• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.76-80
• /
• 1993

In this paper we discuss optimization of neural network parameters, such as inclination of the sigmoid function, the numbers of the input layer's units and the hidden layer's units, considering application to recognition of hand written Hangul. Hangul characters are composed of vowels and consonants, and basically classified to six patterns by their positions. Using these characteristics of Hangul, the pattern of a given character is determined by its peripheral distribution and the other features. After then, the vowels and the consonants are recognized by the optimized neural network. The constructed recognition system including a neural network is applied to non-learning Hangul written by some Korean people, which are the names randomly taken from Korean spiritual and cultural research institute.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1379-1389
• /
• 1996

Hangul character always consists of consonants-vowel-consonants in order. Using this point, this paper proposes an approach to design a model for spotting each letter in Hangul, and then recognize characters based on the spotting results. The network model consist of a set of HMMs. The letter search is carried out by Viterbi algorithm, while character recognition is performed by searching the lattice of letter hypotheses. Experimental results show that, in spite of simple architecture of recognition, the performance is quite high reaching 87.47% for discrete regular characters. In particular the approach shows highly plausible segmentation of letters in characters.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1019-1022
• /
• 1999

In this paper, we analysis the effect of a dictionary in a handwritten Hangul word recognition problem in terms of its size and the length of the words in it. With our experimental results, we can account for the word recognition rate depending not only on character recognition performance, but also much on the amount of the information that the dictionary contains, as well as the reduction rate of a dictionary.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.951-959
• /
• 2017

In this paper, we design and implement an Android-based Hangul food menu recognition application that recognizes characters from images captured by a smart phone. Optical Character Recognition (OCR) technology is divided into preprocessing, recognition and post-processing. In the preprocessing process, the characters are extracted using Maximally Stable Extremal Regions (MSER). In recognition process, Tesseract-OCR, a free OCR engine, is used to recognize characters. In the post-processing process, the wrong result is corrected by using the dictionary DB for the food menu. In order to evaluate the performance of the proposed method, experiments were conducted to compare the recognition performance using the actual menu plate as the DB. The recognition rate measurement experiment with OCR Instantly Free, Text Scanner and Text Fairy, which is a character recognizing application in Google Play Store, was conducted. The experimental results show that the proposed method shows an average recognition rate of 14.1% higher than other techniques.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.24-35
• /
• 2018

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1181-1185
• /
• 1991

Unlike printed character, the recognition of Hand written one has various kinds of difficulties due to the existence of the huge pattern associated with the person who writes. Therefore, in general, recognition of Hand written characters requires an algorithm which takes into consideration of the individual differences. Hangul characters are basically made of straight lines and circles. They can be represented in terms of feature parameters such as the end point of the straight line, the length and the angle. Then all Hangul characters can be represented by the number of basic segments(-, /, vertical bar, O) multiplied by the feature parameters respectively. In this study we propose a method for recognizing Hand written Hangul characters in terms of fuzzy inference.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.33-50
• /
• 1990

Recently, neural networks have been proposed as computaional models for hard prlblems that the brain appears to solve easily. This paper proposes a hierarchical network which practically recognizes printed Hangul characters based on the various psychological stueies. This system is composed of a type classification netwotk and six recognition networks. The former clessifier input character images into one of the six thper by their overall sturcture, and the latter further classify them into character code. Extperiments with most frequently used 990 printed hangul characters conform the superiority of the propsed system. After all, neural nework approach turns out to be very reasonable through a comparison with statistical classifier and an analysis of mis-classification and generalization capability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.887-894
• /
• 2006

This paper proposes a new method that detects the intersection points of handwritten Hangul strokes using run-length. The method firstly finds the strokes' width of handwritten Hangul characters using both horizontal and vertical run-lengths, secondly extracts horizontal and vertical strokes of a character utilizing the strokes' width, and finally detects the intersection points of the strokes exploiting horizontal and vertical strokes. The analysis of both the horizontal and the vertical strokes doesn't use the strokes' angles but both the strokes' width and the changes of the run-lengths. The intersection points of the strokes become the candidated parts for phoneme segmentation, which is one of main techniques for off-line handwritten Hangul recognition. The segmented strokes represent the feature for handwritten Hangul recognition.

• Korean Journal of Cognitive Science
• /
• v.3 no.1
• /
• pp.139-160
• /
• 1991

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.1-5
• /
• 2003

In this paper, we realized a system that converts the character images of the printed Korean alphabet (Hangul) to the editable text documents by using the black and white CCD camera, We were able to abstract the contours information of the character which is based on the structural character by using the boundary tracing technique that is strong to the noise on the character recognition. By using the contours information, we recognized the horizontal vowels and vertical vowels of the character image and classify the character into the six patterns. After that, the character is divided to the unit of the consonant and vowel. The vowels are recognized by using the maximum length projection. The separated consonants are recognized by comparing the inputted pattern with the standard pattern that has the phase information of the boundary line change. We realized a system that the recognized characters are inputted to the word editor with the editable KS Hangul completion type code.