Abstract:
Breast cancer is one the most curable cancer types if it can be diagnosed early. Research efforts have reported with increasing confirmation that the computation methods have greater accurate diagnosis ability. An enhancement of multi classifiers voting technique based on histogram equalization as a pre-processing stage proposed in this paper. The methodology is based on five phases starting by mammogram images collection, preprocessing (histogram equalization and image cropping based region of interest (ROI)), features extracting, classification and last evaluating the classification results. An experimental conducted on different training-testing partitions of the dataset. The numerical results demonstrate that the proposed scheme achieves an accuracy rate of 81.25% and outperformed the accuracy of voting method without using histogram equalization.
Description:
Breast cancer is one the most curable cancer types if it can be diagnosed early. Research efforts have reported with increasing confirmation that the computation methods have greater accurate diagnosis ability. An enhancement of multi classifiers voting technique based on histogram equalization as a preprocessing stage proposed in this paper. The methodology is based on five phases starting by mammogram images collection, preprocessing (histogram equalization and image cropping based region of interest (ROI)), features extracting, classification and last evaluating the classification results. An experimental conducted on different training-testing partitions of the dataset. The numerical results demonstrate that the proposed scheme achieves an accuracy rate of 81.25% and outperformed the accuracy of voting method without using histogram equalization.
