Geometric methods for optical character recognition
Joseph S. Mitchell, Georgios N. Sazaklis · 1997
Optical Character Recognition (OCR) is an important problem of both theoretical and practical interest. In this dissertation, we present solutions to three problems within the area of OCR: 1. A difficulty encountered by many OCR systems is confusion between similar shapes, when flexible matching is employed as a primary recognition mechanism. Our solution, constrained matching as a second stage classification technique, can discriminate between similar shapes using shape geometric attributes; thus the system is enabled to reach a final decision on the character identity. 2. Another important problem in OCR is the fast and reliable fixed-font recognition. We present a hierarchical classification technique that utilizes the concept of geometric probe trees from (4). At each node of the probe tree, a geometric probe collects information from the shape at hand, and makes a partial decision about its identity, eliminating certain candidates from further consideration. The probe tree can be constructed off-line in a preprocessing step and can provide us with high speed recognition for a fixed font. 3. We also present an extension of geometric probes, the prefix probing technique that solves the important practical problem of touching characters for a fixed font. Prefix probing is based on a forest of probe trees that succeeds in identifying each member from a sequence of touching characters independently of its neighbors. This avoids the excessive demands of a straightforward solution. To substantiate our methods, we have developed several tools, and present our experiments with scanned documents.