Ankit Sarkar

Bio: Ankit Sarkar is an academic researcher from Indraprastha Institute of Information Technology. The author has contributed to research in topics: 3D single-object recognition & Counterfeit. The author has an hindex of 2, co-authored 3 publications receiving 29 citations.

Face recognition for look-alikes: A preliminary study

Abstract: One of the major challenges of face recognition is to design a feature extractor and matcher that reduces the intraclass variations and increases the inter-class variations. The feature extraction algorithm has to be robust enough to extract similar features for a particular subject despite variations in quality, pose, illumination, expression, aging, and disguise. The problem is exacerbated when there are two individuals with lower inter-class variations, i.e., look-alikes. In such cases, the intra-class similarity is higher than the inter-class variation for these two individuals. This research explores the problem of look-alike faces and their effect on human performance and automatic face recognition algorithms. There is three fold contribution in this research: firstly, we analyze the human recognition capabilities for look-alike appearances. Secondly, we compare human recognition performance with ten existing face recognition algorithms, and finally, proposed an algorithm to improve the face verification accuracy. The analysis shows that neither humans nor automatic face recognition algorithms are efficient in recognizing look-alikes.

Detecting Counterfeit Currency and Identifying Its Source

Abstract: Counterfeit currency varies from low quality color scanner/printer-based notes to high quality counterfeits whose production is sponsored by hostile states. Due to their harmful effect on the economy, detecting counterfeit currency notes is a task of national importance. However, automated approaches for counterfeit currency detection are effective only for low quality counterfeits; manual examination is required to detect high quality counterfeits. Furthermore, no automatic method exists for the more complex – and important – problem of identifying the source of counterfeit notes. This paper describes an efficient automatic framework for detecting counterfeit currency notes. Also, it presents a classification framework for linking genuine notes to their source printing presses. Experimental results demonstrate that the detection and classification frameworks have a high degree of accuracy. Moreover, the approach can be used to link high quality fake Indian currency notes to their unauthorized sources.

Can humans and automatic algorithms recognize look-alike faces?

Abstract: One of the major challenges of face recognition is to design a feature extractor that reduces the intra-class variations and increases the inter-class variations. The feature extraction algorithm has to be robust enough to extract similar features for a particular class despite variations in quality, pose, illumination, expression, aging and disguise. The problem is exacerbated when there are two individuals with lower inter-class variations, i.e., look-alikes. In such cases, the intra-class similarity is higher than the interclass variation for these two individuals. This research explores the problem of look-alikes faces and their effect on human performance and automatic face recognition algorithms. There is two fold contribution in this research: firstly, we analyze human recognition capabilities for lookalike appearances and secondly, compare it with automatic face recognition algorithms. In our analysis, we observe that neither humans nor automatic face recognition algorithms are efficient for the challenge of look-alikes.

Automated kinship verification and identification through human facial images: a survey

Abstract: Face is the most considerable constituent that people use to recognize one another. Humans can quickly and easily identify each other by their faces and since facial features are unobtrusive to lighting condition and pose, face remains as a dynamic recognition approach to human. Kinship recognition refers to the task of training a machine to recognize the blood relation between a pair of kin and non-kin faces (verification) based on features extracted from facial images, and to determine the exact type or degree of that relation (identification). Automatic kinship verification and identification is an interesting areas for investigation, and it has a significant impact in many real world applications, for instance, forensic, finding missing family members, and historical and genealogical research. However, kinship recognition is still not largely explored due to insufficient database availability. In this paper we present a survey on issues and challenges in kinship verification and identification, related previous works, current trends and advancements in kinship recognition, and potential applications and research direction for the future. We also found that Deep Learning (DL) has mostly outperformed numerous methods using manually designed features by automatically learning and extracting important information from facial features, and enable significant visual recognition functions by improving accuracy in most applications.

Open-set face recognition across look-alike faces in real-world scenarios

Abstract: The open-set problem is among the problems that have significantly changed the performance of face recognition algorithms in real-world scenarios. Open-set operates under the supposition that not all the probes have a pair in the gallery. Most face recognition systems in real-world scenarios focus on handling pose, expression and illumination problems on face recognition. In addition to these challenges, when the number of subjects is increased for face recognition, these problems are intensified by look-alike faces for which there are two subjects with lower intra-class variations. In such challenges, the inter-class similarity is higher than the intra-class variation for these two subjects. In fact, these look-alike faces can be created as intrinsic, situation-based and also by facial plastic surgery. This work introduces three real-world open-set face recognition methods across facial plastic surgery changes and a look-alike face by 3D face reconstruction and sparse representation. Since some real-world databases for face recognition do not have multiple images per person in the gallery, with just one image per subject in the gallery, this paper proposes a novel idea to overcome this challenge by 3D modeling from gallery images and synthesizing them for generating several images. Accordingly, a 3D model is initially reconstructed from frontal face images in a real-world gallery. Then, each 3D reconstructed face in the gallery is synthesized to several possible views and a sparse dictionary is generated based on the synthesized face image for each person. Also, a likeness dictionary is defined and its optimization problem is solved by the proposed method. Finally, the face recognition is performed for open-set face recognition using three proposed representation classifications. Promising results are achieved for face recognition across plastic surgery and look-alike faces on three databases including the plastic surgery face, look-alike face and LFW databases compared to several state-of-the-art methods. Also, several real-world and open-set scenarios are performed to evaluate the proposed method on these databases in real-world scenarios. This paper uses 3D reconstructed models to recognize look-alike faces.A feature is extracted from both facial reconstructed depth and texture images.This paper proposes likeness dictionary learning.Three open-set classification methods are proposed for real-world face recognition.

Face identification using some novel local descriptors under the influence of facial complexities

Abstract: This paper reports a face identification system for visible, look–alike and post–surgery face images of individuals using some novel variants which are exploited from local graph structure (LGS). The proposed LGS variants attempt to improve the performance of the face identification system under the influence of pose changes, facial expression changes, illumination variation, makeup, accessories (glasses) and facial complexity (look alike and plastic surgery). The idea is to represent each pixel along with its neighborhood pixels of a face image based on the regenerated directed local graph structure. From the newly defined local graph structure a binary pattern is generated for each pixel and this binary string is then converted into a decimal value and generates a transformed pattern. Finally, this transformed pattern is used to generate a concatenated histogram which is then used for matching and identification by using three well-known classifiers, namely, locally scaled sum of squared differences (LSSD), locally scaled sum of absolute differences (LSAD), and histogram intersection (HI). Unlike prior works, face images do not have to undergo the preprocessing stages as each novel variant deals with local structure of a face image by disregarding other effects. The UMIST, the JAFFE, the Extended Yale Face B, the Look-alike and the Plastic Surgery face databases are used for the evaluation. Extensive experiments on face databases exhibit promising and convincing results. Further, the experimental results have led to a robust identification system which is found to be invariant to different challenges made of due to capturing environment and face modality changes.

Biometric identification of identical twins: A survey

Abstract: The ability of biometric techniques to distinguish between identical twins is of interest for multiple reasons. The research literature touching on this topic is spread across a variety of areas. This survey pulls together the literature to date in this area, identifies available datasets for research, points out topics of uncertainty and suggests possible future research.

Face recognition system invariant to plastic surgery

Abstract: Facial plastic surgery changes facial features to large extend and thus creating a major problem to face recognition system. This paper proposes a new face recognition system using novel shape local binary texture (SLBT) feature from face images cascaded with periocular feature for plastic surgery invariant face recognition. In-spite of many uniqueness and advantages, the existing feature extraction methods are capable of extracting either shape or texture feature. A method which can extract both shape and texture feature is more attractive. The proposed SLBT can extract global shape, local shape and texture information from a face image by extracting local binary pattern (LBP) instead of direct intensity values from shape free patch of active appearance model (AAM). The experiments conducted using MUCT and plastic surgery face database shows that the SLBT feature performs better than AAM and LBP features. Further increase in recognition rate is achieved by cascading SLBT features from face with LBP features from periocular regions. The result from surgical and non-surgical face database shows that the proposed face recognition system can easily tackle illumination, pose, expression, occlusion and plastic surgery variations in face images.