Elastic graph matching has been proposed as a practical implementation of dynamic link matching, which is a neural network with dynamically evolving links between a reference model and an input image. Each node of the graph contains features that characterize the neighborhood of its location in the image. The elastic graph matching usually consists of two consecutive steps, namely a matching with a rigid grid, followed by a deformation of the grid, which is actually the elastic part. The deformation step is introduced in order to allow for some deformation, rotation, and scaling of the object to be matched. This method is applied here to the authentication of human faces where candidates claim an identity that is to be checked. The matching error as originally suggested is not powerful enough to provide satisfying results in this case. We introduce an automatic weighting of the nodes according to their significance. We also explore the significance of the elastic deformation for an application of face-based person authentication. We compare performance results obtained with and without the second matching step. Results show that the deformation step slightly increases the performance, but has lower influence than the weighting of the nodes. The best results are obtained with the combination of both aspects. The results provided by the proposed method compare favorably with two methods that require a prior geometric face normalization, namely the synergetic and eigenface approaches.

The system presented here is a specialized version of a general object recognition system. Images of faces are represented as graphs, labeled with topographical information and local templates. Different poses are represented by different graphs. New graphs of faces are generated by an elastic graph matching procedure comparing the new face with a set of precomputed graphs: the "general face knowledge". The final phase of the matching process can be used to generate composite images of faces and to determine certain features represented in the general face knowledge, such as gender or the presence of glasses or a beard. The graphs can be compared by a similarity function which makes the system efficient in recognizing faces. 1 Introduction Face recognition systems can be subdivided into two main categories [1] depending on the nature of the coding of an input picture and its processing. Schemes that use pixels (grey-level values) as the basis for their coding and various forms of sta...

We propose a framework and a complete implementation of a translation and scale invariant image recognition system for natural indoor scenes. The system employs higher order autocorrelation features of scale space data which permit linear classification. An optimal linear classification method is presented, which is able to cope with a large number of classes represented by many, as well as very few samples. In the course of the analysis of our system, we examine which numerical methods for feature transformation and classification show sufficient stability to fulfill these demands. The implementation has been extensively tested. We present the results of our own application and several classification benchmarks. Image recognition Face recognition Scale invariancy Scale space Higher order autocorrelation Optimal linear classification 1. INTRODUCTION The task of visual recognition which was defined by Marr (1) with the question: "What objects are where in the environment?" is still ...

Facial landmarks such as eye corners, mouth corners or nose edges are important features for many applications in face recognition. The exact detection of these landmarks, however, is not an easy task because of the high individual variability of facial images and therefore, of the tremendous complexity of all the low-level features existing within the image. For instance, a precise and reliable detection of the eye corners has not been successfully solved until now. However, the knowledge of the exact position of these landmarks in the facial image is important for many matching and face processing tasks. For the classification and discrimination of dysmorphic facial signs a precise and reliable detection of a certain set of anatomical facial landmarks is particularly necessary. For this, an attentive processing strategy has been developed which puts the focus of the processing on only those salient image areas which are really needed to solve the several subtasks. The fundamental idea of the approach presented is to concentrate the artificial attention upon only a small fraction of the existing low-level features within a spatially well restricted image area.

We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals over certain geometric sets. We show that image warping, Radon transform, trace transform, etc. are special cases of our definition. Moreover, three different types of GeTs are designed to handle deformation, articulation and occlusion and applied to fingerprinting the appearance inside a contour. They include the contour-driven GeT, the feature curve based GeT and selecting functionals to model the appearance inside the convex hull of the contour. A multi-resolution representation that combines both shape and appearance information is also proposed. We apply our approach to image synthesis and object recognition. The proposed approach produces promising results when applied to fingerprinting the appearance of human and body parts despite the challenges due to articulated motion and deformations. 1.

A discriminative and robust feature—kernel enhanced informative Gabor feature—is proposed in this paper for face recognition. Mutual information is applied to select a set of informative and nonredundant Gabor features, which are then further enhanced by kernel methods for recognition. Compared with one of the top performing methods in the 2004 Face Verification Competition (FVC2004), our methods demonstrate a clear advantage over existing methods in accuracy, computation efficiency, and memory cost. The proposed method has been fully tested on the FERET database using the FERET evaluation protocol. Significant improvements on three of the test data sets are observed. Compared with the classical Gabor wavelet-based approaches using a huge number of features, our method requires less than 4 milliseconds to retrieve a few hundreds of features. Due to the substantially reduced feature dimension, only 4 seconds are required to recognize 200 face images. The paper also unified different Gabor filter definitions and proposed a training sample generation algorithm to reduce the effects caused by unbalanced number of samples available in different classes. Copyright © 2006 Hindawi Publishing Corporation. All rights reserved. 1.

Automated face recognition has a long history within the field of computer vision, and there have been several different classes of approaches to the problem. It has been about fifteen years since the “Eigenfaces ” method first made an impression on the computer vision research community and helped spur interest in appearance-based recognition, biometrics and vision-based humancomputer interface. In this chapter I give a personal view of the original context and motivation for the work, some of the strengths and limitations of the approach, and progress in the years since. The original Eigenfaces approach was in many respects a reaction to the feature-based approaches to face recognition prevalent in the mid-1980s. Appearance-based approaches to recognition complement feature- or shape-based approaches, and a practical face recognition system should have elements of both. Eigenfaces should not be viewed as a general approach to recognition, but rather one tool out of many to be applied and evaluated in the appropriate context. 1.

We've been developing a Chinese OCR engine for machine printed documents. Currently, our OCR engine can support a vocabulary of 6921 characters which include 6707 simplified Chinese characters in GB2312-80, 12 frequently used GBK Chinese characters, 62 alphanumeric characters, 140 punctuation marks and symbols. The supported font styles include Song, Fang Song, Kai, He, Yuan, LiShu, WeiBei, XingKai, etc. The averaged character recognition accuracy is above 99% for newspaper quality documents with a recognition speed of about 250 characters per second on a Pentium III-450MHz PC yet only consuming less than 2MB memory. In this paper, we describe the key technologies we used to construct the above recognizer. Among them, we highlight three key techniques contributing to the high recognition accuracy, namely the use of Gabor features, the use of discriminative feature extraction, and the use of minimum classification error as a criterion for model training. 1.

The system presented here is a specialized version of a general object recognition system. Images of faces are represented as graphs, labeled with topographical information and local templates. Di erent poses are represented by di erent graphs. New graphs of faces are generated by an elastic graph matching procedure comparing the new face with a set of precomputed graphs: the \general face knowledge". The nal phase of the matching process can be used to generate composite images of faces and to determine certain features represented in the general face knowledge, such as gender or the presence of glasses or a beard. The graphs can be compared by a similarity function which makes the system e cient in recognizing faces. 1

This paper develops a novel face recognition technique