Introduction to U-NET Variant Algorithm Infused from Transfer Learning

Variety, Sparsity and Vagaries in normality offers tough challenge in anomaly detection. This is further aggravated by varying background of images which creates more difficulty in Anamoly Detection. To solve this series of labeling is needed to identify object of interest and categorize given the interest and level of detail. This paper introduces a novel approach for object identification with higher accuracy which can be scaled and applicable in practical situations. This is achieved by creating a unique autoencoder connector from transfer learning to U NET algorithm. The motivation for this innovation stems from the need for autolabeling and efficient anamoly detection in manufacturing settings limited by manual checks. The proposed solution aims to provide reliable and scalable anomaly detection, leveraging semantic segmentation for precise object identification with details of kind of the fault. The approach involves a detailed comparison of semantic segmentation methods, leading to the development of a new semantic segmentation technique. The results highlight the potential of the proposed approach in addressing semantic segmentation tasks and compared the results with existing methods.