Covariates of face recognition
27 Jan 2015-
TL;DR: The report presents an evolutionary granular approach to address one of the emerging covariates of face recognition, plastic surgery, and a review of different techniques proposed to address theisting covariates, limitations of current techniques and future scope of advancements.
Abstract: Face recognition has found several applications ranging from cross border security, surveillance, access c ontrol, multimedia to forensics. Face recognition under variations due to pose, illumination, and expression has been extensively st udied in literature and several approaches have been proposed to address these covariates. Many applications of face recogn ition require matching face images with variations in age and disg uise such as matching a recent photo with your passport image or image on driver’s license. In literature, techniques have a lso been proposed to recognize face images with variations in age and disguise. These challenges can be grouped as existing covariates of face recognition. However, with ever increasing applica tions of face recognition there has emerged a need to understand ne w fascinating challenges in face recognition, emerging covariates of face recognition. Covariates such as forensic sketches, su rgically altered faces, low resolution faces, and look-alikes or twi ns are some of the challenges that have emerged as new covariates of face recognition. These covariates have important law enfo rcement applications; therefore, it has now become imperativefor current face recognition systems to be robust to these chall enges. This report focuses on three different aspects. First, it pr esents a review of different techniques proposed to address thexisting covariates, limitations of current techniques and future scope of advancements. Second, it presents how themerging covariates have evolved, what are the challenges, proposed techniques , and future research directions for each of these covariates. Fi nally, the report presents an evolutionary granular approach to address one of the emerging covariate, plastic surgery.
Citations
More filters
[...]
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.
Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …
33,785 citations
01 Jan 2006
TL;DR: It is concluded that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work, and the efficacy of this algorithm is evaluated against the variables of gender and racial origin.
Abstract: This paper details MORPH a longitudinal face database developed for researchers investigating all facets of adult age-progression, e.g. face modeling, photo-realistic animation, face recognition, etc. This database contributes to several active research areas, most notably face recognition, by providing: the largest set of publicly available longitudinal images; longitudinal spans from a few months to over twenty years; and, the inclusion of key physical parameters that affect aging appearance. The direct contribution of this data corpus for face recognition is highlighted in the evaluation of a standard face recognition algorithm, which illustrates the impact that age-progression, has on recognition rates. Assessment of the efficacy of this algorithm is evaluated against the variables of gender and racial origin. This work further concludes that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work.
139 citations
19 May 2015
TL;DR: In the proposed algorithm, first the deep learning architecture based facial representation is learned using large face database of photos and then the representation is updated using small problem-specific training database.
Abstract: Sketch recognition is one of the integral components used by law enforcement agencies in solving crime. In recent past, software generated composite sketches are being preferred as they are more consistent and faster to construct than hand drawn sketches. Matching these composite sketches to face photographs is a complex task because the composite sketches are drawn based on the witness description and lack minute details which are present in photographs. This paper presents a novel algorithm for matching composite sketches with photographs using transfer learning with deep learning representation. In the proposed algorithm, first the deep learning architecture based facial representation is learned using large face database of photos and then the representation is updated using small problem-specific training database. Experiments are performed on the extended PRIP database and it is observed that the proposed algorithm outperforms recently proposed approach and a commercial face recognition system.
79 citations
Cites background from "Covariates of face recognition"
...With the advent in technology, face recognition algorithms [7], [12] are utilized in several applications in egovernance such as nation-wide identification programs and welfare programs as well as law enforcement applications such as border security and forensics....
[...]
TL;DR: The effects of age, gender, and race covariates on face recognition are summarized, and suggestions on the future direction of the field are given to have a significant understanding of these effects individually and their interactions with one another.
Abstract: The performance of face recognition algorithms is affected by external factors and internal subject characteristics. Identifying these aspects and understanding their behaviors on performance can aid in predicting the performance of algorithms and in designing suitable acquisition settings at prospective locations to enhance performance. Factors that affect the performance of face recognition systems, such as pose, illumination, expression, and image resolution, are recognized as face recognition problems. These are substantially studied, and many algorithms have been developed to tackle these problems. However, the influence of population demographics (i.e., race, age, and gender) on face recognition performance has not received considerable attention. Early findings that deal with demographic influence give conflicting results. The studies conducted in the last decade resolve some of the contentions. Nonetheless, some findings have not reached consensus. Existing reviews on the influence of covariates are either outdated or do not cover the influence of demographic covariates on the performance of face recognition algorithms. This paper gives an intensive and focused review that covers recent research on demographic covariates. The effects of age, gender, and race covariates on face recognition are summarized based on these findings, and suggestions on the future direction of the field are given to have a significant understanding of these effects individually and their interactions with one another.
48 citations
Cites background from "Covariates of face recognition"
...Face recognition across pose variations has received considerable attention in the research community, and several promising approaches have been proposed for addressing the pose problem [21,22] (Fig....
[...]
...These expression variations result in the deformation in local facial structure and the variations of the facial appearance and geometry [22] (Fig....
[...]
...These variations in the visual aspects of a face can be larger than the variation caused by its other features [24], which affect the performance of face recognition algorithms [22,25]....
[...]
TL;DR: A regularizer-based approach to learn weight invariant facial representations using two different deep learning architectures, namely, sparse-stacked denoising autoencoders and deep Boltzmann machines is proposed, which incorporates a body-weight aware regularization parameter in the loss function of these architectures to help learn weight-aware features.
Abstract: Body weight variations are an integral part of a person’s aging process. However, the lack of association between the age and the weight of an individual makes it challenging to model these variations for automatic face recognition. In this paper, we propose a regularizer-based approach to learn weight invariant facial representations using two different deep learning architectures, namely, sparse-stacked denoising autoencoders and deep Boltzmann machines. We incorporate a body-weight aware regularization parameter in the loss function of these architectures to help learn weight-aware features. The experiments performed on the extended WIT database show that the introduction of weight aware regularization improves the identification accuracy of the architectures both with and without dropout.
30 citations
Cites background from "Covariates of face recognition"
...Several covariates such as illumination, pose, aging, disguise, sketch and plastic surgery have been identified in literature [2], [3]....
[...]
References
More filters
[...]
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.
Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …
33,785 citations
"Covariates of face recognition" refers methods in this paper
...[42] proposed a face recognition method using facial symmetry....
[...]
01 Dec 2001
TL;DR: A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Abstract: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.
18,620 citations
"Covariates of face recognition" refers methods in this paper
...[5] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features”, inProceedings of International Conference on Computer Vision and Pattern Recognition, 2001, vol. 1, pp. 511–518....
[...]
...In literature, there has been two widely used fac e detectors: Rowley [4] face detector and Adaboost proposed by Voila and Jones [5]....
[...]
...The face detector proposed by Viola and Jones [5] uses Haar-like features and a cascade of boosted decisio n tree classifiers as a statistical model....
[...]
...In literature, there has been two widely used face detectors: Rowley [4] face detector and Adaboost proposed by Voila and Jones [5]....
[...]
...The face detector proposed by Viola and Jones [5] uses Haar-like features and a cascade of boosted decision tree classifiers as a statistical model....
[...]
TL;DR: A generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis.
Abstract: Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.
14,245 citations
"Covariates of face recognition" refers background or methods in this paper
...In Circular Loca l Binary Patterns (CLBP), texture descriptor is computed bas ed on the neighboring pixels well separated on a circle around a central pixel [21], [22]....
[...]
...CLBP is extended to Uniform Circular Loca l Binary Patterns [21] to achieve robustness to rotation vari ations and dimensionality reduction....
[...]
...Algorithm Database Pose variation Gallery/ Probe Accuracy LBP [21] CMU-PIE 13 poses within±66 in yaw and±15 in tilt 2(0, 66)/ 11 remaining 74....
[...]
...Extended Uniform Circular Local Binary Patterns: Local Binary Patterns (LBP) based descriptor [21], [166] is a wide ly used texture operator because of its robustness to gray leve l changes and high computational efficiency....
[...]
...techniques LBP [21] Eigenfaces [23] View-based matching Mosaicing [24]...
[...]
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.
Abstract: We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image space-if the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions. The eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the eigenface technique for tests on the Harvard and Yale face databases.
11,674 citations