A Two-Stage Process for Accurate Image SegmentationN. W. Campbell, B. T. Thomas, T. Troscianko , A Two-Stage Process for Accurate Image Segmentation. Sixth International Conference on Image Processing and its Applications. ISBN 0 85296 692 X, pp. 655–659. July 1997. PDF, 260 Kbytes.
This paper describes a highly successful two-stage segmentation technique. The performance of this technique has been quantified on a large set of complex, outdoor scenes. In the first stage, a self-organising feature map is trained to perform the segmentation task. The addition of colour information, and the quantification of the technique using real-world data, extends the work of Mao and Jain. The second stage of the segmentation process overcomes the problem of over-segmentation by merging regions. It achieves this through use of a multi-layer perceptron.