Chip and System Design of Image Enhancement Based on Generative Adversarial Neural Network

• Main Authors: CHENG, HAO-WEN, 鄭豪文
• Other Authors: FAN, YU-CHENG
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/r2dve4

碩士 === 國立臺北科技大學 === 電子工程系 === 107 === Visual image processing has always been a very important field. With the development of multimedia, we can use images in everywhere. The quality of images is not perfect in our expectation. Therefore, image processing is to carry out the images to be repaired. Not only enhance image of contrast to make clear, but real-time processing is also very important. For example, the vehicle electronic assistant equipment must perform image restoration in a short time, so that the driver can keep safety with enhanced images. Due to the development of deep learning in recent years, we can use the neural network for training and simulating the models. The machine learning method can replace the traditional method, which not only shortens the time but also has higher precision. We use deep learning to perform image decomposition, so that we can get the shadow image and the reflection image, and then do the enhancement for the shadow layer image. That can be faster than the traditional methods and perform better efficient. It is possible to fix the over-exposed or over-dark parts of the image to get more complete information, and the shadow layer repair we also use the neural network by algorithm simulation, the conditional generation can be used to restrict the network. Let the speed of training and testing be more precise and fast. Finally, we make the chip to against the most computational volume of the mathematical formula - convolution, and the overall speed can be improved by the hardware acceleration.