On Recognizing Face Images With Weight and Age Variations
TL;DR: The proposed algorithm utilizes neural network and random decision forest to encode age variations across different weight categories to improve the performance of face recognition with age variations.
Abstract: With the increase in age, there are changes in skeletal structure, muscle mass, and body fat. For recognizing faces with age variations, researchers have generally focused on the skeletal structure and muscle mass. However, the effect of change in body fat has not been studied with respect to face recognition. In this paper, we incorporate weight information to improve the performance of face recognition with age variations. The proposed algorithm utilizes neural network and random decision forest to encode age variations across different weight categories. The results are reported on the WhoIsIt database prepared by the authors containing 1109 images from 110 individuals with age and weight variations. The comparison with existing state-of-the-art algorithms and commercial system on WhoIsIt and FG-Net databases shows that the proposed algorithm outperforms existing algorithms significantly.
Citations
More filters
TL;DR: Major deep learning concepts pertinent to face image analysis and face recognition are reviewed, and a concise overview of studies on specific face recognition problems is provided, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching.
Abstract: Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face recognition recently, and a number of deep learning methods have been proposed. This paper summarizes about 330 contributions in this area. It reviews major deep learning concepts pertinent to face image analysis and face recognition, and provides a concise overview of studies on specific face recognition problems, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching. A summary of databases used for deep face recognition is given as well. Finally, some open challenges and directions are discussed for future research.
312 citations
TL;DR: A co-transfer learning framework is proposed, which is a cross-pollination of transfer learning and co-training paradigms and is applied for cross-resolution face matching and enhances the performance of cross- resolution face recognition.
Abstract: Face recognition algorithms are generally trained for matching high-resolution images and they perform well for similar resolution test data. However, the performance of such systems degrades when a low-resolution face image captured in unconstrained settings, such as videos from cameras in a surveillance scenario, are matched with high-resolution gallery images. The primary challenge, here, is to extract discriminating features from limited biometric content in low-resolution images and match it to information rich high-resolution face images. The problem of cross-resolution face matching is further alleviated when there is limited labeled positive data for training face recognition algorithms. In this paper, the problem of cross-resolution face matching is addressed where low-resolution images are matched with high-resolution gallery. A co-transfer learning framework is proposed, which is a cross-pollination of transfer learning and co-training paradigms and is applied for cross-resolution face matching. The transfer learning component transfers the knowledge that is learnt while matching high-resolution face images during training to match low-resolution probe images with high-resolution gallery during testing. On the other hand, co-training component facilitates this transfer of knowledge by assigning pseudolabels to unlabeled probe instances in the target domain. Amalgamation of these two paradigms in the proposed ensemble framework enhances the performance of cross-resolution face recognition. Experiments on multiple face databases show the efficacy of the proposed algorithm and compare with some existing algorithms and a commercial system. In addition, several high profile real-world cases have been used to demonstrate the usefulness of the proposed approach in addressing the tough challenges.
68 citations
TL;DR: A memorability based frame selection algorithm is presented that enables automatic selection of memorable frames for facial feature extraction and matching and achieves state-of-the-art performance at low false accept rates.
Abstract: Videos have ample amount of information in the form of frames that can be utilized for feature extraction and matching. However, face images in not all of the frames are ”memorable” and useful. Therefore, utilizing all the frames available in a video for recognition does not necessarily improve the performance but significantly increases the computation time. In this research, we present a memorability based frame selection algorithm that enables automatic selection of memorable frames for facial feature extraction and matching. A deep learning algorithm is then proposed that utilizes a stack of denoising autoencoders and deep Boltzmann machines to perform face recognition using the most memorable frames. The proposed algorithm, termed as MDLFace, is evaluated on two publicly available video face databases, Youtube Faces and Point and Shoot Challenge. The results show that the proposed algorithm achieves state-of-the-art performance at low false accept rates.
63 citations
Cites background from "On Recognizing Face Images With Wei..."
...Face recognition with still face images has been extensively studied and several approaches have been proposed to perform still image face recognition in the presence of challenging covariates such as pose, illumination, aging, disguise, and plastic surgery [2, 6, 8, 9, 20]....
[...]
TL;DR: A survey of techniques, effects of aging on performance analysis and facial aging databases, and discussions on the findings, conclusions and future directions for new researchers are presented.
Abstract: Age invariant face recognition (AIFR) is highly required in many applications like law enforcement, national databases and security. Recognizing faces across aging is difficult even for humans; hence, it presents a unique challenge for computer vision systems. Face recognition under various intra-person variations such as expression, pose and occlusion has been an intensively researched field. However, age invariant face recognition still faces many challenges due to age related biological transformations in presence of the other appearance variations. In this paper, we present a comprehensive review of literature on cross age face recognition. Starting with the biological effects of aging, this paper presents a survey of techniques, effects of aging on performance analysis and facial aging databases. The published AIFR techniques are reviewed and categorized into generative, discriminative and deep learning methods on the basis of face representation and learning techniques. Analysis of the effect of aging on the performance of age-invariant face recognition system is an important dimension. Hence, such analysis is reviewed and summarized. In addition, important facial aging databases are briefly described in terms of the number of subjects and images per subject along with their age ranges. We finally present discussions on the findings, conclusions and future directions for new researchers.
48 citations
TL;DR: In this paper, the authors present a comprehensive analysis of various face recognition (FR) systems that leverage the different types of DL techniques, and for the study, they summarize 171 recent contributions from this area and discuss improvement ideas, current and future trends of FR tasks.
Abstract: In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive analysis of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 171 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks.
39 citations
References
More filters
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
46,906 citations
01 Jan 2011
TL;DR: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.
Abstract: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.
14,708 citations
"On Recognizing Face Images With Wei..." refers background or methods in this paper
...The existing algorithms provide the best rank-1 accuracy of around 14% and the accuracy of individual descriptors such as HOG and LBP is less than 7%....
[...]
...The results of the proposed algorithm are compared with the following algorithms: • HOG [18], • Local Binary Patterns (LBP) [22], • Sparse variation dictionary learning (SVDL) [23] which is a recently proposed algorithm,2 2Source code is available on author’s website....
[...]
...Gabor convoluted sigmoid outputs are used for HOG feature extraction which is provided to RDF for classification....
[...]
...• HOG [18], • Local Binary Patterns (LBP) [22], • Sparse variation dictionary learning (SVDL) [23] which is a recently proposed algorithm,2...
[...]
...Input to RDF is weightedHOGdescriptors (weights beingwl) and output is class label....
[...]
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Abstract: This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are 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 simple and efficient classifier which is built using the AdaBoost learning algorithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection performance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.
13,037 citations
TL;DR: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently.
Abstract: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently For classification a method based on Kullback discrimination of sample and prototype distributions is used The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented
6,650 citations
"On Recognizing Face Images With Wei..." refers background in this paper
...• HOG [18], • Local Binary Patterns (LBP) [22], • Sparse variation dictionary learning (SVDL) [23] which is a recently proposed algorithm,2...
[...]
...Individual descriptors, i.e. HOG and LBP, are not able to provide more than 10.5% identification accuracy whereas existing algorithms yield around 25% accuracy....
[...]
...The existing algorithms provide the best rank-1 accuracy of around 14% and the accuracy of individual descriptors such as HOG and LBP is less than 7%....
[...]
...The results of the proposed algorithm are compared with the following algorithms: • HOG [18], • Local Binary Patterns (LBP) [22], • Sparse variation dictionary learning (SVDL) [23] which is a recently proposed algorithm,2 2Source code is available on author’s website....
[...]
14 Aug 1995
TL;DR: In this article, the authors proposed a method to construct tree-based classifiers whose capacity can be arbitrarily expanded for increases in accuracy for both training and unseen data, which can be monotonically improved by building multiple trees in different subspaces of the feature space.
Abstract: Decision trees are attractive classifiers due to their high execution speed. But trees derived with traditional methods often cannot be grown to arbitrary complexity for possible loss of generalization accuracy on unseen data. The limitation on complexity usually means suboptimal accuracy on training data. Following the principles of stochastic modeling, we propose a method to construct tree-based classifiers whose capacity can be arbitrarily expanded for increases in accuracy for both training and unseen data. The essence of the method is to build multiple trees in randomly selected subspaces of the feature space. Trees in, different subspaces generalize their classification in complementary ways, and their combined classification can be monotonically improved. The validity of the method is demonstrated through experiments on the recognition of handwritten digits.
2,957 citations