查看文章

In this paper, the cancer affected area in the white blood cell images is investigated. Different types of white blood cells are classified using AlexNet architecture. In this model, trained on cells’ images preprocess the images first and extract the best feature. The convolutional layer, Relu layer and max pooling layer are used for extracting the feature. The extracted features are fed into a softmax and a fully connected layer for classification of Eosinophil, Lymphocytes, Monocytes and Neutrophils. The various stages of image processing are utilized to achieve more quality and accuracy in detecting blood cancers. The accuracy depends upon the affected area of the blood sample image.