Digital photography with flash and no-flash image pairs

Computer Graphics Forum, 2012

In this work we present a new algorithm for accelerating the colour bilateral filter based on a subsampling strategy working in the spatial domain. The base idea is to use a suitable subset of samples of the entire kernel in order to obtain a good estimation of the exact filter values. The main advantages of the proposed approach are that it has an excellent trade-off between visual quality and speed-up, a very low memory overhead is required and it is straightforward to implement on the GPU allowing real-time filtering. We show different applications of the proposed filter, in particular efficient cross-bilateral filtering, real-time edge-aware image editing and fast video denoising. We compare our method against the state of the art in terms of image quality, time performance and memory usage.

Multimedia Tools and Applications, 2014

The release of the Kinect has fostered the design of novel methods and techniques in several application domains. It has been tested in different contexts, which span from home entertainment to surgical environments. Nonetheless, to promote its adoption to solve real-world problems, the Kinect should be evaluated in terms of precision and accuracy. Up to now, some filtering approaches have been proposed to enhance the precision and accuracy of the Kinect sensor, and preliminary studies have shown promising results. In this work, we discuss the results of a study in which we have compared the most commonly used filtering approaches for Kinect depth data, in both static and dynamic contexts, by using novel metrics. The experimental results show that each approach can be profitably used to enhance the precision and/or accuracy of Kinect depth data in a specific context, whereas the temporal filtering approach is able to reduce noise in different experimental conditions.

ISRN Signal Processing, 2013

We develop a multiexposure image fusion method based on texture features, which exploits the edge preserving and intraregion smoothing property of nonlinear diffusion filters based on partial differential equations (PDE). With the captured multi-exposure image series, we first decompose images into base layers and detail layers to extract sharp details and fine details, respectively. The magnitude of the gradient of the image intensity is utilized to encourage smoothness at homogeneous regions in preference to inhomogeneous regions. Then, we have considered texture features of the base layer to generate a mask (i.e., decision mask) that guides the fusion of base layers in multiresolution fashion. Finally, well-exposed fused image is obtained that combines fused base layer and the detail layers at each scale across all the input exposures. Proposed algorithm skipping complex High Dynamic Range Image (HDRI) generation and tone mapping steps to produce detail preserving image for display on standard dynamic range display devices. Moreover, our technique is effective for blending flash/no-flash image pair and multifocus images, that is, images focused on different targets.

ISRN Signal Processing, 2014

properly cited.

Multimedia Tools and Applications

The human hand possesses distinctive features which can reveal gender information. In addition, the hand is considered one of the primary biometric traits used to identify a person. In this work, we propose a large dataset of human hand images (dorsal and palmar sides) with detailed ground-truth information for gender recognition and biometric identification. Using this dataset, a convolutional neural network (CNN) can be trained effectively for the gender recognition task. Based on this, we design a two-stream CNN to tackle the gender recognition problem. This trained model is then used as a feature extractor to feed a set of support vector machine classifiers for the biometric identification task. We show that the dorsal side of hand images, captured by a regular digital camera, convey effective distinctive features similar to, if not better, those available in the palmar hand images. To facilitate access to the proposed dataset and replication of our experiments, the dataset, trained CNN models, and Matlab source code are available at (https://goo.gl/rQJndd).

TheScientificWorldJournal, 2014

We present a novel approach for enhancing the quality of an image captured from a pair of flash and no-flash images. The main idea for image enhancement is to generate a new image by combining the ambient light of the no-flash image and the details of the flash image. In this approach, we propose a method based on Adaptive Total Variation Minimization (ATVM) so that it has an efficient image denoising effect by preserving strong gradients of the flash image. Some numerical results are presented to demonstrate the effectiveness of the proposed scheme.

Lecture Notes in Computer Science, 2014

In this paper, we propose a new saliency detection method using a pair of flash and no-flash images. Our approach is inspired by two observations. First, only the foreground objects are significantly brightened by the flash as they are relatively nearer to the camera than the background. Second, the brightness variations introduced by the flash provide hints to surface orientation changes. Accordingly, the first observation is explored to form the background prior to eliminate background distraction. The second observation provides a new orientation cue to compute surface orientation contrast. These photometric cues from the two observations are independent of visual attributes like color, and they provide new and robust distinctiveness to support salient object detection. The second observation further leads to the introduction of new spatial priors to constrain the regions rendered salient to be compact both in the image plane and in 3D space. We have constructed a new flash/no-flash image dataset. Experiments on this dataset show that the proposed method successfully identifies salient objects from various challenging scenes that the state-of-the-art methods usually fail.

Forensic Sciences

The purpose of photography in violent death autopsies is to document the material evidence of the offense and guide decisions in the courts of law. The aim of the present study was to obtain the expectations of legal operators and forensic experts regarding what is expected as adequate photographic documentation in violent death forensics. For this purpose, a survey was prepared through an online form available on the “Google Forms” platform, whose link was sent by e-mail and by the WhatsApp Messenger® application. The 102 participants were divided into two distinct groups: legal practitioners, interested in the materialization of evidence (judges, prosecutors, criminal lawyers and police chiefs), and forensic experts, responsible for materializing the evidence (medical examiners, forensic dentists and criminal experts). The research showed that the inclusion of color photographs in the expert reports is essential for all research participants, as well as the marking of evidence in ...

Journal of Physics: Conference Series

Photographs either with a regular camera or a digital camera where taken from high lighting on people, often producing red spots on the pupils of the eye with the term red eye. This can cause the photo results are not good. With certain software that functions as an image processor, it can easily remove the red eye using only a tool called red eye reduction. So with the existence of the program the results of photos with digital cameras can be edited to eliminate the red eye effect before printing. Red eye reduction used the intensity color checking algorithm in the process of replacing red image pixels and then replacing them with grayish black color according to the process of intensity produced. In this paper program implemented can reduce red eye with the intensity color checking algorithm by processing certain selected regions. The image results can then be printed or saved again in a bitmap format.

Handbook of Digital Imaging, 2015

A schematic diagram of a radial section showing the various layers of the retina published in 1887 by Ferrucio Tartuferi. Tartuferi was Professor of Ophthalmology at the University of Messina in Sicily and was interested primarily in clinical eye diseases. This study, "Sull anatomia della retina" (International Monatsschrift Anatomie Physiolgie 4:421-441), appeared a year before Ramón y Cajal's first work on the retina. Courtesy of Robert Rodieck. …one day in winter, on my return home, my mother, seeing that I was cold, offered me some tea, a thing I did not ordinarily physiological ! optics image! formation retinal! processing inference photo! transduction

SpringerPlus, 2015

This paper presents a Laplacian-based image filtering method. Using a local noise estimator function in an energy functional minimizing scheme we show that Laplacian that has been known as an edge detection function can be used for noise removal applications. The algorithm can be implemented on a 3x3 window and easily tuned by number of iterations. Image denoising is simplified to the reduction of the pixels value with their related Laplacian value weighted by local noise estimator. The only parameter which controls smoothness is the number of iterations. Noise reduction quality of the introduced method is evaluated and compared with some classic algorithms like Wiener and Total Variation based filters for Gaussian noise. And also the method compared with the state-of-the-art method BM3D for some images. The algorithm appears to be easy, fast and comparable with many classic denoising algorithms for Gaussian noise.

ACM Transactions on Graphics, 2006

(a) input (b) sample possible renditions: bright and sharp, gray and highly detailed, and contrasted, smooth and grainy Figure 1: This paper describes a technique to enhance photographs. We equip the user with powerful filters that control several aspects of an image such as its tonal balance and its texture. We make it possible for anyone to explore various renditions of a scene in a few clicks. We provide an effective approach to aesthetic choices, easing the creation of compelling pictures.

Informatik aktuell, 2019

In this paper, we investigate whether is it possible to train a neural network directly from user inputs. We consider this approach to be highly relevant for applications in which the point of optimality is not well-defined and user-dependent. Our application is medical image denoising which is essential in fluoroscopy imaging. In this field every user, i.e. physician, has a different flavor and image quality needs to be tailored towards each individual. To address this important problem, we propose to construct a loss function derived from a forced-choice experiment. In order to make the learning problem feasible, we operate in the domain of precision learning, i.e., we inspire the network architecture by traditional signal processing methods in order to reduce the number of trainable parameters. The algorithm that was used for this is a Laplacian pyramid with only six trainable parameters. In the experimental results, we demonstrate that two image experts who prefer different filter characteristics between sharpness and de-noising can be created using our approach. Also models trained for a specific user perform best on this users test data. This approach opens the way towards implementation of direct user feedback in deep learning and is applicable for a wide range of application.

Signal, Image and Video Processing, 2013

Like bilateral filter (BF), cross bilateral filter (CBF) considers both gray-level similarities and geometric closeness of the neighboring pixels without smoothing edges, but it uses one image for finding the kernel and other to filter, and vice versa. In this paper, it is proposed to fuse source images by weighted average using the weights computed from the detail images that are extracted from the source images using CBF. The performance of the proposed method has been verified on several pairs of multisensor and multifocus images and compared with the existing methods visually and quantitatively. It is found that, none of the methods have shown consistence performance for all the performance metrics. But as compared to them, the proposed method has shown good performance in most of the cases. Further, the visual quality of the fused image by the proposed method is superior to other methods.

Geographic Information Systems in Geospatial Intelligence [Working Title], 2019

The automated detection of pavement distress from remote sensing imagery is a promising but challenging task due to the complex structure of pavement surfaces, in addition to the intensity of non-uniformity, and the presence of artifacts and noise. Even though imaging and sensing systems such as high-resolution RGB cameras, stereovision imaging, LiDAR and terrestrial laser scanning can now be combined to collect pavement condition data, the data obtained by these sensors are expensive and require specially equipped vehicles and processing. This hinders the utilization of the potential efficiency and effectiveness of such sensor systems. This chapter presents the potentials of the use of the Kinect v2.0 RGB-D sensor, as a low-cost approach for the efficient and accurate pothole detection on asphalt pavements. By using spatial fuzzy c-means (SFCM) clustering, so as to incorporate the pothole neighborhood spatial information into the membership function for clustering, the RGB data are...

Computer Vision – ECCV 2018, 2018

Illumination is a critical element of photography and is essential for many computer vision tasks. Flash light is unique in the sense that it is a widely available tool for easily manipulating the scene illumination. We present a dataset of thousands of ambient and flash illumination pairs to enable studying flash photography and other applications that can benefit from having separate illuminations. Different than the typical use of crowdsourcing in generating computer vision datasets, we make use of the crowd to directly take the photographs that make up our dataset. As a result, our dataset covers a wide variety of scenes captured by many casual photographers. We detail the advantages and challenges of our approach to crowdsourcing as well as the computational effort to generate completely separate flash illuminations from the ambient light in an uncontrolled setup. We present a brief examination of illumination decomposition, a challenging and underconstrained problem in flash photography, to demonstrate the use of our dataset in a data-driven approach.

Computers & Graphics, 2018

Weighted average is one of the most common strategies used in various mesh filters, and its performance depends on the weight design. When computing the weight between the current face and one of its neighbours, existing methods consider only properties of the two faces, such as positions and normals. Although they generate some convincing results, they definitely tend to suffer from cross-region mixing. For example, assigning such a large weight between two nearby faces separated by some feature edges, even when their properties are close, will damage the local structure. In this paper, we present a novel mesh filter model, named as Propagated Mesh Normal Filtering. It estimates the weight between the current face and its neighbours based on the integral of two kinds of face normal differences along the geodesic path, connecting them. Therefore, prominent features are better preserved when removing noises or textures. Furthermore, in view of the sparseness of large normal difference for most of geometry shapes, the L 1 norm is employed when integrating to further improve the filter. Experiments illustrate the enhanced efficacy of our propagated filter comparing with state-of-the-art methods.

The Visual Computer, 2013

In this paper, we propose an efficient method for 3D model retrieval using a single depth image. Unlike existing algorithms that use a complete 3D model or a user sketch as input queries, a single depth image is used as an input query, which can be captured easily with an off-theshelf lowcost 3D camera, such as a Kinect camera. 3D models in the database are represented by multiple depth images acquired from adaptively sampled viewpoints. The proposed algorithm can retrieve relevant 3D models while considering local 3D geometric characteristics using a rotation-invariant feature descriptor. The proposed method consists of three steps: preprocessing, multiple depth image based representation (M-DIBR), and description of 3D models, and similarity measurement and comparison. Experimental results demonstrate that the proposed algorithm is convenient to use and its performance is comparable to recent algorithms in terms of retrieval accuracy and speed. Keywords Content-based 3D model retrieval • 3D camera • Depth image based representation • Adaptive view-sampling • Rotation-invariant descriptor

Sensors, 2021

Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and c...

ACM Transactions on Graphics, 2010

We describe a framework for improving the quality of personal photos by using a person's favorite photographs as examples. We observe that the majority of a person's photographs include the faces of a photographer's family and friends and often the errors in these photographs are the most disconcerting. We focus on correcting these types of images and use common faces across images to automatically perform both global and face-specific corrections. Our system achieves this by using face detection to align faces between “good” and “bad” photos such that properties of the good examples can be used to correct a bad photo. These “personal” photos provide strong guidance for a number of operations and, as a result, enable a number of high-quality image processing operations. We illustrate the power and generality of our approach by presenting a novel deblurring algorithm, and we show corrections that perform sharpening, superresolution, in-painting of over- and underexposured...