Anomaly Detection Model for Convolutional Image Transformation Networks
Aditya Bhushan, Ashutosh Kumar Singh, Vijay Kumar Dwivedi · 2024
In the realm of Convolutional Image Transformation Networks (CITN), this study addresses the critical need for robust anomaly detection. The motivation stems from the escalating importance of reliable image classification models in various domains, where identifying anomalies is paramount. Grounded in this context, our hypothesis posits that an enhanced convolutional network can effectively discern anomalies within images. Leveraging innovative methods, we augment traditional Convolutional Neural Networks with specialized transformation techniques. Through extensive experimentation and evaluation, our results demonstrate the model’s superior performance in detecting anomalies, surpassing existing benchmarks. This research contributes a novel approach to bolstering image transformation networks for anomaly detection, offering valuable insights for applications in diverse fields. In conclusion, the proposed methodology showcases promising strides in advancing the capabilities of CITN for heightened anomaly detection accuracy.