Fast Image Correspondence with Global Structure Projection

• Published in: Journal of computer science and technology Vol. 27; no. 6; pp. 1281 - 1288
• Main Author: 林庆樑 盛斌 沈洋 谢志峰 陈志华 马利庄
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.11.2012; Springer Nature B.V; Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China%Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237 China
• Subjects: Accuracy; Analysis; Artificial Intelligence; Computation; Computer Science; Correspondence; Data Structures and Information Theory; Information Systems Applications (incl.Internet); Methods; Object recognition; Pattern recognition systems; Projection; Recognition; Regular Paper; Representations; Sensors; Software Engineering; Studies; Theory of Computation; 像对; 匹配方法; 图像表示; 平面物体; 投影; 数据集; 计算效率; 键结构; object recognition; structure projection; image correspondence; flat object
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-012-1304-2

This paper presents a method for correspondence. This technique works by two recognizing images with steps： reference keypoint flat objects based on global keypoint structure selection and structure projection. The using of global keypoint structure is an extension of an orderless bag-of-features image representation, which is utilized by the proposed matching technique for computation efficiency. Specifically, our proposed method excels in the dataset of images containing ＂flat objects＂ such as CD covers, books, newspaper. The efficiency and accuracy of our proposed method has been tested on a database of nature pictures with flat objects and other kind of objects. The result shows our method works well in both occasions.