Search

A face detection method for the color image with complex background is presented, which is a mixed skin-color segmentation model in both YCbCr and HIS color space constructed; The mixed skin-color segmentation model can be used to segment of possible skin regions in the original image. After skin-color segmentation, the geometrical shape information of face and the maximum of the complexity of eyes in faces can be used to detect face's position accurately. Experimental results show that the proposed approach can effectively prevent the side effects on the image caused by light condition, reduce the undetected rate, increase the speed of the face detection. Compared with other methods, this method has a very good result.

Directing towards the characteristics and importance of copper strips surface inspection, this paper proposes a copper strips surface inspection system based on artificial intelligence from the standpoint of artificial intelligence. It uses computer vision to capture defects images, uses Hu invariant moments as the eigenvectors and uses BP neural network based on genetic algorithm combined with expert system to train and learn the samples. The trained weights are used to diagnose as the knowledge base and a copper surface defects inspection system based on intelligent fusion is constructed . The experimental results proved that intelligent fusion model can compliment all kinds of intelligent models and has a better performance than single model on copper strips surface inspection.

In this paper, novel video transmission architecture is proposed to meet the error robust requirement of wireless video communications. This architecture uses user-defined protocol to provide efficient bandwidth access from wireless link. By taking the time-varying wireless channel condition and video codec characteristics into account, first, we present an end-to-end transport architecture for video streaming over wireless network. Second, we adopt channel of Bernoulli channel model from application layers of 3G networks. And we propose a dynamically estimate the time-varying wireless network condition through estimate of throughout, RTT and merit of packet delay time. Third, we use H.264 as an experiment platform. A data partition scheme is also used to enhance error resilience performance. This architecture is also suitable for various motion compensation based standards like H.261, H.263 series, MPEG-1, MPEG-2, MPEG-4. The simulation results show our strategies can significantly improve the robustness of wireless video transmission.