Srinivas Gutta

Gender and ethnic classification of face images

The paper considers hybrid classification architectures for gender and ethnic classification of human faces and shows their feasibility using a collection of 3006 face images corresponding to 1009 subjects from the FERET database. The hybrid approach consists of an ensemble of RBF networks and inductive decision trees (DT). Experimental cross validation (CV) results yield on average accuracy rate of (a) 96% on the gender classification task and (b) 94% on the ethnic classification task. The benefits of the hybrid architecture include (i) robustness via query by consensus provided by the ensembles of RBF networks, and (ii) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds provided by using only DT.

Detection of human faces using decision trees

The paper proposes a novel algorithm for face detection using decision trees (DT) and shows its generality and feasibility using a database consisting of 2340 face images from the FERET database (corresponding to 817 subjects and including 190 sets of duplicates) over a semi-uniform background. The approach used for face detection involves three main stages, those of location, cropping, and post-processing. The first stage finds a rough approximation for the possible location of the face box, the second stage will refine it, and the last stage decider whether a face is present in the image and if the answer is positive would normalize the face image. The algorithm does not require multiple (scale) templates and the accuracy achieved is 96%. Accuracy is based on the visual observation that the face box includes both eyes, nose, and mouth, and that the top side of the box is below the hairline. Experiments were also performed to assess the accuracy of the algorithm in rejecting images where no face is present. Using a small database of 25 images of various but complex backgrounds the algorithm failed on two images for an overall accuracy rate of 92%.

Face recognition using hybrid classifier systems

This paper considers hybrid classification architectures and shows their feasibility on large databases consisting of facial images. Our architecture, consists of an ensemble of connectionist networks-radial basis functions (RBF)-and decision trees (DT). This architecture enjoys robustness via (i) consensus provided by ensembles of RBF networks, and (ii) categorical classification using decision trees. The results reported in this paper on automatic face recognition using the FERET database are encouraging when one considers that the size of our test bed is in excess of 350 subjects and the great variability of the database. In addition we have also demonstrated the feasibility of our approach on queries aimed at the retrieval of frames (images) using contextual cues.

Face recognition using hybrid classifiers

We address the problem of surveillance and contents-based image retrieval (CBIR) for large image databases consisting of face images. The corresponding face recognition tasks considered herein include (i) surveying a gallery of images for the presence of specific probes. (ii) CBIR, and (iii) CBIR subject to correct ID (“match”) displaying specific facial landmarks such as wearing glasses. We developed robust matching (“classification”) and retrieval schemes based on hybrid classifiers and showed their feasibility using the FERET database. The hybrid classifier architecture consists of an ensemble of connectionist networks—radial basis functions (RBF)—and inductive decision trees (DT). The specific characteristics of our hybrid architecture include (a) query by consensus as provided by ensembles of networks for coping with the inherent variability of the image formation and data acquisition process, (b) categorical classifications using decision trees, (c) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds, and (d) interpretability of the way classification and retrieval are eventually achieved. Experimental results, proving the feasibility of our approach, yield (i) 96% accuracy, using cross validation, for surveillance on a database consisting of 904 images corresponding to 350 subjects (of whom 102 are duplicates), (ii) 97% accuracy for CBIR tasks, such as “find all subjects wearing glasses”, on a database of 1084 images (including noisy versions) of 350 subjects (of whom 102 are duplicates), and (iii) 93% accuracy, using cross validation, for CBIR subject to correct ID match tasks, such as “find Joe Smith with/without glasses”, on a database of 200 images.

Automatic Video-based Person Authentication Using the RBF Network

As more and more forensic information becomes available on video we address in this paper the Automatic Video-Based Biometric Person Authentication (AVBPA). Possible tasks and application scenarios under consideration involve detection and tracking of humans and human (ID) verification. Authentication corresponds to ID verification and involves actual (face) recognition for the subject(s) detected in the video sequence. The architecture for AVBPA takes advantage of the active vision paradigm and it involves difference methods or optical flow analysis to detect the moving subject, projection analysis and decision trees (DT) for face location, and connectionist network — Radial Basis Function (RBF) for authentication. Subject detection and face location correspond to video break and key frame detection, respectively, while recognition itself corresponds to authentication. The active vision paradigm is most appropriate for video processing where one has to cope with huge amounts of image data and where further sensing and processing of additional frames is feasible. As a result of such an approach video processing becomes feasible in terms of decreased computational resources (‘time’) spent and increased confidence in the (authentication) decisions reached despite sometime poor quality imagery. Experimental results on three FERET video sequences prove the feasibility of our approach.

Face and hand gesture recognition using hybrid classifiers

This paper advances the methodology of hybrid classification architectures for face and hand gesture recognition tasks and shows their feasibility through experimental studies using the FERET data base and gesture images. The hybrid architecture, consisting of an ensemble of connectionist networks-radial basis functions (RBF)-and inductive decision trees (DT), combines the merits of holistic template matching with those of abstractive matching using discrete features and subject to both positive and negative learning. The hybrid architecture, quite general as it applies to both face and hand gesture recognition, derives its robustness from (i) consensus using ensembles of RBF network;, and (ii) flexible matching using categorical classification via decision trees. The experimental results, proving the feasibility of our approach, yield (i) 93% accuracy, using cross validation, for contents-based image retrieval (CBIR) subject to correct ID matching tasks, such as find Joe Smith with/without glasses, on a data bate of 200 images, and (ii) 96% accuracy using cross validation, for forensic verification on a data base consisting of 102 images corresponding to 350 subjects (of whom 102 are duplicates). Cross validation results on the hand gesture recognition task yield a false negative rate of 3.6% and a false positive rate of 1.8%, using a data base of 750 images corresponding to 25 hand gestures.

Face recognition using ensembles of networks

We describe a novel approach for fully automated face recognition and show its feasibility on a large database of facial images (FERET). Our approach, based on a hybrid architecture consisting of an ensemble of radial basis function (RBF) neural networks and inductive decision trees, combines the merits of abstractive features with those of holistic template matching. The benefits of our architecture include: 1) robust detection of facial landmarks using decision trees, and 2) robust face recognition using consensus methods over ensembles of RBF networks. Experiments carried out using k-fold cross validation on a large database consisting of 748 images corresponding to 374 subjects, among them 11 duplicates, yield on the average 87% correct match, and 99% correct surveillance (verification).

Hand Gesture Recognition using Ensembles of Radial Basis Function (RBF) Networks and Decision Trees

Hand gestures are the natural form of communication among people, yet human-computer interaction is still limited to mice movements. The use of hand gestures in the field of human-computer interaction has attracted renewed interest in the past several years. Special glove-based devices have been developed to analyze finger and hand motion and use them to manipulate and explore virtual worlds. To further enrich the naturalness of the interaction, different computer vision-based techniques have been developed. At the same time the need for more efficient systems has resulted in new gesture recognition approaches. In this paper we present an hybrid intelligent system for hand gesture recognition. The hybrid approach consists of an ensemble of connectionist networks — radial basis functions (RBF) — and inductive decision trees (AQDT). Cross Validation (CV) experimental results yield a false negative rate of 1.7% and a false positive rate of 1% while the evaluation takes place on a data base including 150 images corresponding to 15 gestures of 5 subjects. In order to assess the robustness of the system, the vocabulary of the gestures has been increased from 15 to 25 and the size of the database from 150 to 750 images corresponding now to 15 subjects. Cross Validation (CV) experimental results yield a false negative rate of 3.6% and a false positive rate of 1.8% respectively. The benefits of our hybrid architecture include (i) robustness via query by consensus as provided by ensembles of networks when facing the inherent variability of the image formation and data acquisition process, (ii) classifications made using decision trees, (iii) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds and (iv) interpretability of the way classification and retrieval is eventually achieved.

Gender classification of human faces using hybrid classifier systems

This paper considers a hybrid classification architectures for gender classification of human faces and shows its feasibility using a collection of 2000 face images from the FERET database (corresponding to 700 male and 300 female subjects). The hybrid approach consists of an ensemble of RBF networks and inductive decision trees (DT). Specifically cross validation (CV) experimental results yield an average accuracy rate of 94% for the hybrid architecture consisting of ensemble of RBF networks (Model 2) and decision trees (C4.5). The benefits of our hybrid architecture, beyond the high accuracy achieved, include: (i) robustness via query by consensus provided by the ensembles of RBF networks, and (ii) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds provided by DT.

Automated face recognition

Access control and authentication techniques were developed within the framework of face recognition. The corresponding face recognition tasks considered herein include, (1) surveilling a gallery of images for the presence of specific probes, and (2) CBIR subject to correct ID (match) displaying specific facial landmarks such as wearing glasses. We describe a novel approach for fully automated face recognition and show its feasibility on a large data base of facial images (FERET). Our approach, based on a hybrid architecture consisting of an ensemble of connectionist networks -- radial basis functions (RBF) -- and inductive decision trees (DT), combines the merits of discrete and abstractive features with those of holistic template matching. Training for face detection takes place over both positive and negative examples. The benefits of our architecture include (1) detection of faces using decision trees, and (2) robust face recognition using consensus methods over ensembles of RBF networks. Experimental results, proving the feasibility of our approach, yield (1) 96% accuracy, using cross validation, for surveillance on a data base consisting of 904 images corresponding to 350 subjects, and (2) 93% accuracy, using cross validation, for CBIR subject to correct ID match tasks on a data base of 200 images.