Title :
Moment Invariants of Restricted Projective Transformations
Author :
Wang Yuanbin ; Zhang Bin ; Yao Tianshun
Author_Institution :
Inst. of Comput. Applic. Technol., Northeastern Univ., Shenyang
Abstract :
It is known that moment invariants for general projective transformations do not exist. This paper presents a novel method to derive moment invariants under two types of restricted projective transformations. For each type of restricted projective transformations, a complete set of moment invariants up to arbitrary order is presented in the explicit form. Experimental results indicate that they are effective, practical, and robust to slight noise such as erosion, blurring, and small occlusion. They have high discriminating power for pattern analysis and object recognition.
Keywords :
computer vision; method of moments; computer vision; moment invariants; restricted projective transformation;
Conference_Titel :
Information Science and Engineering, 2008. ISISE '08. International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-2727-4
DOI :
10.1109/ISISE.2008.246