Oscillatory neural networks are a recent approach for applications in image segmentation. Two positive aspects of such networks are its massively parallel topology and the capacity to separate the segments in time. On the other hand, limitations that restrict the practical application are found in the proposed oscillatory networks, such as the use of differential equations, implying high complexity for implementation in digital hardware, and limited capacity of segmentation. In the present paper, an oscillatory neural network suitable for image segmentation in digital vision chips is presented. This network offers several advantages, including unlimited capacity of segmentation. Preliminary results confirm the successful operation of the proposal in image segmentation and its good potential for real time video segmentation.
展开▼
