A leukocyte pattern recognition based on feature fusion in multi-color space.
- Author:
Liangwang HAO
1
;
Wenxue HONG
2
Author Information
1. College of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China. haolw@ysu.edu.cn
2. College of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China.
- Publication Type:Journal Article
- MeSH:
Algorithms;
Clinical Laboratory Techniques;
Color;
Humans;
Image Enhancement;
methods;
Image Interpretation, Computer-Assisted;
methods;
Leukocyte Count;
methods;
Leukocytes;
classification;
cytology;
Pattern Recognition, Automated;
methods
- From:
Journal of Biomedical Engineering
2013;30(5):909-913
- CountryChina
- Language:Chinese
-
Abstract:
To solve the ineffective problem of leukocytes classification based on multi-feature fusion in a single color space, we proposed an automatic leukocyte pattern recognition by means of feature fusion with color histogram and texture granular in multi-color space. The interactive performance of three color spaces (RGB, HSV and Lab), two features (color histogram and texture granular) and four similarity measured distance metrics (normalized intersection, Euclidean distance, chi2-metric distance and Mahalanobis distance) were discussed. The optimized classification modes of high precision, extensive universality and low cost to different leukocyte types were obtained respectively, and then the recognition system of tree-integration of the optimized modes was established. The experimental results proved that the performance of the fusion classification was improved by 12.3% at least.