| Sumario: | Oral cancer is a chief health issues in the United States and worldwide. The oral cancer cell detection and segmentation stages are greatly influenced by the intensity distribution, contrast, and clarity of the input phase contrast micrographs. The classification stage in turn is dependent on the segmentation output. In this research, we used histopathology PAIP 2020 dataset for experimentation. Initially the given dataset taken into pre-processing to remove the noise from the image and enhance the image. Then the pre-processed image is given to the segmentation process, in this processes we used Patch-based Fuzzy Local Similarity CMeans (PFLSCM) scheme. And also we applied feature extraction methods for extract the feature from the image. Total 30 features are extracted, which consists of a combination of size, shape, and first-order and second-order statistical texture measures, were computed. Finally the extracted features images is correctly classify by using Hybrid Hopfield Neural Network with Ant Colony Optimization (ACO) algorithm. The performance of the model is analysed by using different parametric metrics, which are followed in result section. Finally the proposed model achieved the accuracy of 98.98% of accuracy.
|
|---|