%0 Journal Article
%T Combined Object Detection and Segmentation
%A Jarich Vansteenberge
%A Masayuki Mukunoki
%A Michihiko Minoh
%J International Journal of Machine Learning and Computing
%D 2013
%I IACSIT Press
%R 10.7763/ijmlc.2013.v3.273
%X We develop a method for combined object detection and segmentation in natural scene. In our approach segmentation and detection are considered as two faces of the same coin that should be combined into a single framework. There are two main steps in our strategy. First we focus on the learning of a visual vocabulary that efficiently encompasses objects¡¯ appearance, spatial configuration and underlying segmentation. This vocabulary is used within a Hough voting framework to produces object¡¯s configuration. The second step consists in searching for valid objects¡¯ configurations by interpreting and scoring them in terms of both detection and segmentation. This allows us to prune false detections and hallucinated object-like segmentation. Experiments show the advantage of the combined approach and the improvements over recent related methods.
%K Object recognition
%K random forest
%K hough votes.
%U http://www.ijmlc.org/index.php?m=content&c=index&a=show&catid=35&id=270