Image Enhancement Using Back-Propagation Neural Network Based Histogram Equalization for Image Sensor

摘要

In this paper, we present a image enhancement using back-propagation neural network based histogram equalization (BPNNHE) for image sensor. The problem of darkness in nighttime images has always been an important part of the nighttime sensor system's continuous efforts to improve. However, in view of the fact that the instantaneous images recorded in the nighttime sensor system are often too dark and unclear, the conventional method uses the histogram equalization (HE) method to evenly distribute the grayscale values of the image pixels to the respective pixels. However, the disadvantage is that the amount of calculation is too large to make the image clearer. At the same time, under different light and environment conditions, histogram qualization often cannot adapt to changes in various environments. In order to solve this problem, this paper uses the Back-propagation Neural Network method to judge the brightness of images. According to different judgment results, different input images are adjusted according to the adaptive automatic conversion function. The system adjusts the dark image to the appropriate image brightness. Through the improved histogram equalization algorithm, the brightness of the image is appropriately adjusted. The purpose is to make the image content clear through the brightness enhancement. The proposed method improves the distortion caused by underexposure and overexposure and provides a well solution.