Light-Dependent Properties of Finishing and Leather Defects

The uniformity of the colour in leathers for the furnishing and automotive sectors is a particularly important feature, especially for white or light-coloured articles, intended to the high-end market;on these articles any colour alteration can be very visible and unpleasant, with possible technical and economic consequences for the producers. In a previous study, we analysed the possible causes behind the formation of some peculiar pink/salmon stains on different kinds of white/beige/light-coloured leather furnishing items, where we focalized our attention on TiO2 properties and its possible interaction with some organic-based antioxidants. In recent years, due to many other similar cases of defects that occurred to tanners and to upholstery traders, we decided to enhance the investigations concerning this topic. More in detail we analysed, defective leathers, powder pigments and chemicals, in order to identify the possible role of some substances in this issue, with particular reference to some antioxidants and aluminosilicates, where several diagnostic techniques have been utilised, as ATR-IR (Attenuated Total Reflectance IR Spectroscopy), SEM-EDX (Scanning Electron Microscopy-Energy Dispersive X-ray Analysis), XRF (X-ray Fluorescence spectrometry), GC-MS (Gas Chromatography-Mass Spectrometry), and DSC/TGA (Differential scanning calorimetry/Thermogravimetry) equipment.

Deep learning and machine learning neural network approaches for multi class leather texture defect classification and segmentation

Modern leather industries are focused on producing high quality leather products for sustaining the market com-petitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature;hence machine vision systems have been widely adopted for the automated inspection of leather defects. It is neces-sary develop suitable image processing algorithms for localize leather defects such as folding marks, growth marks, grain off, loose grain, and pinhole due to the ambiguous texture pattern and tiny nature in the localized regions of the leather. This paper presents deep learning neural network-based approach for automatic localization and classifica-tion of leather defects using a machine vision system. In this work, popular convolutional neural networks are trained using leather images of different leather defects and a class activation mapping technique is followed to locate the region of interest for the class of leather defect. Convolution neural networks such as Google net, Squeeze-net, RestNet are found to provide better accuracy of classification as compared with the state-of-the-art neural network architectures and the results are presented.