Scale Invariant Feature Transform with Crow Optimization for Breast Cancer Detection

Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalman filter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).

Scale Invariant Feature Transform with Crow Optimization for Breast Cancer Detection

Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalmanfilter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).