• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.11
• /
• pp.2531-2542
• /
• 1997

This paper describes a method for region segmentation and string extractionin documents which are mixed with text, graphic and picture images by the use of the structural characteristic of connceted components. In segmentation of non-text regionas, with connection-characteristic functions which are made by structural characteristic of connected components, segmentation process is progressed. In the string extraction, first we organize basic-unit-region of which vertical and horizontal length are 1/4 of average length of connection components. Second, by merging the basic-unit-regions one other that have smaller values than a given connection intensity threshold. Third, by linking the word blocks with similar block anagles, initial strings are cresed. Finally the whold strings are generated by merging remaining word blocks whose angles are not decided, if their height and prosition are similar to the initial strings. This method can extract strings that are neither horizontal nor of various character sizes. Through computer exteriments with different style documents, we have shown that the feasibility of our method successes.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.120-131
• /
• 1997

This paper prsents a new method that automatically recognizes the dimension lines (consisting of shape lines, tail lines and extension lines) from the mechanical drawings. In the proposed method, the object and closed-loop symbols are separated from the character-free drawings. Then the object lines and interpretation lines are vectorized by using several techniques such as thinning, line-vectorization, and vector-clustering. Finally, after recognizing arrowheads by using pattern matching, we recognize dimension lines from interpretation lines by using arrohead's directional vector and centroid. By using the methods of geometric modeling and mathematical operation, the proposed method readility recognizes the dimension lines from complex drawings. Experimental resuls are presented, which are obtained by applying the proposed method to drawings drawn in compliance with the KS drafting standard.

• Journal of the Korean Society of Industry Convergence
• /
• v.3 no.3
• /
• pp.229-236
• /
• 2000

This paper proposes on the Hanguel character CAI system using image processing. For this, firstly, the characters written by elementary school students or foreigners arc captured by CCD camera. Secondly, Recognition is accomplished by pre-processing, thinning and recognition processes. Thirdly, strokes are separated and beauty evaluation is done by matching feature value of the input image from the similarity measure function. In particular, this paper describe to define the similarity measuring function using extracted factor values after getting the beauty evaluation factor values of the consonant in the entire CAI system. Finally, the effectiveness of the proposed system is demonstrated by experiments.

• The Journal of the Korea Contents Association
• /
• v.5 no.5
• /
• pp.33-42
• /
• 2005

In this paper, we propose a new training algorithm for improving pattern classification performance of ART neural network. The proposed train algorithm restricts unnecessary cluster generation and transition, applies the location extraction algorithm, and operates the reset system based on the agreement between the present learning pattern and the initial pattern. As a result, repetitive input of a pattern does not generate a new cluster and mis-recognition rate decreases.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1119-1130
• /
• 2018

Writing letters or patterns on a virtual space by moving a person's gaze is called "eye writing," which is a promising tool for various human-computer interface applications. This paper investigates the use of conventional eye writing recognition algorithms for the purpose of user-independent recognition of eye-written characters. Two algorithms are presented to build the user-independent system: eye-written region extraction using wavelet coefficients and template generation. The experimental results of the proposed system demonstrated that with dynamic positional warping, an F1 score of 79.61% was achieved for 12 eye-written patterns, thereby indicating the possibility of user-independent use of eye writing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.1
• /
• pp.213-219
• /
• 2004

This paper proposes speaker recognition algorithm which includes the pitch parameter for the peak and valley. The time-frequency hybrid method for pitch extraction is valuable in that it can improve resolution in the time domain and accuracy in the frequency domain at the same time. It makes reference pattern using membership function and performs vocal track recognition of common character using fuzzy pattern matching in order to include time variation width for non-linear utterance for proposed method, speaker recognition experiments are carried out using vowels and number sounds.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.6
• /
• pp.417-421
• /
• 2007

Recently, many studies have focused on extracting transliteration pairs from bilingual texts. Most of these studies are based on the statistical transliteration model. The paper discusses the limitations of previous approaches and proposes novel approaches called dynamic window and tokenizer to overcome these limitations. Experimental results show that the average rates of word and character precision are 99.0% and 99.78%, respectively.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.113-116
• /
• 2003

A person does communication between each other using language. But, In the case of disabled person, call not communicate own idea to use writing and gesture. We embodied communication system using the ERG so that disabled Person can do communication. After feature extraction of the EEG included facial muscle, it is converted the facial muscle into control signal. and then did so that can select character and communicate idea.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.237-241
• /
• 2002

In this paper, we describe how to represent hand witten decimal digits by a sequence of one to five fuzzy sets. Each fuzzy set represents an arc segment of the digit and is a Cartesian product of four fuzzy sets; the first is fur the arc length of the segment, the second is for the arc direction, the third is fur the arc shape, and the fourth is a crisp number indicating whether it has a junction point and if it has an end point of a stroke. We show that an arbitrary pair of these sequences representing two different digits is mutually disjoint. We also show that various forms of a digit written in different styles can be represented by the same sequence of fuzzy sets and hence the deviations due to different writers can be modeled by using these fuzzy sets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.345-359
• /
• 2017

Optical Character Recognition (OCR) that has been a main research topic of computer vision and artificial intelligence now extend its applications to detection of text area from video or image contents taken by camera devices and retrieval of text information from the area. This paper aims to implement a binarization algorithm that removes user intervention and provides robust performance to outdoor lights by using TopHat algorithm and channel transformation technique. In this study, we particularly concentrate on text information of outdoor signboards and validate our proposed technique using those data.