Authors: Remi Vieux Jenny BenoisPineau JeanPhilippe Domenger Achille Braquelaire
Publish Date: 2010/10/07
Volume: 60, Issue: 2, Pages: 305-326
Abstract
In this paper we study the problem of the detection of semantic objects from known categories in images Unlike existing techniques which operate at the pixel or at a patch level for recognition we propose to rely on the categorization of image segments Recent work has highlighted that image segments provide a sound support for visual object class recognition In this work we use image segments as primitives to extract robust features and train detection models for a predefined set of categories Several segmentation algorithms are benchmarked and their performances for segment recognition are compared We then propose two methods for enhancing the segments classification one based on the fusion of the classification results obtained with the different segmentations the other one based on the optimization of the global labelling by correcting local ambiguities between neighbor segments We use as a benchmark the Microsoft MSRC21 image database and show that our method competes with the current stateoftheart
Keywords: