Large Illumination Variations Research Articles

Lightness perception in simple images: testing the anchoring rules.

One approach toward understanding how vision computes surface lightness is to first determine what principles govern lightness in simple stimuli and then test whether these hold for more complex stimuli. Gilchrist (2006) proposed that in the simplest images that produce the experience of a surface (two surfaces differing in luminance that fill the entire visual field) lightness can be predicted based on two anchoring rules: the highest luminance rule and the area rule, plus a scale normalization. To test whether these anchoring rules hold when critical features of the stimuli are varied, we probed lightness in simple stimuli, painted onto the inside of hemispheric domes viewed under diffuse lighting. We find that although the highest luminance surface appears nearly white across a large variation in illumination (as predicted by the highest luminance rule), its lightness tends to increase as its luminance increases. This effect is small relative to the size of the overall luminance change. Further, we find that when the darker region fills more than half of the visual field, it appears to lighten with further increases in area but only if it is a single surface. Splitting the dark region into smaller sectors that cover an equal cumulative area diminishes or eliminates the area effect.

Multi-scale patch-based sparse appearance model for robust object tracking

When objects undergo large pose change, illumination variation or partial occlusion, most existing visual tracking algorithms tend to drift away from targets and even fail to track them. To address the issue, in this paper we propose a multi-scale patch-based appearance model with sparse representation and provide an efficient scheme involving the collaboration between multi-scale patches encoded by sparse coefficients. The key idea of our method is to model the appearance of an object by different scale patches, which are represented by sparse coefficients with different scale dictionaries. The model exploits both partial and spatial information of targets based on multi-scale patches. Afterwards, a similarity score of one candidate target is input into a particle filter framework to estimate the target state sequentially over time in visual tracking. Additionally, to decrease the visual drift caused by frequently updating model, we present a novel two-step object tracking method which exploits both the ground truth information of the target labeled in the first frame and the target obtained online with the multi-scale patch information. Experiments on some publicly available benchmarks of video sequences showed that the similarity involving complementary information can locate targets more accurately and the proposed tracker is more robust and effective than others.

Color correction with blind image restoration based on multiple images using a low-rank model

We present a method that can handle the color correction of multiple photographs with blind image restoration simultaneously and automatically. We prove that the local colors of a set of images of the same scene exhibit the low-rank property locally both before and after a color-correction operation. This property allows us to correct all kinds of errors in an image under a low-rank matrix model without particular priors or assumptions. The possible errors may be caused by changes of viewpoint, large illumination variations, gross pixel corruptions, partial occlusions, etc. Furthermore, a new iterative soft-segmentation method is proposed for local color transfer using color influence maps. Due to the fact that the correct color information and the spatial information of images can be recovered using the low-rank model, more precise color correction and many other image-restoration tasks—including image denoising, image deblurring, and gray-scale image colorizing—can be performed simultaneously. Experiments have verified that our method can achieve consistent and promising results on uncontrolled real photographs acquired from the Internet and that it outperforms current state-of-the-art methods.

Face recognition under large illumination variations using homomorphic filtering in spatial domain

This paper proposes a homomorphic filtering in spatial domain for reducing of illumination effects in face recognition systems. Also, in this research a simple kernel of homomorphic filter is proposed. Application of this method causes considerable reduction in computational time in the preprocessing step. When a new face image with an arbitrary illumination is given, the homomorphic filter is applied and its reflectance component is extracted. Then the reflectance component is divided into several local regions and histograms of each local region are extracted using multi-resolution uniform local Gabor binary patterns (MULGBP). These histograms are combined for obtaining the overall histogram of the images. Finally, for face recognition, a simple histogram matching process is performed between new face image histogram and the gallery images histogram. The results show that the proposed method is robust for large illumination variation with a reasonable computational complexity.

SLD: A Novel Robust Descriptor for Image Matching

Image matching based on local features is a challenging task because it is difficult to build a robust local descriptor which is invariant to large variations in scale, viewpoints, illumination and rotation. To address these issues, Scale Invariant Feature Transform (SIFT) descriptor has been proposed to build a robust and distinctive local descriptor. However, it is not fully affine invariant. In this letter, we propose a novel robust descriptor: Sampling based Local Descriptor (SLD) to perform reliable image matching under large variations in scale, viewpoints, illumination and rotation. We build the descriptor based on elliptical sampling which samples image pixels according to the elliptic equations. The main advantage of elliptical sampling is that two controllable parameters of elliptical sampling can generate descriptors with different viewpoints and rotations. Besides, the descriptor has two notable properties: 1) it is fully invariant to affine changes; 2) it enables fast matching process because we only need to search two controllable parameters for elliptical sampling, which is more efficient than other affine invariant descriptors. We test the proposed descriptor on standard benchmark for evaluation. Experimental results show the robustness of the proposed method under large variations in illumination, viewpoints and scale.

Visual Tracking via Online Nonnegative Matrix Factorization

In visual tracking, holistic and part-based representations are both popular choices to model target appearance. The former is known for great efficiency and convenience, while the latter for robustness against local appearance or shape variations. Based on nonnegative matrix factorization (NMF), we propose a novel visual tracker that takes advantage of both groups. The idea is to model the target appearance by a nonnegative combination of nonnegative components learned from examples observed in previous frames. To adjust NMF to the tracking context, we include sparsity and smoothness constraints in addition to the nonnegativity one. Furthermore, an online iterative learning algorithm, together with a proof of convergence, is proposed for efficient model updating. Putting these ingredients together with a particle filter framework, the proposed tracker, constrained online nonnegative matrix factorization (CONMF), achieves robustness to challenging appearance variations and nontrivial deformations while running in real time. We evaluate the proposed tracker on various benchmark sequences containing targets undergoing large variations in scale, pose, or illumination. The robustness and efficiency of CONMF is validated in comparison with several state-of-the-art trackers.

Collaborative object tracking model with local sparse representation

There existed many visual tracking methods that are based on sparse representation model, most of them were either generative or discriminative, which made object tracking more difficult when objects have undergone large pose change, illumination variation or partial occlusion. To address this issue, in this paper we propose a collaborative object tracking model with local sparse representation. The key idea of our method is to develop a local sparse representation-based discriminative model (SRDM) and a local sparse representation-based generative model (SRGM). In the SRDM module, the appearance of a target is modeled by local sparse codes that can be formed as training data for a linear classifier to discriminate the target from the background. In the SRGM module, the appearance of the target is represented by sparse coding histogram and a sparse coding-based similarity measure is applied to compute the distance between histograms of a target candidate and the target template. Finally, a collaborative similarity measure is proposed for measuring the difference of the two models, and then the corresponding likelihood of the target candidates is input into a particle filter framework to estimate the target state sequentially over time in visual tracking. Experiments on some publicly available benchmarks of video sequences showed that our proposed tracker is robust and effective.

An efficient approach for face recognition based on common eigenvalues

In this paper, a simple technique is proposed for face recognition among many human faces. It is based on the polynomial coefficients, covariance matrix and algorithm on common eigenvalues. The main advantage of the proposed approach is that the identification of similarity between human faces is carried out without computing actual eigenvalues and eigenvectors. A symmetric matrix is calculated using the polynomial coefficients-based companion matrices of two compared images. The nullity of a calculated symmetric matrix is used as similarity measure for face recognition. The value of nullity is very small for dissimilar images and distinctly large for similar face images. The feasibility of the propose approach is demonstrated on three face databases, i.e., the ORL database, the Yale database B and the FERET database. Experimental results have shown the effectiveness of the proposed approach for feature extraction and classification of the face images having large variation in pose and illumination.

A local adaptive image descriptor

The local binary pattern (LBP) is a robust but computationally simple approach in texture analysis. However, LBP performs poorly in the presence of noise and large illumination variation. Thus, a local adaptive image descriptor termed as LAID is introduced in this proposal. It is a ternary pattern and is able to generate persistent codes to represent microtextures in a given image, especially in noisy conditions. It can also generate stable texture codes if the pixel intensities change abruptly due to the illumination changes. Experimental results also show the superiority of the proposed method over other state-of-the-art methods.

VIEW AND ILLUMINATION INVARIANT ITERATIVE BASED IMAGE MATCHING

In this paper, the challenges in local-feature-base d image matching are variations of view and illumin ation. Different methods have been recently proposed to address these problems by using invariant feature detectors and distinctive descriptors. However, the matching performance is still unstable and inaccura te, particularly when large variation in view or il lumination occurs. In this paper, we propose a view and illumination invariant image matching method. We iteratively estimate the relati onship of the relative view and illumination of the images, transform the view of o ne image to the other, and normalize their illumina tion for accurate matching. The performance of matching is significantly improved a nd is not affected by the changes of view and illum ination in a valid range. The proposed method would fail when the initial view an d illumination method fails, which gives us a new sto evaluate the traditional detectors. We propose two novel indicators for dete ctor evaluation, namely, valid angle and valid illu mination, which reflect the maximum allowable change in view and illumination, respectively.

Anisotropic diffusion algorithm based on weber local descriptor for illumination invariant face verification

The anisotropic diffusion (AD) algorithm is well known for the illumination invariant feature extraction of face images. The performance of anisotropic diffusion algorithm depends on its conduction function and discontinuity measure. However, in the traditional anisotropic diffusion algorithm, the discontinuity measure usually adopts space gradient or in-homogeneity. Though they are good at describing the local variation of image well, they cannot reflect the variation relative to its background. The relative variations tend to be more able to reflect the variation's degree of local image. In this paper, we propose an improved anisotropic diffusion algorithm that uses Weber local descriptor (WLD), a powerful and robust local descriptor as the discontinuity measure. Then, we introduce a centre-symmetric logarithmic transformation to eliminate the effect of shadow boundary. Experiments are executed in our proposed illumination invariant face verification scheme on CMU PIE, CAS-PEAL databases and a self-built real-life face database. The results demonstrate that the proposed method outperforms some typical methods on the face databases with large illumination variations.

Multiple instance learning tracking method with local sparse representation

When objects undergo large pose change, illumination variation or partial occlusion, most existed visual tracking algorithms tend to drift away from targets and even fail in tracking them. To address this issue, in this study, the authors propose an online algorithm by combining multiple instance learning (MIL) and local sparse representation for tracking an object in a video system. The key idea in our method is to model the appearance of an object by local sparse codes that can be formed as training data for the MIL framework. First, local image patches of a target object are represented as sparse codes with an overcomplete dictionary, where the adaptive representation can be helpful in overcoming partial occlusion in object tracking. Then MIL learns the sparse codes by a classifier to discriminate the target from the background. Finally, results from the trained classifier are input into a particle filter framework to sequentially estimate the target state over time in visual tracking. In addition, to decrease the visual drift because of the accumulative errors when updating the dictionary and classifier, a two‐step object tracking method combining a static MIL classifier with a dynamical MIL classifier is proposed. Experiments on some publicly available benchmarks of video sequences show that our proposed tracker is more robust and effective than others.

Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification

Face verification is the task of determining whether two given face images represent the same person or not. It is a very challenging task, as the face images, captured in the uncontrolled environments, may have large variations in illumination, expression, pose, background, etc. The crucial problem is how to compute the similarity of two face images. Metric learning has provided a viable solution to this problem. Until now, many metric learning algorithms have been propos'ed, but they are usually limited to learning a linear transformation In this paper, we propose a nonlinear metric learning method, which learns an explicit mapping from the original space to an optimal subspace using deep Independent Subspace Analysis (ISA) network. Compared to the linear or kernel based metric learning methods, the proposed deep ISA network is a deep and local learning architecture, and therefore exhibits more powerful ability to learn the nature of highly variable dataset. We evaluate our method on the Labeled Faces in the Wild dataset, and results show superior performance over some state-of-the-art methods.

Modular Weighted Global Sparse Representation for Robust Face Recognition

This work proposes a novel framework of robust face recognition based on the sparse representation. Image is first divided into modules and each module is processed separately to determine its reliability. A reconstructed image from the modules weighted by their reliability is formed for the robust recognition. We propose to use the modular sparsity and residual jointly to determine the modular reliability. The proposed framework advances both the modular and global sparse representation approaches, especially in dealing with disguise, large illumination variations and expression changes. Compared with the related state-of-the-art methods, experimental results on benchmark face databases verify the advancement of the proposed method.

Face recognition under varying illumination

To eliminate the effects of illumination variation, the conventional approaches firstly produce a compensation-based face image under standard illumination from the input image and then match the image with the face templates in a database. This method is not inapplicable to the input image with large illumination variation. Therefore, a novel method for varying illumination conditions is proposed. Firstly, the quotient image method is improved. Then, the nine basis images of each subject are generated by the improved quotient image method. Thirdly, one new image of each subject under the same lighting conditions with an input image is synthesized by the corresponding basis images. Finally, the synthetic images and the input image are projected to PCA plane to fulfill the recognition task. The experimental results show that the proposed approach can eliminate the effects of illumination variation and have a high recognition rate in the illumination conditions with remarkable changes.

Robust disparity estimation based on color monogenic curvature phase

Disparity estimation for binocular images is an important problem for many visual tasks such as 3D environment reconstruction, digital hologram, virtual reality, robot navigation, etc. Conventional approaches are based on brightness constancy assumption to establish spatial correspondences between a pair of images. However, in the presence of large illumination variation and serious noisy contamination, conventional approaches fail to generate accurate disparity maps. To have robust disparity estimation in these situations, we first propose a model - color monogenic curvature phase to describe local features of color images by embedding the monogenic curvature signal into the quaternion representation. Then a multiscale framework to estimate disparities is proposed by coupling the advantages of the color monogenic curvature phase and mutual information. Both indoor and outdoor images with large brightness variation are used in the experiments, and the results demonstrate that our approach can achieve a good performance even in the conditions of large illumination change and serious noisy contamination.

An Improved Face Recognition Using Neighborhood Defined Modular Phase Congruency Based Kernel PCA

A face recognition algorithm based on NMPKPCA algorithm presented in this paper. The proposed algorithm when compared with conventional Principal component analysis (PCA) algorithms has an improved recognition Rate for face images with large variations in illumination, facial expressions. In this technique, first phase congruency features are extracted from the face image so that effects due to illumination variations are avoided by considering phase component of image. Then, face images are divided into small sub images and the kernel PCA approach is applied to each of these sub images. but, dividing into small or large modules creates some problems in recognition. So a special modulation called neighborhood defined modularization approach presented in this paper, so that effects due to facial variations are avoided. Then, kernel PCA has been applied to each module to extract features. So a feature extraction technique for improving recognition accuracy of a visual image based facial recognition system presented in this paper.

Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results.

Illumination Invariant Face Recognition Using Fuzzy LDA and FFNN

The most significant practical challenge for face recognition is perhaps variability in lighting intensity. In this paper, we developed a face recognition which is insensitive to large variation in illumination. Normalization step including two steps, first we used Histogram truncation as a pre-processing step and then we implemented Homomorphic filter. The main idea is that, achieving illumination invariance causes to simplify feature extraction module and increases recognition rate. Then we utilized Fuzzy Linear Discriminant Analysis (FLDA) in feature extraction stage which showed a good discriminating ability compared to other methods while classification is performed using Feedforward Neural Network (FFNN). The experiments were performed on the ORL (Olivetti Research Laboratory) face image database and the results show the present method outweighs other techniques applied on the same database and reported in literature.

Mutual Information-Based Visual Servoing

In this paper, we propose a new information theoretic approach to achieve visual servoing directly utilizing the information (as defined by Shannon) contained in the images. A metric derived from information theory, i.e., mutual information, is considered. Mutual information is widely used in multimodal image registration since it is insensitive to changes in the lighting condition and to a wide class of nonlinear image transformations. In this paper, mutual information is used as a new visual feature for visual servoing, which allows us to build a new control law that can control the six degrees of freedom (DOF) of a robot. Among various advantages, this approach requires no matching or tracking step, is robust to large illumination variations, and allows the consideration of different image modalities within the same task. Experiments on a real robot demonstrate the efficiency of the proposed visual-servoing approach.