Regularised Layerwise Weight Norm Based Skin Lesion Features Extraction and Classification

Melanoma is the most lethal malignant tumour, and its prevalence increasing. Early detection diagnosis of skin cancer can alert patients to manage precautions dramatically improve lives people. Recently, deep learning has grown increasingly popular in extraction categorization features for effective prediction. A model learns co-adapts representations from training data point where it fails perform well on test data. As a result, overfitting poor performance occur. To deal with this issue, we proposed novel Consecutive Layerwise weight Constraint MaxNorm (CLCM-net) constraining norm vector that scaled each time bounding limit. This method uses convolutional neural networks also custom layer-wise constraints are set whole matrix directly learn efficiently. In research, detailed analysis these norms performed two distinct datasets, International Skin Imaging Collaboration (ISIC) 2018 2019, which challenging handle. According findings work, CLCM-net did better job raising model’s by efficiently within size limit weights appropriate constraint settings. The results proved techniques achieved 94.42% accuracy ISIC 2018, 91.73% 2019 datasets 93% combined dataset.