Contrast Enhancement-Based Preprocessing Process to Improve Deep Learning Object Task Performance and Results

Abstract

Excessive lighting or sunlight can make it difficult to judge visually. The same goes for cameras that function like the human eye. In the field of computer vision, object tasks have a significant impact on performance depending on how much object information is provided. Light presents difficulties in recognizing objects, and recognition is not easy in shadows or dark areas. In this paper, we propose a contrast enhancement-based preprocessing process to obtain improved results in object recognition tasks by solving problems that occur due to light or lighting conditions. The proposed preprocessing process involves the steps of extracting optimal values, generating optimal images, and evaluating quality and similarity, and it can be applied to the generation of training and input data. As a result of an experiment in which the preprocessing process was applied to an object task, the object task results for areas with shadows or low contrast were improved while the existing performance was maintained for datasets that require contrast enhancement technology.