Quality control in clothing manufacturing with machine learning

• Autor(a) principal: San-Payo, Gonçalo Laginha Serafim
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10071/17782
• topic: Quality control; Incremental learning; Image classification; Engenharia de telecomunicações; Processos de fabrico; Vestuário; Controlo da qualidade; Aprendizagem; Classificação; Imagem

Quality control is vital for business and machine learning has proven to be successful in this type of area. In this work we propose and develop a classification model to be used in a quality control system for clothing manufacturing using machine learning. The system consists of using pictures taken through mobile devices to detect defects on clothing items. A defect can be a missing component or a wrong component in a clothing item. Therefore, the function of system is to classify the objects that compose a clothing item through the use of a classification model. As a manufacturing business progresses, new objects are created, thus, the classification model must be able to learn the new classes without losing previous knowledge. However, most classification algorithms do not support an increase of classes, these need to be trained from scratch with all classes. In this work, we make use of an incremental learning algorithm to tackle this problem. This algorithm classifies features extracted from pictures of the clothing items using a convolutional neural network (CNN), which have proven to be very successfully in image classification problems. As the result of this work, we have developed a quality control system that combines a mobile application to take pictures of clothing items and a server that performs defect detection processes using an accurate image classification model capable of increasing its knowledge from new unseen data. This system can help factories improve their quality control processes.