• PATNAIKUNI AKHILA
• DEEPATI MADHUBABU

Skin cancer is one of the top three perilous types of cancer caused by damaged DNA that can cause death. Cells start to expand out of control as a result of this damaged DNA, and this growth is happening more quickly these days. A few research on the automatic identification of cancer in skin lesion photographs have been carried out. However, it is quite challenging to analyze these images because of a variety of problematic factors, such as light reflections from the skin's surface, variations in color illumination, and varied sizes and patterns of lesions. Consequently, the development of evidence automatic recognition of skin cancer is beneficial in enhancing pathologists' early diagnostic precision and expertise. In this work, we propose a Deep Convolution Neural Network (DCNN) model based on deep learning for accurate classification of benign and malignant skin lesions. Initially, we use a filter or kernel to remove noise and artifacts from the input images. After normalizing the photos, we identify characteristics that help with precise classification. Lastly, we enrich the data with more images to boost the accuracy of the classification rate. To evaluate its performance, our proposed DCNN model is compared with many Transfer learning techniques, such as MobileNet, AlexNet, and DenseNet. Ultimately, we were able to obtain training and testing accuracy, respectively. The final results of our proposed DCNN model show that it is more reliable and robust than other transfer learning techniques.

Skin Cancer, Deep Convolutional Neural Network, DenseNet201, MobileNetV2, AlexNet

"COMPARITIVE STUDY OF DCNN WITH TRANSFER LEARNING TECHNIQUES FOR SKIN CANCER CLASSIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.a397-a405, May-2024, Available :http://www.jetir.org/papers/JETIR2405047.pdf

"COMPARITIVE STUDY OF DCNN WITH TRANSFER LEARNING TECHNIQUES FOR SKIN CANCER CLASSIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppa397-a405, May-2024, Available at : http://www.jetir.org/papers/JETIR2405047.pdf