Adaptive Colour Segmentation in Digital Video Images by means of Artificial Neural Networks and Morphological Operations

There are many industrial products that use digital video image processing for orientation control or object detection. Often object shape is used for classification. However, if detection task has to be performed very fast and there are many different candidate shapes for an object, other characteristic features have to be used. One of the most relevant object features can be colour. For example, the detection of human hands is a challenging problem, where a shape-based approach is unpromising, if detection has to be done in real time. The presented approach proves that a robust detection can be obtained by applying a neural network to the RGB values of digital video images and subsequent use of morphological operations. Furthermore, the claim for very small processing times is considered in the presented solution. Key-Words: Artificial Neural Networks, Digital Image Processing, Binary Morphological Operations