Image Enhancement using Modified Laplacian Filter, Clahe and Adaptive Thresholding
Sabeeh Abdul Rehman, Zoe Jeffrey, Yichuang Sun, Oluyomi Simpson · 2024
In this paper, a new method for image enhancement is proposed for object recognition in autonomous vehicles. The new method involves image segmentation, Contrast-Limited Advanced Histogram Equalization (CLAHE), a Modified Laplacian filter and Adaptive Thresholding. The image is segmented into four-by-four segments. Each segment is assessed and corrected for blurriness and darkness. Adaptive Thresholding gives a unique automated threshold value for each region of the image depending upon the lighting conditions of the region of the image. The aim is to enhance the contrast and brightness of the image and increase sharpness of the image without inducing noise. The proposed method enhances the image quality that the image recognition system receives and was tested on low-light datasets. The extensive experiments show higher performance both qualitative and quantitively compared to the state of art methods.