Research And Implementation Of An Automatic Picture Oriented Television Advertisement Monitoring System

Commonly, the televising length, picture quality, and the televising time of the advertisement segments are wondered in television advertisement monitoring. To monitor the pictures'quality, we should focus on the advertisements'images. However, among the television advertisement monitoring systems in use at the present time, there is no veriest picture oriented system, the existing systems are mainly focus on the audio. This article introduces an automatic picture oriented television advertisement monitoring system. The system implements television advertisements monitoring in the way of pattern recognition together with image capturing and image binarization technologies.The system captures television signal with video capture card by DirectShow technique. To reduce computational complexity, the system captures the key-frames in fixed time interval.After the original data collection step, binarizing the captured images is needed to make the following steps more efficient. In the binarization module, aiming at the variety of the television pictures, this article ameliorates the mean algorithm and Otsu algorithm. Based on these two ameliorated algorithms, presents a new binarization algorithm that reduce computational complexity in the precondition of high-quality binarization.Since the monitored objects, the advertisements, are known , the system can extract samples of the advertisements, and use algorithms based on template match to recognize these advertisements. SSDA algorithm is adopted in this system. Because the pictures are all binary images, this article adjusts SSDA algorithm so that it can process binary images more efficiently, and an additional limitation, the absolute error accumulation times, are affiliated to insure the recognition correctness.