A Generic Object Detection Using a Single Query Image Without Training

作     者：Bin Xiong Xiaoqing Ding 

作者机构：State Key Laboratory of Intelligent Technology and SystemsTsinghua National Laboratory for Information Science and TechnologyDepartment of Electronic EngineeringTsinghua UniversityBeijing 100084China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2012年第17卷第2期

页      面：194-201页

核心收录：

学科分类：081504[工学-水利水电工程] 08[工学] 080203[工学-机械设计及理论] 0815[工学-水利工程] 0802[工学-机械工程] 

基　　金：Supported by the National Key Basic Research and Development (973) Program of China (No.2007CB311004) 

主　　题：object detection densely computed SIFT training free single query image 

摘      要：A method was developed to detect generic objects using a single query image. The query image could be a typical real image, a virtual image, or even a hand-drawn sketch of the object. Without a training process, the key problem is how to describe the object class from only one query image with no pre-segmentation or other pre-processing procedures. The method introduces densely computed Scale-lnvariant Feature Transform （SIFT） as the descriptor to extract ＂gradient distribution＂ features of the image. The descriptor emphasizes the edge parts and their distribution structures, which are very representative of the object class, so it is very robust and can deal with virtual images or hand-drawn sketches. Tests on car detection, face detection, and generic object detection demonstrate that the method is effective, robust, and widely applicable. The results using queries of real images compare well with other training-free methods and state-of-the-art training-based methods.