DocumentCode
2786393
Title
Multiscale retinex color image recovery enhancement algorithm
Author
Nian, Liu ; Xiuyuan, Peng
Author_Institution
Sci. & Eng. Coll., Shenyang Ligong Univ., Shenyang, China
fYear
2009
fDate
17-19 June 2009
Firstpage
3976
Lastpage
3979
Abstract
To improve the quality of classification in color image recognition, during the pretreatment of color image it must be removed the noise to improve the invariance of color, compress image dynamic range to improve balance, effectively showed the details in shadow and light area. Begin with enhancing image in airspace, describes the theory of multiscale retinex, multiscale retinex was used to realize enhancing of grey image firstly, and the method and parameters of image enhancing was described in detail. Then multiscale retinex color retrieval algorithm was used to realize color retrieval of image. A emulational example was carried on in vc++ software, the image was improved, at the same time the noise was controlled. A emulational example is given to illustrate the efficiency and the practicability of the algorithm.
Keywords
C++ language; algorithm theory; image classification; image colour analysis; image denoising; image retrieval; Multiscale retinex; color image pretreatment; color image recovery enhancement; grey image enhancing; image color retrieval; vc++ software; Color; Colored noise; Data acquisition; Data mining; Educational institutions; Humans; Image recognition; Image retrieval; Space technology; Vehicles; Color Retrieval; Enhancing of Image; MultiScale Retinex (MSR);
fLanguage
English
Publisher
ieee
Conference_Titel
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location
Guilin
Print_ISBN
978-1-4244-2722-2
Electronic_ISBN
978-1-4244-2723-9
Type
conf
DOI
10.1109/CCDC.2009.5192094
Filename
5192094
Link To Document