Ensemble of Fine-Tuned Deep Learning Networks for Wet-Blue Leather Segmentation

Abstract

As part of industrial quality control in the leather industry, it is important to segment features/defects in wet-blue leather samples. Manual inspection of leather samples is the current norm in industrial settings. To comply with the current industrial standards that advocate large-scale automation, visual inspection based leather processing is imperative. Visual inspection of wet-blue leather features is a challenging problem as the characteristics of these features can take on a variety of shapes and colour variations to constitute various normal and abnormal surface regions. The aim of this work is to automatically segment leather images to detect various features/defects along with the background through visual analysis of the surfaces. To accomplish this, a deep learning-based technique is developed that learns to segment wet-blue leather surface features. On our own curated leather images dataset, the proposed ensemble network performed well, with an F1-Score of 74 percent.

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

“…boundaries, inherent uncertainty in segmented regions, diverse textures, nonuniform intensity distribution, and significant contrast variations commonly encountered in medical images [5], [6], [7], [8], [9], [10]. These complexities emphasise the importance of developing advanced segmentation techniques to facilitate clinical diagnosis.…”