Keshav Seshadri

Robust modified Active Shape Model for automatic facial landmark annotation of frontal faces

In this paper we present an improved method for locating facial landmarks in images containing frontal faces using a modified Active Shape Model. Our main contributions include the use of an optimal number of facial landmark points, better profiling methods during the fitting stage and the development of a more suitable optimization metric to determine the best location of the landmarks compared to the simplistic minimum Mahalanobis distance criteria used to date. We build a subspace to model variations of appearance around each facial landmark and use this subspace to enhance the accuracy of the fitting process around each landmark. This enhancement provides a significant improvement in fitting and simultaneously determines which points were poorly fitted using reconstruction error, thus allowing for automatic correction or interpolation of any poorly fitted points. Our implementation, with the above mentioned improvements, leads to extremely accurate results even when dealing with faces with expressions, slight pose variations and in-plane rotations. Experiments conducted on test sets drawn from three databases (NIST Multiple Biometric Grand Challenge-2008 (MBGC-2008), CMU Multi-PIE and the Japanese Female Facial Expression (JAFFE) database) show that our proposed approach leads to far better performance compared to the classical Active Shape Model of Cootes et al. and other traditional methods and provides a robust automatic facial landmark annotation which is the first critical step in face registration, pose correction and face recognition.

Contourlet appearance model for facial age estimation

In this paper we propose a novel Contourlet Appearance Model (CAM) that is more accurate and faster at localizing facial landmarks than Active Appearance Models (AAMs). Our CAM also has the ability to not only extract holistic texture information, as AAMs do, but can also extract local texture information using the Nonsubsampled Contourlet Transform (NSCT). We demonstrate the efficiency of our method by applying it to the problem of facial age estimation. Compared to previously published age estimation techniques, our approach yields more accurate results when tested on various face aging databases.

Driver cell phone usage detection on Strategic Highway Research Program (SHRP2) face view videos

The harmful effects of cell phone usage on driver behavior have been well investigated and the growing problem has motivated several several research efforts aimed at developing automated cell phone usage detection systems. Computer vision based approaches for dealing with this problem have only emerged in recent years. In this paper, we present a vision based method to automatically determine if a driver is holding a cell phone close to one of his/her ears (thus keeping only one hand on the steering wheel) and quantitatively demonstrate the methods efficacy on challenging Strategic Highway Research Program (SHRP2) face view videos from the head pose validation data that was acquired to monitor driver head pose variation under naturalistic driving conditions. To the best of our knowledge, this is the first such evaluation carried out using this relatively new data. Our approach utilizes the Supervised Descent Method (SDM) based facial landmark tracking algorithm to track the locations of facial landmarks in order to extract a crop of the region of interest. Following this, features are extracted from the crop and are classified using previously trained classifiers in order to determine if a driver is holding a cell phone. We adopt a through approach and benchmark the performance obtained using raw pixels and Histogram of Oriented Gradients (HOG) features in combination with various classifiers.

An Analysis of the Sensitivity of Active Shape Models to Initialization When Applied to Automatic Facial Landmarking

Active Shape Models (ASMs) have recently gained popularity for performing automatic facial landmark fitting. Their demonstrated ability to generalize and fit unseen faces make them ideal candidates for this task unlike the traditional Active Appearance Model (AAM)-based approaches, which have difficulty in accurately landmarking unseen images. Given a test image, a face detector is used to determine the locations, orientations and sizes of faces in the image. Facial landmarking algorithms, such as ASMs, are initialized based on these parameters. In this paper, we conduct a series of experiments to exhaustively evaluate the tolerance of three popular ASMs to initialization perturbations (translation, rotation, and scaling in size) of the face detected, a topic that has not been analyzed in depth to date. Our results are consistent across different databases, provide an understanding of the role initialization plays in the landmark fitting process and serve as a performance gauge that could be considered when comparing facial landmarking algorithms.

A facial aging approach to identification of identical twins

Biometric recognition based on the characteristics of human faces has attracted a great deal of attention over the past few years. However, the similarity in the facial appearance of identical twins has made the task difficult and has even compromised commercial face recognition systems. In this paper, we shed new light on the study of facial recognition of identical twins and propose a novel approach using twins group classification and facial aging features to tell them apart. Our experiments, conducted on the University of Notre Dame ND-twins database, that was acquired over two years (2009 and 2010), indicate that our proposed approach demonstrates good generalization ability and high identification rates.

Beard and mustache segmentation using sparse classifiers on self-quotient images

In this paper, we propose a novel system for beard and mustache detection and segmentation in challenging facial images. Our system first eliminates illumination artifacts using the self-quotient algorithm. A sparse classifier is then used on these self-quotient images to classify a region as either containing skin or facial hair. We conduct experiments on the MBGC and color FERET databases to demonstrate the effectiveness of our proposed system.

Facial aging and asymmetry decomposition based approaches to identification of twins

A reliable and accurate biometric identification system must be able to distinguish individuals even in situations where their biometric signatures are very similar. However, the strong similarity in the facial appearance of twins has complicated facial feature based recognition and has even compromised commercial face recognition systems. This paper addresses the above problem and proposes two novel methods to distinguish identical twins using (1) facial aging features and (2) asymmetry decomposition features. Facial aging features are extracted using Gabor filters from regions of the face that typically exhibit wrinkles and laugh lines, while Facial asymmetry decomposition based features are obtained by projecting the difference between the two left sides (consisting of the left half of the face and its mirror) and two right sides (consisting of the right half of the face and its mirror) of a face onto a subspace. Feature vectors obtained using these methods were used for classification. Experiments conducted on images of five types of twins from the University of Notre Dame ND-Twins database indicate that both our proposed approaches achieve high identification rates and are hence quite promising at distinguishing twins. HighlightsThe proposal of two novel approaches to distinguishing identical twins.Facial aging and intrinsic facial symmetry features are sued.A thorough evaluation on a challenging database.The summarizing of existing techniques and the results obtained by them.

An analysis of facial shape and texture for recognition: A large scale evaluation on FRGC ver2.0

Traditional approaches to face recognition have utilized aligned facial images containing both shape and texture information. This paper analyzes the contributions of the individual facial shape and texture components to face recognition. These two components are evaluated independently and we investigate methods to combine the information gained from each of them to enhance face recognition performance. The contributions of this paper are the following: (1) to the best of our knowledge, it is the first large-scale study of how face recognition is influenced by shape and texture as all of our results are benchmarked against traditional approaches on the challenging NIST FRGC ver2.0 experiment 4 dataset, (2) we empirically show that shape information is reasonably discriminative, (3) we demonstrate significant improvement in performance by registering texture with dense shape information, and finally (4) show that fusing shape and texture information consistently boosts recognition results across different subspace-based algorithms.

Facecut - a robust approach for facial feature segmentation

Segmentation of facial features is a key pre-processing step in enabling facial recognition, building of 3D facial models, expression analysis, and pose estimation. Recently, graph cuts based algorithms have been adapted to carry out this task but many of these methods require manual initialization of points in the foreground and background. In this paper, we propose a novel and fully automatic approach, named Face-Cut, to perform accurate facial feature segmentation. FaceCut combines the positive features of the Modified Active Shape Model (MASM) and GrowCut algorithms to ensure highly accurate and completely automatic segmentation of facial features. We demonstrate the effectiveness of FaceCut on images from two challenging databases.