Worldwide, breast cancer is a serious concern to women, stressing the importance of early detection for effective treatment and survival improvement. Computer-aided cancer prediction helps the doctor for accurate decisions. It also helps the patients to improve their quality of life. This study proposes three algorithms, namely, random forest, Inception V3, and convolutional neural network for breast cancer detection. All three algorithms are implemented and performances are compared. The features are extracted and analyzed using Local Binary Pattern (LBP) from medical images to capture essential textural information of breast tissue characteristics. The breast cancer dataset is taken from data.mendeley.com for experimentation. Metrics like recall, accuracy, precision, and F1 score are taken into account when assessing how well the algorithms work. Among these three algorithms, the Random Forest Classifier achieved the highest accuracy of 0.9108, followed by the convolutional neural network (CNN) with an accuracy of 0.8535, whereas the InceptionV3 Transfer Learning Model exhibited comparatively lower accuracy at 0.5924.