Title :
Multi-level thresholding: maximum entropy approach using ICM
Author :
Luo, Xiping ; Tian, Jie
Author_Institution :
Inst. of Autom., Acad. Sinica, Beijing, China
Abstract :
The maximum entropy approach is one of the most important threshold selection methods. Many authors avoid the computationally prohibitive problem when the maximum entropy criterion is applied to multi-level threshold selection. The paper deals with this problem using the ICM (iterated conditional modes) method. Experiments show that using the ICM with our initialization algorithm method gets satisfactory, if not optimal, results and the problem of computation is excellently solved
Keywords :
maximum entropy methods; probability; initialization algorithm method; iterated conditional modes; maximum entropy approach; multi-level thresholding; threshold selection methods; Automation; Computational modeling; Entropy; Histograms; Image converters; Probability distribution; Search methods; Simulated annealing; Space technology; State-space methods;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.903660