Live Demonstration: Supervised-learning-based Visual Quantification for Image Enhancement

Wei Zhang1; Junfeng Chang2; Zizhao Peng1; Lei Chen1; Fengwei An1

10.1109/AICAS57966.2023.10168650

2023-06

2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)

2834-9830

979-8-3503-3268-1

2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)

1-2

11-13 June 2023

Hangzhou, China

This demonstration showcases a framework of visual quantification for image enhancement where multivariate Gaussian (MVG) models are trained to assess image visibility. The visibility of an image is depicted by statistical features such as the contrast energy of the gray channel, yellow-blue channel, and red-green channel, average saturation, and gradients. The predicted visibility scores are then applied to define adaptive histogram equalization clip parameters for image enhancement. Finally, the hardware architecture is implemented on an FPGA to demonstrate the results for real-time image enhancement.

Low Visibility Enhancement Image Enhancement Visual Perception

第一 ; 通讯

EI

20233114469042

Computer Vision ; Machine Learning ; Visibility

Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2

IEEE

1.Southern University of Science and Technology, Shenzhen, China
2.Shenzhen Semiconductor Industry Association, Shenzhen, China

Wei Zhang,Junfeng Chang,Zizhao Peng,et al. Live Demonstration: Supervised-learning-based Visual Quantification for Image Enhancement[C],2023:1-2.