Title :
Blurred image recognition based on complex moment invariants
Author :
Tianxu, Zhang ; Jin, Liu
Author_Institution :
State Key Lab. of Image Process. & Intelligent Control, Huazhong Univ. of Sci. & Technol., Hubei, China
Abstract :
An important class of radiometric degradations we are faced with often in practice is image blurring. Special attention is paid to the recognition of the blurred image by moment invariant approach. Some important rules of complex moments for the blurred image are presented. Based on these rules, a useful subset of moment invariants is introduced, that are not affected by the blur, rotation, scale, and translation of the images. The experiments have shown that these invariants can be successfully used in recognition of the blurred image.
Keywords :
Gaussian processes; image recognition; image restoration; image blurring; image recognition; image rotation; image scale; image translation; moment invariant approach; radiometric degradation; Biomedical imaging; Cameras; Character recognition; Computer vision; Convolution; Degradation; Image recognition; Layout; Radiometry; Target recognition;
Conference_Titel :
Image Processing, 2004. ICIP '04. 2004 International Conference on
Print_ISBN :
0-7803-8554-3
DOI :
10.1109/ICIP.2004.1421507