To increase efficiency of automated leucocyte pattern recognition using lower feature dimensions, a novel inter-class distinctive feature selection method for chromatic leucocyte images was proposed based on attribute hierarchical relationship. According to the attribute constraints in formal concept analysis, we established a knowledge representation and discovery method based on the hierarchical optimal diagram by defining attribute value and visual representation of optimized hierarchical relationship. It was applied to human peripheral blood leucocytes classification and 12 distinctive attributes were simplified from 60 inter-class attributes, which contributes significantly to reduced feature dimensions and efficient inter-class feature classification. Compared with the classical experimental data, the inter-class distinctive feature selection method based on hierarchical optimal diagram was proved to be usable and effective for six leucocyte pattern recognition.
Humans ; Leukocytes ; classification ; Pattern Recognition, Automated

We propose an algorithm for segmentation of the overlapped leukocyte in the microscopic cell image. The histogram of the saturation channel in the cell image is smoothed to obtain the meaningful global valley point by the fingerprint smoothing method, and then the nucleus can be segmented. A circular region, containing the entire regions of the leukocyte, is marked off according to the equivalent sectional radius of the nucleus. Then, the edge of the overlapped leukocyte is represented by polar coordinates. The overlapped region by the change of the polar angle of the edge pixels is determined, and the closed edge of the leukocyte integrating the gradient information of the overlapped region is reconstructed. Finally, the leukocyte is exactly extracted. The experimental results show that our method has good performance in terms of recall ratio, precision ratio and pixel error ratio.
Algorithms ; Cell Adhesion ; Humans ; Image Enhancement ; instrumentation ; methods ; Image Processing, Computer-Assisted ; instrumentation ; methods ; Leukocytes ; cytology ; Microscopy