题目:Cascaded face alignment via intimacy definition feature

报告人:Prof. Kenneth K.M. Lam
Department of Electronic and Information Engineering
The Hong Kong Polytechnic University  Hong Kong

邀请人:邱国平教授

时间:2017年11月27日(周一)15:00

地点:深圳大学南区基础实验楼北座信息工程学院N710会议室

摘要:
Recent years have witnessed the emerging popularity of regression-based face aligners, which directly learn mappings between facial appearance and shape-increment manifolds. In this talk, I will introduce a random-forest-based, cascaded regression model for face alignment by using a novel locally lightweight feature, namely intimacy definition feature (IDF). This feature is more discriminative than the pose-indexed feature, more efficient than the histogram of oriented gradients (HOG) feature and the scale-invariant feature transform (SIFT) feature, and more compact than the local binary feature (LBF). Experimental validation of the algorithm shows that it achieves state-of-the-art performance when testing on some challenging datasets. Compared with the LBF-based algorithm, the method achieves about twice the speed, 20% improvement in terms of alignment accuracy, and save an order of magnitude on memory requirement.

欢迎各位老师和同学参加。