Combining heterogeneous features for face detection using multiscale feature selection with binary particle swarm optimization
We propose a fast multiscale face detector that boosts a set of SVM-based hierarchy classifiers constructed with two heterogeneous features, i.e. Multi-block Local Binary Patterns (MB-LBP) and Speeded Up Robust Features (SURF), at different image resolutions. In this hierarchical architecture, simple and fast classifiers using efficient MB-LBP descriptors remove large parts of the background in low and intermediate scale layers, thus only a small percentage of background patches look similar to faces and require a more accurate but slower classifier that uses distinctive SURF descriptor to avoid false classifications in the finest scale. By propagating only those patterns that are not classified as background, we can quickly decrease the amount of data need to be processed. To lessen the training burden of the hierarchy classifier, in each scale layer, a feature selection scheme using Binary Particle Swarm Optimization (BPSO) searches the entire feature space and filters out the minimum number of discriminative features that give the highest classification rate on a validation set, then these selected distinctive features are fed into the SVM classifier. We compared detection performance of the proposed face detector with other state-of-the-art methods on the CMU+MIT face dataset. Our detector achieves the best overall detection performance. The training time of our algorithm is 60 times faster than the standard Adaboost algorithm. It takes about 70 ms for our face detector to process a 320×240 image, which is comparable to Viola and Jones’ detector.
Face detection feature selection binary particle swarm optimization
Hong Pan Si-Yu Xia Li-Zuo Jin Liang-Zheng Xia
School of Automation, Southeast University, Nanjing, China, 210096
国际会议
桂林
英文
1-6
2011-11-01（万方平台首次上网日期，不代表论文的发表时间）