GESTALT-INSPIRED FEATURES EXTRACTION FOR OBJECT CATEGORY RECOGNITION

International audienceWe propose a methodology inspired by Gestalt laws to ex- tract and combine features and we test it on the object cat- egory recognition problem. Gestalt is a psycho-visual the- ory of Perceptual Organization that aims to explain how vi- sual information is organized by our brain. We interpreted its laws of homogeneity and continuation in link with shape and color to devise new features beyond the classical proxim- ity and similarity laws. The shape of the object is analyzed based on its skeleton (good continuation) and as a measure of homogeneity, we propose self-similarity enclosed within shape computed at super-pixel level. Furthermore, we pro- pose a framework to combine these features in different ways and we test it on Caltech 101 database. The results are good and show that such an approach improves objectively the ef- ficiency in the task of object category recognition