iClean - Deteção Automática de Defeitos em Peças de Vestuário para Cegos.

• Autor(a) principal: Pinto, Leandro Montenegro
• Data de Publicação: 2023
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/11110/2712
• topic: Blind people; Artificial Intelligence; Neural Networks; Deep Learning; Image Processing; Clothing defects

Vision is one of the senses that dominates human life. It allows them to know and perceive the "world" around them, while giving meaning to objects, concepts, ideas, and tastes. The way we dress and the style we prefer for different occasions are part of our personal identity. Blind people do not have this sense, and the act of dressing can be a difficult and stressful task. With the advancement of technology, it is important to minimize all the limitations of a blind person in managing their clothing. The lack of knowledge of colors, pattern type, or the state of clothing pieces makes this a daily challenge, where current resources for blind people support have many gaps. Therefore, this project consists of extracting the basic conditions of clothing pieces through a computer vision detection system using deep learning algorithms, to identify defects in clothes such as: tears, holes or stains, with the aim of assisting the blind. With this system it is intended to improve the quality of life of the blind, allowing greater autonomy in their day-to-day