Off-line handwritten Thai name recognition for student identification in an automated assessment system

Abstract

In the field of pattern recognition, off-line handwriting recognition is one of the most intensive areas of study. This paper proposes an automatic off-line Thai language student name identification system which was built as a part of a completed off-line automated assessment system. There is limited work undertaken in developing off-line automatic assessment systems using handwriting recognition. To the authors' knowledge, none of the work on the proposed system has been performed on the Thai language. In addition the proposed system recognises each Thai name by using an approach for whole word recognition, which is different from the work found in the literature as most perform character-based recognition. In this proposed system, the Gaussian Grid Feature (GGF) and the Modified Direction Feature (MDF) extraction techniques are investigated on upper and lower contours, loops from full word contour images of each name sample, and artificial neural networks and support vector machine are used as classifiers. The encouraging recognition rates for both feature extraction techniques were achieved when applied on loop, upper and lower contour images (99.27% accuracy rate was achieved using MDF on artificial neural networks and 99.27% using GGF with a support vector machine classifier).

Short answer question examination using an automatic off-line handwriting recognition system and a novel combined feature

“…For HPCHC OFLAS, it was also found that the accuracy rate obtained when applying MDF3 [5] to HPCHC OFLAS was 95.7 1% compared to 94.09% when applying MDF. With CH, the best recognition and accuracy rates were obtained when applying MDF or MDF3 [5] to the CH OFLAS.…”

“…Recognition, Accuracy, and Efficiency Rates best efficiency rate of 80. 12% was obtained when using MDF3 [5] with the OFLAS.…”

An Automatic Student Verification System Utilising Off-Line Thai Name Components

“…All samples were scanned at 300 dpi and stored in grey-level format, then were binarised and saved in Portable Network Graphics (PNG) format. [4]. Another aspect to mention here is zoning.…”

“…The heads of a character can be found in various locations. Thai characters can be divided into three types according to the head [4], which are: 1) No-head character, for example, "ก" for a consonant, "า" for a vowel, and ‫"|"‬ for a voice tone mark.…”

“…This research proposed an automatic Student Verification System (SVS) using student name components. This research was an extension from Student Identification Systems (SIS) which were proposed in [4], [5]; the SISs were developed to identify students, so that their marks which were produced from handwritten short answer assessment system [6] can be recorded accordingly. In [4], [5], and [6], student name components were used to identify students, the student numbers were not used as it was planned that the verification system using the name components could be developed.…”