An Improved Approach for Cell Image Recognition based on Fractal Coding and Fractal Singular Value Neighbor Distance

Abstract

Based on fractal coding and fractal singular value neighbor distance, an improved approach for cell image recognition is proposed in this paper. Fractal singular value neighbor distance is brought forward based on fractal neighbor distance and singular value decomposition. Fractal coding and local singular value decomposition are used to improve the recognition rate. The experimental results show that the method can keep a good robustness to the variation of illumination, pose and expression, compared with traditional fractal neighbor distances. Furthermore, the method shows that the training time is short and recognition rate is high.