Weld fault identification using X-ray pictures is a useful nondestructive testing technique. Traditionally, this job has relied on skilled human experts, while the extraction and classification of heterogeneity required their personal involvement. To overcome those challenges, various approaches are used, including machine learning (ML) and image processing technologies. Although the detection and categorization of low contrast and poor-quality images have been improved, the end result is still unsatisfactory. Unlike earlier ML-based research, this paper provides a new deep learning network-based classification approach. In this work base convolutional neural network architecture with optimization techniques was used to enhance the performance of the architecture to obtain a best performance result in simpler CNN architecture. In this work we have obtained overall classification accuracy of 89% using simple CNN with optimization technique.

This literature survey offers a comprehensive analysis of deep learning techniques for skin cancer diagnosis. Prompt identification is crucial for improving patient survival rates, and deep learning has demonstrated promising results. The survey examines the fundamentals of skin cancer, various neural network architectures, and their classification efficacy. It investigates the application of deep learning models in clinical decision-making and assesses authentic datasets for evaluating skin cancer detection techniques. Training strategies for enhancing deep learning models are delineated. The survey assesses essential performance indicators, including accuracy, precision, recall, and F1-score. This survey underscores the growing importance of deep learning in skin cancer diagnosis, demonstrating its potential to improve the patient experience and advance clinical practice.