The detection and recognition of objects in images is a key research topic in the computer vision community Within this area, face recognition and interpretation has attracted increasing attention owing to the possibility of unveiling human perception mechanisms, and for the development of practical biometric systems This book and the accompanying website, focus on template matching, a subset of object recognition techniques of wide applicability, which has proved to be particularly effective for face recognition applications Using examples from face processing tasks throughout the book to illustrate more general object recognition approaches, Roberto Brunelli: examines the basics of digital image formation, highlighting points critical to the task of template matching; presents basic and advanced template matching techniques, targeting grey-level images, shapes and point sets; discusses recent pattern classification paradigms from a template matching perspective; illustrates the development of a real face recognition system; explores the use of advanced computer graphics techniques in the development of computer vision algorithms Template Matching Techniques in Computer Vision is primarily aimed at practitioners working on the development of systems for effective object recognition such as biometrics, robot navigation, multimedia retrieval and landmark detection It is also of interest to graduate students undertaking studies in these areas

Template Matching Techniques in Computer Vision: Theory and Practice

/pdf/template-matching-techniques-in-computer-vision-433exjz3wi.pdf

Template Matching Techniques in Computer Vision

Where possible, automation has been a common response of humankind to many activities that have to be repeated numerous times. The routine identification of specimens of previously described species has many of the characteristics of other activities that have been automated, and poses a major constraint on studies in many areas of both pure and applied biology. In this paper, we consider some of the reasons why automated species identification has not become widely employed, and whether it is a realistic option, addressing the notions that it is too difficult, too threatening, too different or too costly. Although recognizing that there are some very real technical obstacles yet to be overcome, we argue that progress in the development of automated species identification is extremely encouraging that such an approach has the potential to make a valuable contribution to reducing the burden of routine identifications. Vision and enterprise are perhaps more limiting at present than practical constraints on what might possibly be achieved.

/pdf/automated-species-identification-why-not-3q3nh3ozor.pdf

Automated species identification: why not?

In this paper, we propose the use of lustering methods for automatic counting of pedestrians in video sequences. As input, we consider the output of those detection/tracking systems that overestimate the number of targets. Clustering techniques are applied to the resulting trajectories in order to reduce the bias between the number of tracks and the real number of targets. The main hypothesis is that those trajectories belonging to the same human body are more similar than trajectories belonging to different individuals. Several data representations and different distance/similarity measures are proposed and compared, under a common hierarchical clustering framework, and both quantitative and qualitative results are presented

/pdf/counting-pedestrians-in-video-sequences-using-trajectory-3ly0ost6lw.pdf

Counting Pedestrians in Video Sequences Using Trajectory Clustering

Illumination invariant face recognition

Human face recognition based on spatially weighted Hausdorff distance

Hausdorff distance is an efficient measure of the similarity of two point sets. We propose a modified Hausdorff distance measure for human face recognition. This modified Hausdorff distance measure incorporates information about the location of important facial features when comparing the edge maps of two facial images. The distance measure is weighted according to a weighted function derived from the spatial information of the human face. This distance measure, namely spatially weighted Hausdorff distance (SWHD), is further improved by combining it with the 'doubly' modified Hausdorff distance (M2HD). This new Hausdorff distance measure is called spatially weighted 'doubly' Hausdorff distance (SW2HD), which can alleviate the effect of facial expressions in human face recognition. Experiment results show that both the SWHD and SW2HD outperform the M2HD in recognition rate. The SW2HD can achieve the best recognition rate among the different Hausdorff distance measures. In our experiment, its recognition rates are 89%, 94%, and 98% for the first one, the first five, and the first ten likely matched faces, respectively. The average processing time for recognition of a human face is less than one second.

Human face recognition using a spatially weighted modified Hausdorff distance

We propose an efficient indexing structure for searching a human face in a large database. In our method, a set of eigenfaces is computed based on the faces in the database. Each face in the database is then ranked according to its projection onto each of the eigenfaces. A query input will be ranked similarly, and the corresponding nearest faces in the ranked position with respect to each of the eigenfaces are selected from the database. These selected faces will then form a small database, namely a condensed database, for face recognition, instead of considering the original large database. In the experiments, the effect of the number of eigenfaces used on the size of the condensed database is investigated. Experimental results show that the size of the condensed database is 35% of the original large database when 25% of the eigenfaces with the largest eigenvalues are selected. The processing time required to generate the condensed database is less than one second.

An efficient human face indexing scheme using eigenfaces

Hausdorff distance is an efficient measure of the similarity of two point sets. In this paper, we propose two new spatially weighted Hausdorff distance measures for human face recognition, namely, spatially eigen-weighted Hausdorff distance (SEWHD) and spatially eigen-weighted 'doubly' Hausdorff distance (SEW2HD). These new Hausdorff distances incorporate the information about the location of important facial features so that distances at those regions will be emphasized. The weighting function used in the Hausdorff distance measure is based on an eigenface, which has a large value at locations of important facial features and can reflect the face structure more effectively. Experimental results based on a combination of the ORL, MIT, and Yale face databases show that SEW2HD can achieve recognition rates of 83%, 90% and 92% for the first one, the first three and the first five likely matched faces, respectively, while the corresponding recognition rates of SEWHD are 80%, 83% and 88%, respectively.

A new approach using modified Hausdorff distances with eigenface for human face recognition

In this paper, an efticient automatic human face recognition system is proposed Fractal dimension is an efficient representation of texture which is used to locate the eyes in a human face We propose a modified approach to estimate the fractal dimensions which is less sensitive to lighting conditions and provides information about the orientation of an image under consideration Based on the position of the eyes, two face images are normalized, aligned and then compared by a new modified Hausdorff distance measure As different facial regions have different degrees of importance for face recognition, the modified Hausdorff distance is weighted according to a weighted function derived from the spatial information of the human face Experimental results show that our approach can achieve recognition rates of 76%, 84%, and 92% for the first one, the first five, first ten likely matched faces, respectively If the position of the eyes is selected manually, the corresponding recognition rates are 82%, 95% and 98%, respectively The average processing time for detecting the eyes and recognize a human face is less than two seconds

Kwan-Ho Lin

Papers

Human face recognition based on spatially weighted Hausdorff distance

Human face recognition using a spatially weighted modified Hausdorff distance

An efficient human face indexing scheme using eigenfaces

A new approach using modified Hausdorff distances with eigenface for human face recognition

Automatic Human Face Recognition System Using Fractal Dimension and Modified Hausdorff Distance