Research of Face Location System Based on Human Vision Simulations

In this paper we present a robust face location system based on human vision simulations to automatically locate faces in color static images. Our method is divided into four stages. In the first stage we use a gauss low-pass filter to remove the fine information of images, which is useless in the initial stage of human vision. During the second and the third stages, our technique approximately detects the image regions, which may contain faces. During the fourth stage, the existence of faces in the selected regions is verified. Having combined the advantages of Bottom-Up Feature Based Methods and Appearance-Based Methods, our algorithm performs well in various images, including those with highly complex backgrounds.

色光适应条件下对人眼颜色感受性变化的研究及其机制的初步探讨

The fact of change in human vision sensitivity in color adaption was studied with the method of minimo step change. In this experiment, subjects were asked to judge the just-different threshold on 1° target stimulus which superimposed on 6° background. The target and the surrourding field flicked and different kinds of stimuli were shown to Ss. Data of Pre-color adaption and that of post-color adaption have been compared and ① Evidence of opponent effect is found. This result is contraversary to coefficient law and the "two process" hypothesis are supported; ② Opponent effect is strongly related to the kinds of stimuli ③ When the background light flicks, subjects sensitivity to target stimuli is obviously increased while under the condition of flicking target stimuli less increase can be found. But the increase in sensitivity seem to be not related with color adaption.

Novel approach for region merging and image segmentation for human-computer interaction

For the purpose of human-computer interaction (HCI), a vision-based gesture segmentation approach is proposed. The technique essentially includes skin color detection and gesture segmentation. The skin color detection employs a skin-color artificial neural network (ANN). To merge and segment the region of interest, we propose a novel mountain algorithm. The details of the approach and experiment results are provided. The experimental segmentation accuracy is 96.25%. (C) 2003 Society of Photo-Optical Instrumentation Engineers.