A. Pezeshk and R.L. Tutwiler (USA)
Image segmentation, feature extraction, document analysis, digital image processing
Automatic separation of the different layers of information in maps poses an immense challenge due to the heavy interconnectedness of these layers. This process is further complicated by the problem of mixed color pixels and aliasing induced by the scanning process. In this paper we present a new semi-interactive method to segment, reorient, and extract the text layer from scanned color images of topographic maps. The contour lines are initially extracted by treating the mixed color pixel problem. Linear features are subsequently removed using Multi-Angled Parallelism. Following the removal of the remaining non-character objects, individual characters are grouped into words using pyramid decomposition. Finally, text strings are reoriented to the horizontal direction using a novel geometric approach in conjunction with pyramid decomposition. .
Important Links:
Go Back
