniques to extract the palmprint features based on fractal codes and fractal dimension. Four new techniques based on fractal, namely FDFC (fractal dimension from fractal codes), FDIFC (fractal dimension image from fractal code), DIFC (distance image from fractal code), and AIFC (Angle image from fractal code) are proposed.. The main idea of these methods is the forming palmprint image representation by using fractal code parameters. There are three parameters of fractal codes are used namely position of range block, position of domain block, and size of range block. Those methods have been applied for palmprint verification system. The system has been tested by using database of 1050 palmprint images, are generated from 5 samples from each of the 210 persons randomly selected. Experiment results show that our proposed methods can achieve an acceptable accuracy rate.

Forensic palmprint recognition, which mainly deals with high-resolution palmprints and latent-to-full palmprint comparison, has aroused research highlights because of the increased use of the evidence of palmprints in forensics. There are some in-depth works on high-resolution palmprint preprocessing (i.e., segmentation and enhancement) and feature extraction. However, few works on latent-to-full palmprint comparison have been done. Recently, radial triangulation-based latent-to-full palmprint comparison algorithm was proposed as it has been proposed for forensic likelihood ratio computation using fingerprints, and proved to have identification usability and efficiency for palmprint comparison. In this work, we generalize point pattern comparison by relaxation to minutiae-based palmprint recognition and improve the latent-to-full palmprint comparison algorithm based on radial triangulation. Firstly, local minutiae comparison is modified according to novel point pattern comparison method and global minutiae comparison is based on centroid distribution. Then logistic regression learning is used for comparison score computation. Performance of the proposed algorithm is evaluated on forensic databases including 22 latent palmprints from real cases and 8680 full palmprints from criminal investigation field. Experimental results show the improvement on identification accuracy and efficiency of our approach. A rank-1 identification rate of 69% is achieved, compared with 63% of previous radial triangulation-based.

Recently, a novel matching strategy based on regional fusion for high resolution palmprint recognition arises for both forensic and civil applications, under the concept of different regional discriminability of three palm regions, i.e., interdigital, hypothenar and thenar. This matching strategy requires accurate automatic region segmentation techniques since manual region segmentation is time consuming. In this work, we develop automatic region segmentation techniques based on datum point detection for high-resolution palmprint recognition which can be further applied to forensic applications. Firstly, Canny edge detector is applied to a full palmprint to obtain gradient magnitudes and strong edges. Then a first datum point, i.e., the endpoint of heart line, is detected by using convex hull on gradient magnitude image and its left/right differential image and strong edge image. A second datum point, i.e., the endpoint of life line, is estimated based on the position and direction of the first datum point and statistical average distance between the two datum points. Finally, segmented palm regions are generated based on the two datum points and their perpendicular bisector. To evaluate the accuracy of our region segmentation method, we compare the automatic segmentation with manual segmentation performed on a public high resolution palmprint database THUPALMLAB with full palmprint images. The regional error rates of interdigital, thenar and hypothenar regions are 15.72%, 17.05% and 21.38% respectively. And the total error rate is 19.54% relative to full palmprint images.

Recently, a novel matching strategy based on regional fusion for high resolution palmprint recognition arises for both forensic and civil applications, under the concept of different regional discriminability of three palm regions, i.e., interdigital, hypothenar and thenar. This matching strategy requires accurate automatic region segmentation techniques since manual region segmentation is time consuming. In this work, we develop automatic region segmentation techniques based on datum point detection for high-resolution palmprint recognition which can be further applied to forensic applications. Firstly, Canny edge detector is applied to a full palmprint to obtain gradient magnitudes and strong edges. Then a first datum point, i.e., the endpoint of heart line, is detected by using convex hull on gradient magnitude image and its left/right differential image and strong edge image. A second datum point, i.e., the endpoint of life line, is estimated based on the position and direction of the first datum point and statistical average distance between the two datum points. Finally, segmented palm regions are generated based on the two datum points and their perpendicular bisector. To evaluate the accuracy of our region segmentation method, we compare the automatic segmentation with manual segmentation performed on a public high resolution palmprint database THUPALMLAB with full palmprint images. The regional error rates of interdigital, thenar and hypothenar regions are 15.72%, 17.05% and 21.38% respectively. And the total error rate is 19.54% relative to full palmprint images.

Efficient eGovernment and eCommerce require the ability to authenticate citizens and transactions online, whereas the increasing mobility of citizens demands reliable identification. Identity documents tend to become the most popular form of identity tokens used for these purposes. An important problem, however, is that they can easily be passed on or used by a fraudster. We discuss the use of identity documents and the problem of linking these documents with their genuine holder. We discuss ePassports and eID cards in general using the Belgian identity documents as a reference.

Cattle, buffalo and cow identification plays an influential role in cattle traceability from birth to slaughter, understanding disease trajectories and large-scale cattle ownership management. Muzzle print images are considered discriminating cattle biometric identifiers for biometric-based cattle identification and traceability. This paper presents an exploration of the performance of the bag-of-visual-words (BoVW) approach in cattle identification using local invariant features extracted from a database of muzzle print images. Two local invariant feature detectors—namely, speeded-up robust features (SURF) and maximally stable extremal regions (MSER)—are used as feature extraction engines in the BoVW model. The performance evaluation criteria include several factors, namely, the identification accuracy, processing time and the number of features. The experimental work measures the performance of the BoVW model under a variable number of input muzzle print images in the training, va...

This article proposes robust features fusion methodology for supervised palmprint recognition. The process of features fusion has been formulated according to the hybridization between robust morphological features of principal lines and the following features extractors: principal component analysis (PCA), transformed domain extractors, and invariant moments. The region of interest (ROI) has been extracted based on the identification of the valley points locations. Moreover, both morphological operations and edge detection have been applied in order to formulate the correct ROI. First, both length and slope of each extracted principal line have been estimated morphologically. Second, different features extraction techniques have been applied for the resultant ROI including (PCA), transformed domain, and invariant moments. Finally, seven supervised machine learning methods have been manipulated in order to achieve the highest palmprint recognition accuracy. The accuracy of the recognition was evaluated by measuring sensitivity, dice, precision, Jaccard coefficients, correlation, accuracy, and recognition time. Experimental findings show that, among all tested machine learning methods, the feed forward neural network with back propagation based on features vector of the fusion between invariant moments and principal lines morphology has achieved approximately 99.9% of successful palmprints recognition. K E Y W O R D S discrete cosine transform, discrete wavelet transform, invariant moments, principal component analysis, Hough transform, morphological features, transformed domain.

Recently, a novel matching strategy based on regional fusion for high resolution palmprint recognition arises for both forensic and civil applications, under the concept of different regional discriminability of three palm regions, i.e., interdigital, hypothenar and thenar. This matching strategy requires accurate automatic region segmentation techniques since manual region segmentation is time consuming. In this work, we develop automatic region segmentation techniques based on datum point detection for high-resolution palmprint recognition which can be further applied to forensic applications. Firstly, Canny edge detector is applied to a full palmprint to obtain gradient magnitudes and strong edges. Then a first datum point, i.e., the endpoint of heart line, is detected by using convex hull on gradient magnitude image and its left/right differential image and strong edge image. A second datum point, i.e., the endpoint of life line, is estimated based on the position and direction of the first datum point and statistical average distance between the two datum points. Finally, segmented palm regions are generated based on the two datum points and their perpendicular bisector. To evaluate the accuracy of our region segmentation method, we compare the automatic segmentation with manual segmentation performed on a public high resolution palmprint database THUPALMLAB with full palmprint images. The regional error rates of interdigital, thenar and hypothenar regions are 15.72%, 17.05% and 21.38% respectively. And the total error rate is 19.54% relative to full palmprint images.

Human activity recognition and object detection are techniques for detecting a human and objects from an image respectively. Which can be greatly useful for medical, security and industrial fields. This paper presents a new approach by combining both the techniques for extra usability and accurate detection of activities. This paper presents the HOG features for detecting the human in an image and SURF features for extraction of matched points from the image. The accuracy of results are higher due to combination of both the techniques by merging the results of features obtained from an image. The algorithm helps to perform better in low-light conditions which helps to perform better feature extraction. This technique determines the distance of the object from a human and provides the results of activities based on the distance.

Because of their high recognition rates, coding-based approaches that use multispectral palmprint images have become one of the most popular palmprint recognition methods. This paper describes a new multispectral palmprint recognition method that aims to further improve the performance of coding-based approaches by focusing on the local binary pattern (LBP) filters and spiral moments features. The final feature map is derived through a staged process of creating a composite of spiral and LBP features by fusing them together and passing the features through the minimum redundancy maximum relevance transformers. Using Hamming distances, the inter-and intra-similarities of the palmprint feature maps are determined. The experimental technique was evaluated using the available data on the IITD, MSPolyU and PolyU PPDB databases. The results indicate that the method achieved high levels of accuracy in the identification and verification modes. Furthermore, this method outperforms the existing advanced techniques.

Doku sınıflandırma amacı ile,çok sayıda doku analizi yaklaşımlarıönerilmiştir. Son olarak, Dalgacıkçerçeveler, dokuöznitelik ayrışımı için teklif edildi. Buçalışmada, alt-örneklemesiz dalgacıkçerçeve dönüşümü, Brodatz albümünden alınan 16 adet dokuörnegininçeşitli dalgacık aileleri vasıtasıylaözniteliklerinin saptanmasında kullanıldı. Doku sınıflandırma, hızlı adaptif geriye yayılımlı algoritmalı yapay sinir agları kullanılarak gerçekleştirildi. Yapay sinir agları sınıflandırıcısını egitmek maksadı ile, rastgele döndürülmüş ve degişken boyutlarda doku pencereleri oluşturan yeni bir piramit pencereleme algoritması sunuldu ve tam bir sınıflandırma sonuçları elde edildi.

With the fast development of smart mobile devices, mobile phones have gradually become an indispensable part of people's lives. Many biometric technologies based on mobile platforms have also developed rapidly, such as face verification and fingerprint recognition. However, the great potential of palmprint has been neglected. In this paper, we conducted a thorough study of palmprint verification on mobile devices for the first time. Firstly, we established an annotated, palmprint dataset named MPD, which was collected by multi-brands phones in two different sessions. As the largest dataset in this field, MPD contains 16,000 palm images from 200 subjects. Secondly, we built a DCNN-based palmprint verification system named DeepMPV for mobile platforms. The efficiency and performance of our system have been corroborated on our collected dataset. The labelled dataset and the source code are publicly available at https://cslinzhang.github.io/deepmpv/.

Reliable identification notification is still a problem that needs solution in today's world. This thesis study was developed to contribute solutions of that problem in the light of algorithm and biometric identification notification and verification systems. Palm print traces an important role in biometric identification notification. Visions that were obtained from palm print scanner, translated numerical status with using image processing technics. To determine palm print trace attribute vectors, palm trace's referenced working region of interest omitted and viii ŞEKİLLER SAYFA NO

Biyometrik sistemler, bireylerin fiziksel ve davranissal ozelliklerini tanimlayarak kimliklendirme yapan sistemlerdir. En yaygin kullanilanlari ise parmak izi, el geometrisi, ses, retina, yuz, imza vb. biyometriklerdir. Bu sistemler gunumuzde hava alanlarinda, fabrikalarda ve yuksek guvenlik gerektiren binalar gibi alanlarda, giris cikislari kontrol etmede ya da girilen verileri onaylama gibi sureclerde kullanilmaktadir. Bunun yaninda yasam icerisinde bireylerin hayatini kolaylastiracak akilli sistemlerde, dijital fotograf makinelerinde, e-ticarette, kriminal incelemelerde vb. bircok alanda kullanilmaktadir. Her bir sistemin kendi icerisinde avantajlari ve dezavantajlari bulunmaktadir. Bu nedenle bu tur teknolojilerin basarisini belirlemek ozellikle guvenligin on planda oldugu durumlarda kritik faktorler ongormek calismalara yardimci olacaktir. Bu calismada da genel olarak kullanilan biyometrik sistemler arastirilmis ve incelenen guncel calismalar icerisinde bu sistemlerle ilgili ka...

Recently, researchers have been paying an excessive amount of attention to biometric palmprint which has gained popularity and received significant prominence due to its high stability and uniqueness. In this study, two certain filters have been taken into consideration, namely Gabor filter and Circular Gabor filter which are used to obtain feature information from two distinguishing regions of interest, square and inscribed circle areas as the central part sub-images and the two palmprint images are compared with one another in terms of their hamming distance. The outcomes of the experiment gave an indication to the fact that circular Gabor Filter had a comparatively better performance than traditional one in extracting distinct feature information.

The resolution of the acquired biometric image is considered as one of the primary factors affecting the performance of a biometric authentication system. For low quality images, a powerful feature extraction method is very essential. Orthogonal Legendre moments are used in several pattern recognition and image processing applications for feature extraction. Translation and scale invariant Legendre moments are achieved directly by using the Legendre polynomial. However, this method does not yield a rotational invariant form. In this paper we propose a palmprint verification system in which the 2D Legendre moments are represented as a linear combination of geometric moment invariants. Geometric moments are invariant to translation, non-uniform scaling and rotation. The modified Legendre moments are used for feature extraction and a weighted fusion technique is used to fuse the matching scores of the sub-images. The results obtained using a Baye's classifier indicate an impressive prediction accuracy of 98%, validating the choice of low order Legendre moment for effective palmprint verification.

The demand on devices and systems empowered by biometric verification and identification mechanisms has been increasing in recent years as they have become a significant part of our lives. Palm vein biometric is an emerging technology that has drawn considerable attention from researchers and scientists over the last decade. In the present work, a novel feature extraction methodology named GPWLD combing the Gabor features with positional Weber's local descriptor (PWLD) features is proposed. WLD is a highly representative micro-pattern descriptor that performs well against noise and illumination changes in images. However, it lacks the ability to capture the vein pattern features at different orientations. Moreover, its descriptor packs the local information content into a single histogram that does not take the spatial locality of micro-patterns into consideration. To solve these two issues, firstly, the palm vein image is passed through Gabor filter with different orientations to capture the salient rotational features found in the output feature maps. Secondly, the spatiality is achieved by uniformly dividing each feature map into several blocks. Next, Weber's law feature descriptor (WLD) histogram is computed for each block in every feature map. Finally, these histograms are concatenated to compose the final feature vector. Due to the high dimensionality of the final feature vector, Principal component analysis (PCA) algorithm is utilized for feature size reduction. In the classification stage, a deep neural network (DNN) comprising an optimized stacked autoencoder (SAE) with Bayesian optimization and a softmax layer is used. Optimization of the SAE is carried out by using Bayesian optimization to find the optimal SAE structure and the options of the training algorithm. The Experimental results verify the discriminative power of the extracted features and the accuracy of the proposed DNN. For both Identification and verification experiments, the proposed method attains higher identification rate and lower EER than state-of-the-art methods. INDEX TERMS WLD descriptor, Gabor filter, deep neural network, stacked autoencoder, Bayesian optimization.

Identification and verification are the fundamental process in biometrics recognition system. Research indicates that palmprint, as one of the biometric recognitions system is commonly used for human identification. It is because there are many features and information contained inside the palmprint that can be used in the identification process. However, only a small region of the palmprint can be extracted using the existing palmprint region of interest (ROI) extraction algorithms. This has become a problem for identification systems due to negligible and loss of important features which are located outside the ROI. Hence, it is a necessity to improve the palmprint ROI extraction algorithm whereby bigger palmprint ROI can be extracted using this algorithm. Therefore, a larger fixed size extraction algorithm for palmprint ROI is proposed where the extraction region is larger so that more important identification features can be captured inside these ROIs. The performance between pr...

In this research, images of Kızıltepe (Mardin) agricultural land are classified based on development in different period of crops (1-sowing term, 2-little ripe term, 3-ripe term and 4-harvest term). The digital crop images are derived from TARIT (Agricultural Crop Forecast and Following Project) stations. The texture feature vectors are obtained from images of different crop periods with using Gray Level Co-Occurrence Matrix (GLCM) and Law's Texture Energy Measure (TEM) which are very popular methods for image texture extraction. GLCM and TEM based feature vectors are applied to different type of classifiers as inputs and the performance results of each system are compared. For classification the crop images, Multilayer Perceptron (MLP) neural network, k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) methods are used. While the best performance is observed as 100% in GLCM based SVM classifier only, the same performance is observed in TEM based all classifier types. Texture features of crop images based on TEM method allow us to exhibit high performance in all classifiers.

Bu çalışmada, histopatolojik imgelerden çeşitli hastalıkların tanınması işleminde, hekime yardımcı olacak ve kolaylık sağlayacak bir karar destek sistemi tasarlanmıştır. Otomatik hücre sayma sisteminde, hekimler için uzun zaman ve dikkat gerektiren uygulamaların daha kısa sürede ve istenen başarım ölçütleri içinde yapılması sağlanmıştır. Geliştirilen sistem, histopatolojik imgeden istenen hücrelerin ayrıştırılmasını sağlayan bölütleme, söz konusu hücrelerin daha görünür hale getirilmesinde iyileştirme ve istenen hücrelerin sayılması aşamalarını içermektedir. Otomatik hücre sayma sisteminin hepatitli ve kanserli hastalardan alınan histopatolojik imgeler üzerinde değerlendirmesi yapılmıştır. Elde edilen sonuçlar, hekim bulguları ile karşılaştırılarak, %90 oranında doğruluk örtüşmesi sağlanmıştır. In this study, a decision support system is designed which makes things easier for physicians and helps them for recognizing various diseases from histopathologic images. In automatic enumera...

Bu calismada, histopatolojik imgelerden cesitli hastaliklarin taninmasi isleminde, hekime yardimci olacak vekolaylik saglayacak bir karar destek sistemi tasarlanmistir. Gelistirilen karar destek sistemi, oruntu tanimatemellidir. Oruntu tanima surecinin, ozellik cikarim asamasi Fraktal analiz ve siniflandirma asamasi icinse kararagaclari kullanilmistir. Hepatitli hastalarin histopatolojik imgeleri ile gelistirilen sistemin basarisidegerlendirilmistir. 50 hasta verisi uzerinde gelistirilen sistemin dogruluk yuzdesi %92 olarak bulunmustur.

Palmprint recognition being one of the important aspects of biometric technology is one of the most reliable and successful identification methods. In this paper, several existing palmprint recognition algorithms have been studied and analyzed. A simple approach to preprocessing and roi extraction has been discussed. The available databases have also been analyzed and the most efficient of all will be used for the development of

Biometric recognition by hand geometry has a large number of measurements that may be used for authentication. The higher number of attributes, the harder is to define the importance of each one. In this paper, we analyze the use of a Genetic Algorithm-based approach in improving Equal Error Rate (EER) performance for biometric authentication by hand geometry. We used an own data set of dorsal and palm images of hand in a controlled environment to validate our approach. As the best results, the genetic algorithm decreased the equal error rate up to 0% in the training set and 0.01% for the test set. Additionally, a relative improvement of 90.91% was achieved by GA in the best case for the test set.

This paper proposes an automated system for recognizing palmprints for biometric identification of individuals. Complex Zernike moments are constructed using a set of complex polynomials which form a complete orthogonal basis set defined on the unit disc. Palmprint images are projected onto the basis set resulting in a set of complex signals. The magnitude of the complex value is computed and a scalar value is derived from it by computing the mean of the vector elements. Classification is done by subtracting the test samples from the mean of the training set. The data set consists of 80 images divided into 4 classes. Accuracy obtained is comparable to the best results reported in literature

A new palmprint recognition system is presented here. The method of extracting and evaluating textural feature vectors from palmprint images is tested on the PolyU database. Furthermore, this method is compared against other approaches described in the literature that are founded on binary pattern descriptors combined with spiral-feature extraction. This novel system of palmprint recognition was evaluated for its collision test performance, precision, recall, F-score and accuracy. The results indicate the method is sound and comparable to others already in use.

Palmprint is one of the main biometric features that has gained a lot of attention recently due to its commercial applications. Palmprint is more flexible in identifying an individual based on wrinkles, ridges and Principal lines. These features do not change during the lifetime of a person and no two individuals have similar palmprints. Most of the conventional methods use edge detection operators to detect lines in the palm which produce too many trivial lines. In this paper, a novel technique has been proposed to extract principal lines in two phases without using edge detection. The first phase involves some preprocessing operations and the second phase consists of morphological operations and elimination of undesirable components. The experimental results show that the proposed technique is more effective than existing techniques.

In this paper, the author propose palm print recognition algorithm of human being based on radon transform. We propose a general framework for Directional and Texture Features. Firstly we use canny edge detection on taken image. Normally palm prints are recognized by changes in ridges, singular points, minutiae and bifurcation etc. For palm print recognition we use radon transform which is little bit different than other techniques. The proposed algorithm gives us good feature vector of palm print images.