%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2012/07.10.00.53
%2 sid.inpe.br/sibgrapi/2012/07.10.00.53.06
%@doi 10.1109/SIBGRAPI.2012.20
%T Multi-Scale Spectral Residual Analysis to Speed up Image Object Detection
%D 2012
%A Silva Filho, José Grimaldo da,
%A Schnitman, Leizer,
%A Oliveira, Luciano Rebouças de,
%@affiliation Universidade Federal da Bahia
%@affiliation Universidade Federal da Bahia
%@affiliation Universidade Federal da Bahia
%E Freitas, Carla Maria Dal Sasso ,
%E Sarkar, Sudeep ,
%E Scopigno, Roberto ,
%E Silva, Luciano,
%B Conference on Graphics, Patterns and Images, 25 (SIBGRAPI)
%C Ouro Preto, MG, Brazil
%8 22-25 Aug. 2012
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K multi-scale spectral residue, saliency, person detection.
%X Accuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-off between detection performance and fast execution commonly represents the ultimate goal of an object detector in real life applications. In this present work, we propose a novel method toward that goal. The proposed method was grounded on a multi-scale spectral residual (MSR) analysis for saliency detection. Compared to a regular sliding window search over the images, in our experiments, MSR was able to reduce by 75% (in average) the number of windows to be evaluated by an object detector. The proposed method was thoroughly evaluated over a subset of LabelMe dataset (person images), improving detection performance in most cases.
%@language en
%3 PID2440145.pdf