• 통합자연과학논문집
• /
• 제5권2호
• /
• pp.120-126
• /
• 2012

This paper describes the algorithm that lowers the dimension, maintains the gesture recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.311-318
• /
• 2022

Tobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.

• 음성과학
• /
• 제8권2호
• /
• pp.83-90
• /
• 2001

We proposed a probabilistic approach of using syllable bigrams to the word-spacing problem. Syllable bigrams are extracted and the frequencies are calculated for the large corpus of 12 million words. Based on the syllable bigrams, we performed three experiments: (1) automatic word-spacing, (2) detection and correction of word-spacing errors for spelling checker, and (3) automatic insertion of a space at the end of line in the character recognition system. Experimental results show that the accuracy ratios are 97.7 percent, 82.1 percent, and 90.5%, respectively.

• 한국정밀공학회지
• /
• 제31권11호
• /
• pp.987-992
• /
• 2014

Register control of roll-to-roll printing system for printed electronics requires accurate measurement of register errors. The register marks used for the recognition of patterns position between layers have inherently defects due to low printability of register marks themselves, which brings out inaccurate register accuracy and consequently low performance of printed electronics devices. In this study, the compensation methods for the unrecognized or missing register data are proposed to improve the recognition and consequently the control performance of register accuracy in roll-to-roll printing equipment. The compensation methods using the prior data and the linear interpolation are proposed and compared with the case without compensation for the simulation as well as experiment. Only the linear interpolation method could successfully compensate the missing data and consequently improve the register control performance. We should apply the compensation process of the register errors to improve the register control accuracy in the roll-to-roll printing equipment.

• 대한음성학회지:말소리
• /
• 제48호
• /
• pp.127-139
• /
• 2003

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Korean speak Japanese. For this purpose we also develop phoneme recognizers for Korean and Japanese. Experimental results show that the machine scores of the proposed recognizer correlate with expert ratings well.

• Transactions on Control, Automation and Systems Engineering
• /
• 제2권1호
• /
• pp.76-83
• /
• 2000

A measurement technique of a sea height of burst is introduced for a proximate test using the image recognition of video cameras. In the burst of fuse on the ocean, the burst center of fuse, the sea surface level and the height of calibration poles are measured by the process of image obtained from cameras. Finally, the height of burst of fuse can be computed by Hough transform algorithm. The error compensation algorithms are proposed to eliminate the errors caused by camera level and environmental parameters. As a result of experiment, it has been proved that the proposed measurement system shows the recognition of the center point of the burst image with ${\pm}$0.5m error.

• 한국콘텐츠학회논문지
• /
• 제5권2호
• /
• pp.229-242
• /
• 2005

우리는 스캔된 한글 문서 영상에 대한 전문(full-text) 검색 시스템을 구축하였다. 이 시스템은 크게 전처리부, 인식부, 그리고 검색부로 구성되어 있다 검색 알고리즘은 k순위까지의 인식 결과를 이용한다. 이 방법은 검색 성능이 인식 오류에 둔감할 뿐만 아니라, 재현률과 정확률을 사용자가 조절할 수 있는 장점을 갖는다. 객관적인 성능 평가를 위해 KISTI가 제공하는 정보과학회 논문지 영상을 실험에 사용하였다. 인식과 검색 성능을 통하여 시스템이 실용적임을 보였다.

• 음성과학
• /
• 제10권3호
• /
• pp.225-239
• /
• 2003

In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the recognition results, and filler models, anti-subword models and N-best decoding results are considered as an alternative hypothesis for likelihood ratio scoring. We also examine different methods to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clustering. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance and N-best decoding method show better performance than other methods, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.

• International Journal of Contents
• /
• 제10권4호
• /
• pp.63-68
• /
• 2014

In this paper, we propose a smart system that can optically recognize a music score within a document and can play the music after recognition. Many historic handwritten documents have now been digitalized. Converting images of a music score within documents into digital files is particularly difficult and requires considerable resources because a music score consists of a 2D structure with both staff lines and symbols. The proposed system takes an input image using a mobile device equipped with a camera module, and the image is optimized via preprocessing. Binarization, music sheet correction, staff line recognition, vertical line detection, note recognition, and symbol recognition processing are then applied, and a music file is generated in an XML format. The Music XML file is recorded as digital information, and based on that file, we can modify the result, logically correct errors, and finally generate a MIDI file. Our system reduces misrecognition, and a wider range of music score can be recognized because we have implemented distortion correction and vertical line detection. We show that the proposed method is practical, and that is has potential for wide application through an experiment with a variety of music scores.

• 한국통신학회논문지
• /
• 제19권6호
• /
• pp.1140-1148
• /
• 1994

본 논문에서는 음성신호의 프랙탈 차원을 이용하여 한국어 모음인식 실험을 수행하였다. 프랙탈 차원은 Minkowski-Bouligand 차원을 사용하였으며, 형태학적 커버링(morphological covering) 방법을 이용하여 구하였다. 프렉탈 차원과 더불어 기존에 우수한 음성 인식 파라메타로 알려져 있는 LPC 켐스트럼(cepstrum)을 함께 사용하였으며, 프랙탈 차원의 음성인식에의 유용성 여부를 조사하였다. 다양한 자음환경에서의 모음인식 실험결과, LPC 켐스트럼 만을 사용하는 경우 및 프렉탈 차원과 LPC 켐스트럼을 함께 사용하는 경우의 모음 오인식율이 각각 5.6% 및 3.2%로 얻어졌다. 이는 LPC 켑스트럼에 프렉탈 차원을 추가함으로써 오인식되는 데이터가 40%이상 감소되는 결과이며, 프랙탈 차원이 음성인식에 있어서 유용한 특징 파라메터임을 보여준다.