A Tool Chain for the Active Shape Model
we present a tool chain to ease the use of the active shape models in applications. Active shape models (ASMs) are statistical models for deformable objects. They have been widely used for facial feature localization. However using an ASM is complex and requires a lot of work. This paper presents the design and implementation of a tool chain for ASMbased applications. It includes a labeling tool, a training tool, a fitting tool and a test tool. The labeling tool is used to label the features points in a face image and save the marked points to an annotation file very easily. The original code of training and fitting tools is open source from JIAPEI and we extend the fitting algorithm in our fitting tool. The test tool is used to divide the images into several groups by file names and apply crossvalidation to test the accuracy of fitted feature points. Based on this tool chain, we get the fitting result with limited required effect. Finally, we introduce a gender classification prototype application based on accurate feature points detected by the tool chain.
ASMs labeling tool training tool fitting tool test tool gender classification
Fan Zhang Ruimin Shen Lishuang Xu Gang Chen Jiajun Wang
Department of Computer Technology Shanghai Jiao Tong University Shanghai, China Continuing Education College Shanghai Jiao Tong University Shanghai, China
国际会议
南昌
英文
586-589
2012-08-26（万方平台首次上网日期，不代表论文的发表时间）