The Semi-Explicit Shape Model for Multi-object Detection and Classification

We propose a model for classification and detection of object classes where the number of classes may be large and where multiple instances of object classes may be present in an image. The algorithm combines a bottom-up, low-level, procedure of a bag-of-words naive Bayes phase for winnowing out unlikely object classes with a high-level procedure for detection and classification. The high-level process is a hybrid of a voting method where votes are filtered using beliefs computed by a class-specific graphical model. In that sense, shape is both explicit (determining the voting pattern) and implicit (each object part votes independently) -- hence the term "semi-explicit shape model".

• Type: Conference
• Year: 2010
• Where: ECCV
• Keywords: Bag-of-words Naive Bayes, Computer Vision, ECCV 2010, Object Classes, Unlikely Object Classes