Title :
Crystal image segmentation based on gray distribution steepest descent method
Author :
Liu, Wei ; Zhao, Yuhong
Author_Institution :
Inst. of Ind. Control, Zhejiang Univ., Hangzhou, China
Abstract :
In the image-based monitoring and control of crystallization process, effective crystal image segmentation is a basis for crystal object recognition and measurement. In this paper, a new threshold segmentation algorithm based on gray distribution steepest descent method is presented according to the unimodal characteristics of the black background crystal images. The image segmentation threshold is selected to be the fastest decline point on the probability density function of the crystal image´s gray distribution. The experimental results demonstrate the effectiveness and superiority of the proposed approach compared with the current image segmentation algorithms.
Keywords :
gradient methods; image segmentation; production engineering computing; crystal image segmentation; crystal object recognition; gray distribution; image based monitoring; probability density function; steepest descent method; threshold segmentation; unimodal characteristics; Crystallization; Entropy; Histograms; Image segmentation; Pixel; Probability density function; crystal image; gray distribution; steepest descent method; unimodal thresholding;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5646267