A local dimming method based on improved multi-objective evolutionary algorithm

36‐4: Analysis of Halo Improvement Factors of Mini‐LED Backlit Display Based on Visual Sensitivity

“…At present, there have been some research progress on the characterization and improvement of the halo phenomenon of MLED-LCD, mainly through optimizing the hardware performance of backlight partition, display panel and backlight dimming algorithm to improve the halo problem to a certain extent [2]. For example, by studying the luminance distribution of halo from the perspective of backlight and module, some factors affecting the size of halo are put forward to guide the optimization design of hardware and software such as backlight partition and dimming algorithm [3,4]. Furthermore, in combination with the human visual system (HVS), an optical model was used to simulate the HDR image generated by MLED-LCD and a subjective evaluation verification experiment was designed, and evaluation indexes such as LocalPSNR were proposed to characterize the intensity of the halo.…”

Luminescence Enhancement of K2LiAlF6:Mn4+ Phosphors by Zn2+-Mediated Charge Compensation for Fast-Response Backlighting Applications

“…Mini-light-emitting diodes (Mini-LEDs) are novel devices for display terminals such as TVs that can adjust the local brightness of the screen dynamically, especially in dark areas, to achieve a high contrast similar to organic LED (OLED) screens. − However, the rapid transition between light and dark regions poses a challenge for the response speed of phosphors assembled on the Mini-LEDs. − As Figure a shows, the Mini-LEDs are so small and dense that they cannot use lenses to smooth out light distribution. As a result, when the screen displays a video with a moving white circle on a black background, as in Figure b, there is uneven brightness and darkness at the border of the circle.…”

EvolveNet: Evolving Networks by Learning Scale of Depth and Width

“…Evolutionary algorithms have been found to significantly outperform random and systemic search methods when searching in large search spaces [24]. Over the years, various multi-objective evolutionary algorithms have been proposed to varying degrees of success [25,26]. However, they tend to suffer from a weak global search ability in low inter-task relevance problems [27] because the cross-over operator is unable to distinguish between information and noise.…”