T
Tai-Hsiang Huang
Researcher at National Taiwan University
Publications - 26
Citations - 294
Tai-Hsiang Huang is an academic researcher from National Taiwan University. The author has contributed to research in topics: Image quality & Human visual system model. The author has an hindex of 7, co-authored 26 publications receiving 274 citations.
Papers
More filters
Journal ArticleDOI
Image Enhancement for Backlight-Scaled TFT-LCD Displays
TL;DR: In this paper, the authors proposed a method to enhance the image quality for a given backlight intensity by performing brightness compensation and local contrast enhancement, where global image statistics and backlight level are considered to maintain the overall brightness of the image.
Journal ArticleDOI
Learning-Based Prediction of Visual Attention for Video Signals
TL;DR: This paper proposes a computational scheme that adopts both low-level and high-level features to predict visual attention from video signal by machine learning and shows that such a scheme is more robust than those using purely single low- or high- level features.
Journal ArticleDOI
Enhancement of Backlight-Scaled Images
TL;DR: An image enhancement algorithm is proposed that overcomes such effects of dim LCD backlight by taking the human visual property into consideration and boosts the luminance of image areas below the perceptual threshold while preserving the contrast of the other image areas.
Patent
Learning-based visual attention prediction system and method thereof
TL;DR: In this article, a learning-based visual attention prediction method is disclosed, which includes a correlation relationship between the fixation density and at least one feature information being learned by training, followed by a test video sequence of test frames being received.
Proceedings ArticleDOI
Perception-based high dynamic range compression in gradient domain
TL;DR: An automatic algorithm for high dynamic range compression based on the properties of human visual system is proposed to avoid the halo artifact and automates the parameter adjustment process while preserving the image details.