| Summary: | 碩士 === 國立勤益科技大學 === 資訊工程系 === 104 === The image quality will be reduced with the light attenuation by atmospheric particles when taking a photograph outdoors, especially in the environment with haze. Because the hazy images lose a lot of information, the image recognition systems cannot recognize the target in the image. In order to raise image processing effectiveness, there are two image de-hazing methods proposed which are using the fuzzy inference system and the TSK-type IRSFCMAC to estimate transmission maps, then refine transmission maps with the weighted method. In the part of atmospheric light, we use the results which are estimated from the fuzzy inference system and the TSK-type IRSFCMAC, and combine the average method to calculate the atmospheric light to solve the color cast problem. We use hardware to implement both methods. In the experimental results, we compare the proposed methods with the other existing approaches which are divided into two part simulation implement and hardware implement. The experimental results show that hardware results have great performance and similar to the simulation results.
|
|---|
