Historical review of OCR research and development

Abstract

In this paper research and development of OCR systems are considered from U historical point of t k v . The paper is mainly divided into two parts: the research and development of OCR systems, and the historical development of commercial OCR's. The R&D part is further diLided into two approaches: template matching and structure analysis. It has been shown that both approaches are coming closer and closer to each other arid it seems they tend to merge into one big stream. On [he other hand, commercial products can be classified into three generations, for each of which some represenfative OCR systems are chosen and described in some detail. Some comments on recent techniques applied to OCR such as expert systems, neural networks, and some open problems are also raised in this paper. Finally we present our views and hopes on future trends in this fascinating area.

Identification of Receipts in a Multi-receipt Image using Spectral Clustering

“…There has been a lot of research done in the area of Optical Character Recognition (OCR) [1]. There are several approaches and software available to identify text from scanned images.…”

“…Several techniques are used to recognize text in an image using various Optical Character Recognition techniques [1].…”

A hierarchical classifier for multifont digits

“…In order to select the feature to be extracted from the digit image, experiments have been carried out to evaluate the features reported in the literature [14,15]. In general, the features can be classified in two great groups according to their nature: global, they are based on the association of patterns examining the image of a global form, and structural, treat the image analyzing topological aspects (for example, holes, contour, skeleton, etc.).…”

“…Thus, the importance of the capacity of acquisition and " understanding " on the part of the computers is a fundamental aspect and in continuous study [9,14,20]. In this sense, a system of Optical Character Recognition (OCR) has as objective the conversion of independent form of characters written to codes that represent them and that are intelligible to the computer.…”

A Set of Features Extraction Methods for the Recognition of the Isolated Handwritten Digits

“…First only the recognition of isolated handwritten characters was investigated [1], [2], but later whole words were addressed [3]. Most of the systems reported in the literature until today consider constrained recognition problems based on vocabularies from specific domains, e.g.…”