Open AccessEnhancing Dark Images Captured On Camera
Author(s) -
Shiyuan Liu,
Ning He,
Xiaojie Yin
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1453/1/012017
Subject(s) - naturalness , artificial intelligence , computer vision , brightness , computer science , pixel , process (computing) , image (mathematics) , point (geometry) , color balance , object (grammar) , image processing , color image , mathematics , physics , optics , geometry , quantum mechanics , operating system
In recent years, dark image enhancement technology has emerged as a popular subject of research, and has played an important role in security monitoring, traffic management, military reconnaissance, and film production. To solve the problems posed by images captured in poor lighting such that the target is not visible or is difficult to read, we propose a method to process such images to identify the targets in them. An algorithm is developed that uses the dynamic threshold method to determine the white reference point in the image as well as the brightest ten percent of pixels according to size. It then adjusts the white point and balances the area to obtain the final result. Using this, the gamma transform is used to adjust the brightness of the image. The results of experiments show that the proposed method can enhance image brightness without loss of color in the image to preserve its naturalness and improve object recognition in natural scenes.