CORREÇÃO DE ILUMINAÇÃO EM IMAGENS CAPTURADAS EM AMBIENTES COM BAIXA LUMINOSIDADE

Abstract

A big obstacle for the Computer Vision area is the quality of the processed input images. As an example, there are dark images, which can be caused by several factors such as low light source at night, adverse weather conditions, among others. This work aims to use images with low lighting for the development of algorithms that help to improve the quality of light and image. Computer Vision techniques were used with the help of the OpenCV library in the development of algorithms to perform smoothing, correlation between minimum and maximum intensities, intensities reinforcement and exposure correction, definition of weight matrix and image enhancement. The results show that the proposed method was able to improve the images, considerably reducing unwanted features, maintaining good lighting and image quality.