Incorporating multiple distance spaces in optimum-path forest classification to improve feedback-based learning

• Published in: Computer vision and image understanding Vol. 116; no. 4; pp. 510 - 523
• Main Authors: da Silva, André Tavares, dos Santos, Jefersson Alex, Falcão, Alexandre Xavier, Torres, Ricardo da S., Magalhães, Léo Pini
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01-04-2012; Elsevier
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Composite descriptor; Computer science; control theory; systems; Content-based image retrieval; Exact sciences and technology; Genetic programming; Image pattern analysis; Learning; Mathematical analysis; Mathematical models; Multi-scale parameter search; Optimization; Optimum-path forest classifiers; Pattern recognition. Digital image processing. Computational geometry; Representations; Retrieval; Optimum-path forest classifiers; Image pattern analysis; Composite descriptor; Multi-scale parameter search; Content-based image retrieval; Genetic programming; Image processing; Hierarchical classification; Image retrieval; Evolutionary algorithm; Case based reasoning; Optimization; Relevance; Image analysis; Scale parameter; Genetic algorithm; Efficiency; Content-based retrieval; Pattern analysis; Distance; Content analysis
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2011.12.001

► Two feedback-based learning methods based on OPF and multiple distance space. ► They solve image retrieval in a few iterations of relevance feedback. ► Considerable gains in effectiveness are demonstrated.
In content-based image retrieval (CBIR) using feedback-based learning, the user marks the relevance of returned images and the system learns how to return more relevant images in a next iteration. In this learning process, image comparison may be based on distinct distance spaces due to multiple visual content representations. This work improves the retrieval process by incorporating multiple distance spaces in a recent method based on optimum-path forest (OPF) classification. For a given training set with relevant and irrelevant images, an optimization algorithm finds the best distance function to compare images as a combination of their distances according to different representations. Two optimization techniques are evaluated: a multi-scale parameter search (MSPS), never used before for CBIR, and a genetic programming (GP) algorithm. The combined distance function is used to project an OPF classifier and to rank images classified as relevant for the next iteration. The ranking process takes into account relevant and irrelevant representatives, previously found by the OPF classifier. Experiments show the advantages in effectiveness of the proposed approach with both optimization techniques over the same approach with single distance space and over another state-of-the-art method based on multiple distance spaces.