IMAGE SALIENCY DETECTION METHOD

WIPO Patent Application WO/2015/180527

A1

Disclosed is an image saliency detection method, comprising the steps of: 1) conducting segmentation processing on an image to divide same into K image blocks with the size of M × N, where the values of M and N are set by a user; 2) calculating a characteristic value of each image block, the characteristic value comprising a brightness characteristic value, a colour characteristic value, a direction characteristic value, a depth characteristic value and a sparseness characteristic value; 3) quantifying various characteristic values of each image block to the same interval range, conducting fusion calculation on various characteristic values to obtain difference values between each image block and the remaining image blocks; and 4) determining a weighting coefficient, conducting weighted summation on the difference values between each image block and the remaining image blocks to obtain a saliency value of each image block. By introducing a depth characteristic and a sparseness characteristic based on the traditional characteristic value, the image saliency detection method of the present invention meets the characteristic of image observation by vision systems of human beings, thereby guaranteeing that saliency images obtained by processing meet the vision systems of human beings, and the saliency images are accurate.

YUAN CHUN (CN)
CHEN GANGBIAO (CN)

PCT/CN2015/075514

December 03, 2015

March 31, 2015

Click for automatic bibliography generation  

UNIV TSINGHUA GRADUATE SCHOOL (CN)

G06K9/46; G06T7/00

CN103679173A	2014-03-26
CN103810503A	2014-05-21
CN103065302A	2013-04-24
CN103714537A	2014-04-09
US7260259B2	2007-08-21
CN103996195A	2014-08-20

CHINA TRUER IP (CN)
深圳新创友知识产权代理有限公司 (CN)

View/Download PDF      PDF Help

Previous Patent: COMPATIBLE CIRCUIT AND TERMINAL

Next Patent: TRIANGULAR COMPONENT PLUGGED-CONNECTION THREE-DIMENSIONAL SHAPE