• Smart Media Journal
• /
• v.1 no.4
• /
• pp.59-71
• /
• 2012

Since mobile phones are used as common communication devices, their applications are increasingly important to human's life. Using smart-phones camera to collect daily life environment's information is one of targets for many applications such as text recognition, object recognition or context awareness. Studies have been conducted to provide important information through the recognition of texts, which are artificially or naturally included in images and movies acquired from mobile phones. In this study, a character segmentation method that improves character-recognition accuracy in images obtained from mobile phone cameras is proposed. The proposed method first classifies texts in a given image to printed letters and handwritten letters since segmentation approaches for them are different. For printed letters, rough segmentation process is conducted, then the segmented regions are integrated, deleted, and re-segmented. Segmentation for the handwritten letters is performed after skews are corrected and the characters are classified by integrating them. The experimental result shows our method achieves a successful performance for both printed and handwritten letters as 95.9% and 84.7%, respectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.84-87
• /
• 2018

Handwritten letter recognition is important for numerous real-world applications and many topics like human-machine interaction, education, entertainment, and more. This paper describes the implementation of a real-time handwritten letters recognition system on a common embedded computer. Recognition is performed using a customized convolutional neural network, which was designed to work with low computational resources such as the Raspberry Pi platform. The experimental results show that the proposed real-time system achieves an outstanding performance in the accuracy rate and the response time for recognition of twenty-six handwritten letters.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.495-502
• /
• 2018

The advent of deep learning technology has made rapid progress in handwritten letter recognition in many languages. Handwritten Chinese recognition has improved to 97.2% accuracy while handwritten Japanese recognition approached 99.53% percent accuracy. Hanguel handwritten letters have many similar characters due to the characteristics of Hangeul, so it was difficult to recognize the letters because the number of data was small. In the handwritten Hanguel recognition using Hybrid Learning, it used a low layer model based on lenet and showed 96.34% accuracy in handwritten Hanguel database PE92. In this paper, 98.64% accuracy was obtained by organizing deep CNN (Convolution Neural Network) in handwritten Hangeul recognition. We designed a new network for handwritten Hangeul data based on GoogLenet without using the data augmentation or the multitasking techniques used in Hybrid learning.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.577-580
• /
• 1997

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.167-173
• /
• 2023

Hangul is unique compared to other Asian languages because of its simple letter forms that combine to create syllabic shapes. There are 24 basic letters that can be combined to form 27 additional complex letters. This produces 51 graphemes. Hangul optical character recognition has been a research topic for some time; however, handwritten Hangul recognition continues to be challenging owing to the various writing styles, slants, and cursive-like nature of the handwriting. In this study, a dataset containing thousands of samples of 51 Hangul graphemes was gathered from 110 freshmen university students to create a robust dataset with high variance for training an artificial neural network. The collected dataset included 2200 samples for each consonant grapheme and 1100 samples for each vowel grapheme. The dataset was normalized to the MNIST digits dataset, trained in three neural networks, and the obtained results were compared.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.54-64
• /
• 1999

This paper proposes an efficient handwritten English word recognition scheme which can be applied practical applications. To effectively use the lexicon which is available in most handwriting related applications, the lexicon entries are introduced in the early stage of the recognition. Dynamic programming is used for matching between over-segmented character segments and letters in the lexicon entries. Character segmentation statistics which can be obtained while the training is being performed are used to adjust the matching window size. Also, the matching results between the character segments and the letters in the lexicon entries are cached to avoid repeat of the same computation. In order to verify the effectiveness of the proposed methods, several experiments were performed using thousands of word images with various writing styles. The results show that the proposed methods significantly improve the matching speed as well as the accuracy.

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.653-668
• /
• 2012

In this study, an improved HMM based recognition model is proposed for online English and Korean handwritten characters. The pattern elements of the handwriting model are sub character strokes and ligatures. To deal with the problem of handwriting style variations, a modified Hierarchical Clustering approach is introduced to partition different writing styles into several classes. For each of the English letters and each primitive grapheme in Korean characters, one HMM that models the temporal and spatial variability of the handwriting is constructed based on each class. Then the HMMs of Korean graphemes are concatenated to form the Korean character models. The recognition of handwritten characters is implemented by a modified level building algorithm, which incorporates the Korean character combination rules within the efficient network search procedure. Due to the limitation of the HMM based method, a post-processing procedure that takes the global and structural features into account is proposed. Experiments showed that the proposed recognition system achieved a high writer independent recognition rate on unconstrained samples of both English and Korean characters. The comparison with other schemes of HMM-based recognition was also performed to evaluate the system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.723-726
• /
• 2004

문자들 중에는 매우 비슷한 모양을 갖고 있는 문자가 존재하기 때문에 오인식은 이러한 유사한 문자들 사이에서 일어날 경우가 많다고 볼 수 있다. 즉, 입력된 문자가 유사한 다른 문자에 대응하는 모델에서 발생 확률이 가장 높게 나와 오인식이 되었다고 할지라도, 해당 모델에서는 입력된 문자의 발생 확률도 여전히 높다고 볼 수 있다. 본 논문에서는 사전을 통한 후처리 시, 오인식 된 단어에서 사용된 모델들을 통해 오인식을 보정하는 방법을 제안한다.

• (The)Study of the Eastern Classic
• /
• no.34
• /
• pp.167-206
• /
• 2009

This paper discovers and introduces the collection of letters, "A Collector of Correspondence from Chinese Intellectuals (中朝學士書翰錄)" which was made by Kim Youngjak(1802~1868) who had collected the letters from Chinese intellectuals. "A Collector of Correspondence from Chinese Intellectuals (中朝學士書翰錄)" is a collector which contains handwritten letters to Kim Youngjak from Chinese people such as cheng gong shou(程恭壽), weng xue han(翁學涵), zhang bing yan(張丙炎), shao yan han(少言翰), and li wen yuan(李文源). Kim Youngjak had frequent meetings with Chinese intellectuals not only directly but also indirectly. He had exchanged letters with li bo heng(李伯衡), shuai fang wei(帥方蔚) for 30 years. In 1858, he went to Beijing and met Chinese intellectuals ye ming li(葉名澧), zhang bing yan(張丙炎), wu kun tian(吳昆田), cheng gong shou(程恭壽), and zhao guang(趙光). After coming back to Chos?n, he continued to exchange letters with them. "A Collector of Correspondence from Chinese Intellectuals (中朝學士書翰錄)" contains autograph letters by Kim Youngjak and Chinese intellectuals. It has ten letters for Kim Youngjak written by cheng gong shou(程恭壽), weng xue han(翁學涵), zhang bing yan(張丙炎), shao yan han(少言翰) and so on. One letter and five poems which zhao ting huang(趙廷璜) wrote to the son of Kim are also contained. The letters by zhao ting huang(趙廷璜) shows a sincere friendship with Kim Youngjak. The relationship between li bo heng(李伯衡) (who had exchanged letters with Kim for 30 years) and his son li wen yuan(李文源) proves that the cultural interchange between Korea and China had lasted successively. Kim Youngjak has not been widely known in academic circles yet but should not be ignored for the study in the cultural interchange between Korea and China. He proposed to have a relationship with li bo heng(李伯衡) and shuai fang wei(帥方蔚) first and they sent back positively. Therefore, they had a literal and private relationship by only exchanging letters each other. Also considering the fact that Kim Youngjak, as a man of high birth, had a close relationship with Chinese intelletuals, we can notice that Chinese and Korean intellectuals had open minds based on sincerity and trust. This was possible because many intellectuals before him like Hong Daeyong made a basis of the tradition of companionship. At this point, the relationship between Kim Youngjak and Chinese intellectuals and "A Collector of Correspondence from Chinese Intellectuals (中朝學士書翰錄)" have an important value. The collections of Kim Youngjak's works contain only several letters and poems which he sent to Chinese intellectuals. Accordingly, the letters in "A Collector of Correspondence from Chinese Intellectuals (中朝學士書翰錄)" are important to understand the aspects of their interchange.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.132-137
• /
• 2004

Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.