and color processing

ABSTRACT The purpose of our works is to provide fast and reliable face localization techniques in real time an in real-life scenes. Person localization is included in this problem. The end application sought is theability of mobile robots to navigate in human populated environments, and to start visual interactionwith them. Known methods are computationally intensive, far from real time implementation at nearfuture processing power of off-the-shelf processors. Our technique is based in motion segmentation.signature analysis and color processing. Signature analysis provides fast hints of the person and facelocalization. Color processing is used to confirm the face hypothesis, and it is based on our works onadaptive color quantization of image sequences. The technique can be implemented in real time and combined with other approaches to enhance the recognition results. keywords Color Processing, Face localization, Person localization 1 Introduction Most of the systems that dealt with some form of face information processing assume the facelocalization problem as solved, and work upon very restricted face images, most of them are likemugshots, with little background and constant scale. They impose2"4"6"7 very severe illuminationand position conditions in order to abstract from the tasks of face localization and registration. In

[1]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[2]  King Ngi Ngan,et al.  Locating facial region of a head-and-shoulders color image , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[3]  Bogdan Raducanu,et al.  An approach to face localization based on signature analysis , 1997, AVSP.

[4]  D. J. Myers,et al.  Image Feature Location in Multi-Resolution Images Using a Hierarchy of Multilayer Perceptrons , 1992 .

[5]  Shigeru Akamatsu,et al.  Automatic detection of human faces in natural scene images by use of a skin color model and of invariant moments , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[6]  J. B. Waite.  Training Multilayer Perceptrons for Facial Feature Location: A Case Study , 1992 .

[7]  Manuel Graña,et al.  A Sensitivity Analysis of the Self Organizing Maps as an Adaptive One-pass Non-stationary Clustering Algorithm: the Case of Color Quantization of Image Sequences , 1997, Neural Processing Letters.

[8]  Takeo Kanade,et al.  Human Face Detection in Visual Scenes , 1995, NIPS.

[9]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[10]  Masafumi Hagiwara,et al.  Human faces detection method using genetic algorithm , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[11]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[13]  Kyu Ho Park,et al.  Automatic human face location in a complex background using motion and color information , 1996, Pattern Recognit..

[14]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Rohini K. Srihari,et al.  Automatic Indexing and Content-Based Retrieval of Captioned Images , 1995, Computer.

[16]  Weimin Huang,et al.  Face detection based on color and local symmetry information , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[17]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[18]  Roberto Cipolla,et al.  Finding initial estimates of human face location , 1995 .

[19]  David G. Stork,et al.  Speechreading by Humans and Machines , 1996 .