The prevalence of skin cancer, the most common form the cancer in men, has been steadily increasing. Detecting this type of cancer can be challenging due the appearance of complex and dynamically changing skin lesions patches of skin with varying color, shape, and texture. This variability makes accurate diagnosis a formidable task for specialists. To address this issue, advanced image classification algorithms play a crucial role in assessing and categorizing these lesions. In this article, we focus on the application of image classification techniques for disease diagnosis. Our contribution lies in a novel hybrid approach that combines Support Vector Machine (SVM) and Convolutional Neural Network (CNN) classifiers, aimed at enhancing diagnostic accuracy. By leveraging the strengths of both SVM and CNN, we strive to improve the overall performance of skin cancer diagnosis. In this article, we use the ISIC dataset, which contains a collection of photos for melanoma skin cancer and we get 97.35% of accuracy.