Hybrid deep emperor penguin classifier algorithm‐based image quality assessment for visualisation application in HDR environments

Abstract

One of the main open challenges in visualisation applications such as cathode ray tube (CRT) monitor, liquid-crystal display (LCD), and organic light-emitting diode (OLED) display is the robustness for high dynamic range (HDR) environs. This is due to the imperfections in the sensor and the incapability to track interest points successfully because of the brightness constancy in visualisation applications. To address this problem, different tone mapping operators are required for visualising HDR images on standard displays. However, these standard displays have different dynamic ranges. Thus, there is a need for a new model to find the best quality tone mapped image for specific kinds of visualisation applications. The authors propose a hybrid deep emperor penguin classifier to accurately classify the tone mapped images for different visualisation applications. Here, a selective deep neural network is trained to predict the quality of a tone-mapped image. Based on this quality, a decision is made as to the suitability of the image for CRT monitor, LCD display or OLED display. Also, they evaluate the proposed model on the TMIQD database and the simulation results prove that the proposed model outperforms the state-of-the-art image quality assessment methods.