This research addresses the challenge of monkeypox, a contagious skin disease that may be spread from animal to human contact. Recognizing its broad reach and potential severity, the research emphasizes the critical need for early and precise detection. The project sets out to evaluate how well a computer vision-based approach and CNN-based technology can accurately spot instances of monkeypox. Various algorithms, including Googlenet, Resnet50, VGG16, VGG19, Darknet53, Mobilenetv2, Inceptionv3, Inceptionresnetv2, and Yolov7, are put to the test. Notably, Mobilenetv2 stands out with an exceptional validation accuracy of 95.2%, showcasing its effectiveness in pinpointing and identifying the disease. The study emphasizes the significance of deep learning optimizers in improving the outcomes of image classification, not only for monkeypox detection but also for making strides in diagnosing monkeypox diseases. Furthermore, the research suggests avenues for refining deep learning architectures and optimization techniques.