Real-time feature extraction from artificial marks using interline method

This paper describes an improvement on the interline method in order to include feature extraction using n Finite State Machine (FSM) on the directions followed by this algorithm. Normally, a feature extraction is based on edge or corner detection. Differential operators, such as Sobel operator, are used to detect edges and the SUSAN operator can be used to detect corners, both are good algorithms but they are computationally expensive. In our approach we are using marks on the end-effector to speed up the processing time. There is an off-line stage where the marks are learned. Next, user or operator can select the mark to follow, or a recognition stage is used to distinguish a learned mark. Once the mark is identified, the improved interline method is used to extract mark features, specifically corners, and implicity to track the end-effector. This approach is very simply, and it has the advantage of reducing the number of pixels points processed for stereo-images.