Automatic Classification of Normal and Infected Blood Cells for Leukemia Through Color Based Segmentation Technique Over Innovative CNN Algorithm and Comparing the Error Rate with RNN

Abstract

To classify the normal infected blood cells through color-based segmentation for leukemia by comparing the error rate for the innovative Convolutional Neural Network and Recurrent Neural Network algorithm. Materials and Methods: Convolutional Neural Network algorithm, which has been taken as an input image and differentiating according to the properties of the image. Here the white blood cells acted as the major parameter for detecting the disease. Result: Data collection was carried out and the analysis could have been done by using blood cell sample images to detect the result and error rate of a particular algorithm. Here in this proposed work, the error rate was reduced in innovative Convolutional Neural Networks compared to Recurrent Neural Networks. Conclusion: The data was collected from various resources for the usage of disease detection. The reduced error rate for the Convolutional Neural Network (87.02%) was used as an algorithm for the whole disease detection process for reduced error rate results compared to the Recurrent Neural Network (89.42%).