An on-line content based image monitoring system

This paper proposed a new scheme for an online content based image monitoring system, which can filter unexpected images from the Internet, support searching, detecting, and recognizing images, video and multimedia data. The approach includes three parts. First is texture feature extraction with quasi-Gabor filters. These filters are constructed in different directions and sizes in the image frequency domain. This avoids convolution and multiplication with images spatially. Second, the extracted features are sent to Kohonon neural networks to perform dimension reduction. The outputs of the Kohonon network are then fed to a neural network classifier to get the final classification result. The proposed approach has been applied in our content monitoring system, which can filter unexpected images and generate an alarm by pre-defined requirements.