DocumentCode :
736886
Title :
Image Synthesis Algorithms Based on Texture Feature
Author :
Haiyan, Yu
fYear :
2015
fDate :
13-14 June 2015
Firstpage :
549
Lastpage :
552
Abstract :
When adopting the texture algorithm, the color difference of the corresponding pixels of two matching blocks requires to be considered. For the traditional synthesis algorithms, the size of the sample block needs to be set by manual. Thus, after the synthesis, generally it will cause disorder in the feature of the texture and lacks the self-adaption. In order to solve the above-mentioned issue, a new texture synthesis algorithm of texture block is proposed, it takes the color difference of the texture and gradient structure information as the standard to measure the similarity of two matching blocks and the influence of the best matched texture block on the synthesis is deeply analyzed. According to different texture self-adaptions, the size of the texture block is confirmed so as to improve the rate and quality of the texture synthesis. Comparatively ideal effect has been obtained after the experimental verification.
Keywords :
Algorithm design and analysis; Histograms; Image color analysis; Maintenance engineering; Manuals; Standards; Weight measurement; algorithms; image; self-adaption matching block; texture feature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Measuring Technology and Mechatronics Automation (ICMTMA), 2015 Seventh International Conference on
Conference_Location :
Nanchang, China
Print_ISBN :
978-1-4673-7142-1
Type :
conf
DOI :
10.1109/ICMTMA.2015.139
Filename :
7263632
Link To Document :
بازگشت