Study on Chaotic Neural Network and its Application in Blood Cell Classification of Medical Image

Automatic analysis and classification of blood cell image has become the main stream of blood cell automatic detection technology. However, the automatic classification of blood cell image is not very good, since the large change of blood cell concentration and the shape and the variety of blood cell diseases are very great. For improving the recognizing accuracy rate, we have developed the automatic procedure of the cell extraction which uses the strong classifier power of chaotic neural network (CNN). For validating the efficiency of our method, comparative work has been performed for SVM and CNN on the HEp-2 set of blood cell image which consist of 721 images which belongs to twelve types and widely used. Experiment result shows that the procedure proposed in this paper outperforms the existing algorithms in both recognition precision rates.