HVS-DBS: human visual system-aware dynamic luminance backlight scaling for video streaming applications

Despite the advances in Liquid Crystal Display's (LCD) technology, LCD power consumption is still one of the major limiters of battery lifetime for handheld devices. The main contribution to LCD subsystem power consumption comes from the backlight. This can be substantially reduced by dynamically adapting backlight intensity while compensating the image quality degradation through image pixel transformation. Several compensation algorithms have been recently proposed to this purpose, but none of them is really capable of ensuring a target image quality while achieving major power savings. We propose a novel on-line technique for dynamic backlight scaling. Our approach is HVS (i.e. Human Visual System) and image structure-aware. We provide a fully operational implementation of the proposed framework by which we carried out a full characterization of the overall system power consumption versus QoS.