Image/video visibility restoration system based on dark channel prior

• Main Authors: Nai-Cyun Ke, 柯乃群
• Other Authors: Ju-Chin Chen
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/27035675238152398521

碩士 === 國立高雄應用科技大學 === 資訊工程系 === 101 === We propose a simple and fast algorithm for haze removal in a single input image. During the processing of outdoor images, the presence of haze or smoke reduces the color information of the observed objects. Compare with the existing methods, the proposed method has the advantage of fast processing speed because of the modification of the dark channel prior during the estimation of the transmission. Further, the modification of the parameter reduction of the patch size can avoid the halo effect, which is caused by the improper patch size setting, in the haze-free image. Nevertheless, the restored image is unnatural because of over-dehazing. Two non-linear correction functions are proposed to refine the transmission and adjust the color of the restored image. Because all the operations are simple and efficient, the proposed method is suitable for applications performed on a platform with a limited computing ability, e.g., a digital camera or a smart phone, while simultaneously obtaining the promising dehazing results.