Segmentation of Handwritten Characters for Digitalizing Korean Historical Documents

Abstract

Abstract. The historical documents are valuable cultural heritages and sources for the study of history, social aspect and life at that time. The digitalization of historical documents aims to provide instant access to the archives for the researchers and the public, who had been endowed with limited chance due to maintenance reasons. However, most of these documents are not only written by hand in ancient Chinese characters, but also have complex page layouts. As a result, it is not easy to utilize conventional OCR(optical character recognition) system about historical documents even if OCR has received the most attention for several years as a key module in digitalization. We have been developing OCR-based digitalization system of historical documents for years. In this paper, we propose dedicated segmentation and rejection methods for OCR of Korean historical documents. Proposed recognition-based segmentation method uses geometric feature and context information with Viterbi algorithm. Rejection method uses Mahalanobis distance and posterior probability for solving out-of-class problem, especially. Some promising experimental results are reported.

A new algorithm for text segmentation based on stroke filter

“…The average recognition score, SA, of the segmented text image is represented by these two scores as follows: (12) where i and N denote the index and the number of characters, KG and KR are constants and Si, SG, and SR denote the total, geometric, and recognition scores of each character, respectively. KG and KR, are usually assigned as 0.3 and 5, respectively.…”

“…The optimal separation path is determined by using two scores: (1) the geometric score that is used to estimate the likelihood of "being a character" by geometric features and (2) the recognition score obtained by the character recognition function. The geometric score is calculated by using two character evaluators, the squareness (SQU) and the internal gap (GAP), which are estimated by the Parzen window [12] . If the geometric score is low, the sub-image is eliminated in the separation paths and not recognized, by which the overhead of recognition can be reduced.…”

Automatic Estimation of Age Distributions from the First Ottoman Empire Population Register Series by Using Deep Learning

“…Digitization of historical archives and application of information retrieval methods on them have gained pace in recent decades, including non-European handwritten archival collections [11]. Some historical documents might have a tabular structure, which makes it easier to analyze the layout.…”

Document Image Retrieval to Support Reading Mokkans

“…Recently, some research proposed supporting methods and systems to decode historical documents [1]- [3]. We also proposed a system to help archeologists decode mokkans.…”