Multiobjective design of operators that detect points of interest in images

In this paper, a multiobjective (MO) learning approach to image feature extraction is described, where Pareto-optimal interest point (IP) detectors are synthesized using genetic programming (GP). IPs are image pixels that are unique, robust to changes during image acquisition, and convey highly descriptive information. Detecting such features is ubiquitous to many vision applications, e.g. object recognition, image indexing, stereo vision, and content based image retrieval. In this work, candidate IP operators are automatically synthesized by the GP process using simple image operations and arithmetic functions. Three experimental optimization criteria are considered: 1) the repeatability rate; 2) the amount of global separability between IPs; and 3) the information content captured by the set of detected IPs. The MO-GP search considers Pareto dominance relations between candidate operators, a perspective that has not been contemplated in previous research devoted to this problem. The...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Leonardo Trujillo, Gustavo Olague, Evelyne Lutton, Francisco Fernández de Vega
• Keywords: Content Based Image Retrieval, GECCO 2008, Image, Image Feature Extraction, Optimization