Class Specific Threshold Selection in Face Space Using Set Estimation Technique for RGB Color Components
15 Dec 2009-pp 351-356
TL;DR: A novel thresholding technique for classification, where the query image is not necessarily classified to one of the classes in the training set, is introduced, and the proposed class specific threshold based technique performs better than the non threshold based systems using subspace algorithms.
Abstract: In conventional face recognition techniques, any query image is always classified to one of the face classes irrespective of whether the query image is a face or not. Most of the recognition algorithms are dissimilarity based, and one needs to put a proper threshold on the dissimilarity value for the sake of classification. In this paper, we have introduced a novel thresholding technique for classification, where the query image is not necessarily classified to one of the classes in the training set. The theoretical formulation of the thresholding technique and its utility are demonstrated on color face and non face datasets with RGB color components as features in the subspace. The proposed threshold selection is based on statistical method of set estimation and is guided by minimal spanning tree. Experiment shows that the proposed class specific threshold based technique performs better than the non threshold based systems using subspace algorithms.
Citations
More filters
TL;DR: In this paper set estimation technique is applied for generation of 2D face images on the basis of inheriting features from inter and intra face classes in face space using nearest neighbor classifier.
Abstract: In this paper set estimation technique is applied for generation of 2D face images. The synthesis is done on the basis of inheriting features from inter and intra face classes in face space. Face images without artifacts and expressions are transformed to images with artifacts and expressions with the help of the developed methods. Most of the test images are generated using the proposed method. The measured PSNR values for the generated faces with respect to the training faces reflect the well accepted quality of the generated images. The generated faces are also classified properly to their respective face classes using nearest neighbor classifier. Validation of the method is demonstrated on AR and FIA datasets. Classification accuracy is increased when the new generated faces are added to the training set.
5 citations
Cites methods from "Class Specific Threshold Selection ..."
...Minimal spanning tree as a tool ofset estimation method [16]...
[...]
References
More filters
TL;DR: In this paper, the authors provide an up-to-date critical survey of still-and video-based face recognition research, and provide some insights into the studies of machine recognition of faces.
Abstract: As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.
6,384 citations
[...]
01 Jan 1998
3,650 citations
"Class Specific Threshold Selection ..." refers methods in this paper
...The proposed method of threshold based classification has been used for open and closed test face identification and tested over the well known color AR face database [11] and one object (i....
[...]
01 Jan 1996
TL;DR: Columbia Object Image Library COIL is a database of color images of objects that were placed on a motorized turntable against a black background and rotated through degrees to vary object pose with respect to a xed color camera.
Abstract: Columbia Object Image Library COIL is a database of color images of objects The objects were placed on a motorized turntable against a black background The turntable was rotated through degrees to vary object pose with respect to a xed color camera Images of the objects were taken at pose intervals of degrees This corresponds to poses per object The images were size normalized COIL is available online via ftp
1,891 citations
TL;DR: A generalization of the convex hull of a finite set of points in the plane leads to a family of straight-line graphs, "alpha -shapes," which seem to capture the intuitive notions of "fine shape" and "crude shape" of point sets.
Abstract: A generalization of the convex hull of a finite set of points in the plane is introduced and analyzed. This generalization leads to a family of straight-line graphs, " \alpha -shapes," which seem to capture the intuitive notions of "fine shape" and "crude shape" of point sets. It is shown that a-shapes are subgraphs of the closest point or furthest point Delaunay triangulation. Relying on this result an optimal O(n \log n) algorithm that constructs \alpha -shapes is developed.
1,648 citations