Samarth Bharadwaj | Delhi university (original) (raw)

Uploads

Papers by Samarth Bharadwaj

This paper presents an efficient algorithm for matching sketches with digital face images. The al... more This paper presents an efficient algorithm for matching sketches with digital face images. The algorithm extracts discriminating information present in local facial regions at different levels of granularity. Both sketches and digital images are decomposed into multi-resolution pyramid to conserve high frequency information which forms the discriminating facial patterns. Extended uniform circular local binary pattern based descriptors use these patterns to form a unique signature of the face image. Further, for matching, a genetic optimization based approach is proposed to find the optimum weights corresponding to each facial region. The information obtained from different levels of Laplacian pyramid are combined to improve the identification accuracy. Experimental results on sketch-digital image pairs from the CUHK and IIIT-D databases show that the proposed algorithm can provide better identification performance compared to existing algorithms.

Newborn swapping and abduction is a global problem and traditional approaches such as ID bracelet... more Newborn swapping and abduction is a global problem and traditional approaches such as ID bracelets and footprinting do not provide the required level of security. This paper introduces the concept of using face recognition for identifying newborns and presents an automatic face recognition algorithm. The proposed multiresolution algorithm extracts Speeded up robust features and local binary patterns from different levels of Gaussian pyramid. The feature descriptors obtained at each Gaussian level are combined using weighted sum rule. On a newborn face database of 34 babies, the proposed algorithm yields rank-1 identification accuracy of 86.9%.

In large scale deployment of fingerprint recognition systems, especially in Indian environment, t... more In large scale deployment of fingerprint recognition systems, especially in Indian environment, there are some challenges involved. Along with sensor noise and poor image quality, presence of scars, warts, and deteriorating ridge/minutiae patterns in fingerprints from rural population affects the data distribution. In other words, quality of fingerprint patterns, particularly belonging to rural Indian population, may differ from standard urban or western population and may be difficult to process. Since there is no study that analyzes fingerprint images in Indian context, this paper presents an analytical study using standard fingerprint image quality assessment tool and fingerprint databases collected from the rural and urban Indian population. On a database of over 0.25 million images, we observed that the worn and damaged patterns lead to poor quality ridges and therefore can affect the performance. Also, region specific causes such as manual labor and Lawsonia Inermis also degrade the quality of fingerprints.

IEEE Transactions on Information Forensics and Security, 2010

Advancement and affordability is leading to popularity of plastic surgery procedures. Facial plas... more Advancement and affordability is leading to popularity of plastic surgery procedures. Facial plastic surgery can be reconstructive to correct facial feature anomalies or cosmetic to improve the appearance. Both corrective as well as cosmetic surgeries alter the original facial information to a great extent thereby posing a great challenge for face recognition algorithms. The contribution of this research is (i) preparing a face database of 900 individuals for plastic surgery, and (ii) providing an analytical and experimental underpinning of the effect of plastic surgery on face recognition algorithms. The results on the plastic surgery database suggest that it is an arduous research challenge and the current state-ofart face recognition algorithms are unable to provide acceptable levels of identification performance. Therefore, it is imperative to initiate a research effort so that future face recognition systems will be able to address this important problem.

Face recognition systems has engrossed much attention and has been applied in various domains, pr... more Face recognition systems has engrossed much attention and has been applied in various domains, primarily for surveillance, security, access control and law enforcement. In recent years much advancement have been made in face recognition techniques to cater to the challenges such as pose, expression, illumination, aging and disguise. However, due to advances in technology, there are new emerging challenges for which the performance of face recognition systems degrades and plastic/cosmetic surgery is one of them. In this paper we comment on the effect of plastic surgery on face recognition algorithms and various social, ethical and engineering challenges associated with it.

The performance of iris recognition is affected if iris is captured at a distance. Further, image... more The performance of iris recognition is affected if iris is captured at a distance. Further, images captured in visible spectrum are more susceptible to noise than if captured in near infrared spectrum. This research proposes periocular biometrics as an alternative to iris recognition if the iris images are captured at a distance. We propose a novel algorithm to recognize periocular images in visible spectrum and study the effect of capture distance on the performance of periocular biometrics. The performance of the algorithm is evaluated on more than 11,000 images of the UBIRIS v2 database. The results show promise towards using periocular region for recognition when the information is not sufficient for iris recognition.

Existing face recognition systems have demonstrated success in constrained settings with limited ... more Existing face recognition systems have demonstrated success in constrained settings with limited variability in illumination, pose, and expression. However, these incremental improvements are not sufficient to transcend the challenging applications such as identifying missing persons or matching individuals with photo ID. These applications require recognition of face images with aging variations and matching digital to scanned photo images. This paper presents a preprocessing framework to enhance the quality of the input scanned and digital face images and minimize the aging differences. Three face recognition algorithms are used to evaluate the efficacy of the proposed framework. Experimental results computed on a digital and scanned database of 310 subjects show that the framework improves the accuracy of all three algorithms by minimizing the quality differences and the variations due to aging.

Multibiometric systems fuse the evidence (e.g., match scores) pertaining to multiple biometric mo... more Multibiometric systems fuse the evidence (e.g., match scores) pertaining to multiple biometric modalities or classifiers. Most score-level fusion schemes discussed in the literature require the processing (i.e., feature extraction and matching) of every modality prior to invoking the fusion scheme. This paper presents a framework for dynamic classifier selection and fusion based on the quality of the gallery and probe images associated with each modality with multiple classifiers. The quality assessment algorithm for each biometric modality computes a quality vector for the gallery and probe images that is used for classifier selection. These vectors are used to train Support Vector Machines (SVMs) for decision making. In the proposed framework, the biometric modalities are arranged sequentially such that the stronger biometric modality has higher priority for being processed. Since fusion is required only when all unimodal classifiers are rejected by the SVM classifiers, the average computational time of the proposed framework is significantly reduced. Experimental results on different multimodal databases involving face and fingerprint show that the proposed quality-based classifier selection framework yields good performance even when the quality of the biometric sample is sub-optimal.

A probe face image may contain noise due to environmental conditions, incorrect use of sensors or... more A probe face image may contain noise due to environmental conditions, incorrect use of sensors or transmission error. The performance of face recognition severely depletes when the probe image is contaminated with noise. Denoising techniques can improve recognition performance, provided the correct parameters are used. In this paper, a parameter selection framework is presented. In the proposed framework, the optimal parameter set is selected for denoising using quality assessment algorithms with low complexity. Quality score based parameter selection is evaluated on the AR face dataset. A correlation study is discussed to ascertain the relationship between the quality scores and recognition rate. The experiments suggest that the proposed framework improves the performance both in terms of accuracy and computation time.

Recognizing faces with altered appearances is a challenging task and is only now beginning to be ... more Recognizing faces with altered appearances is a challenging task and is only now beginning to be addressed by researchers. The paper presents an evolutionary granular approach for matching face images that have been altered by plastic surgery procedures. The algorithm extracts discriminating information from non-disjoint face granules obtained at different levels of granularity. At the first level of granularity, both pre and post-surgery face images are processed by Gaussian and Laplacian operators to obtain face granules at varying resolutions. The second level of granularity divides face image into horizontal and vertical face granules of varying size and information content. At the third level of granularity, face image is tessellated into non-overlapping local facial regions. An evolutionary approach is proposed using genetic algorithm to simultaneously optimize the selection of feature extractor for each face granule along with finding optimal weights corresponding to each face granule for matching. Experiments on pre and post-plastic surgery face images show that the proposed algorithm provides at least 15% better identification performance as compared to other face recognition algorithms.

In an operational biometric verification system, changes in biometric data over a period of time ... more In an operational biometric verification system, changes in biometric data over a period of time can affect the classification accuracy. Online learning has been used for updating the classifier decision boundary. However, this requires labeled data that is only available during new enrolments. This paper presents a biometric classifier update algorithm in which the classifier decision boundary is updated using both labeled enrolment instances and unlabeled probe in- stances. The proposed co-training online classifier update algorithm is presented as a semi-supervised learning task and is applied to a face verification application. Experiments indicate that the proposed algorithm improves the performance both in terms of classification accuracy and computational time.

IEEE Transactions on Information Forensics and Security, 2010