• ETRI Journal
• /
• 제33권1호
• /
• pp.78-88
• /
• 2011

In this paper, we present the Touch Text exTractor (Touch TT), an interactive text segmentation tool for the extraction of scene text from camera-based images. Touch TT provides a natural interface for a user to simply indicate the location of text regions with a simple touchline. Touch TT then automatically estimates the text color and roughly locates the text regions. By inferring text characteristics from the estimated text color and text region, Touch TT can extract text components. Touch TT can also handle partially drawn lines which cover only a small section of text area. The proposed system achieves reasonable accuracy for text extraction from moderately difficult examples from the ICDAR 2003 database and our own database.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• 음성과학
• /
• 제7권2호
• /
• pp.235-244
• /
• 2000

This paper was focused on realizing the text-independent speaker recognizer using the VQ and GMM algorithm and studying the characteristics of the speaker recognizers that adopt these two algorithms. Because it was difficult ascertain the effect two algorithms have on the speaker recognizer theoretically, we performed the recognition experiments using various parameters and, as the result of the experiments, we could show that GMM algorithm had better recognition performance than VQ algorithm as following. The GMM showed better performance with small training data, and it also showed just a little difference of recognition rate as the kind of feature vectors and the length of input data vary. The GMM showed good recognition performance than the VQ on the whole.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1994년도 춘계공동학술대회논문집; 창원대학교; 08월 09일 Apr. 1994
• /
• pp.703-712
• /
• 1994

This paper presents an automatic conversion of machining data from the orthographic views of press mold by feature recognition rule. The system includes following 6 modules : separation of views, function support, dimension text recognition, feature recognition, dimension text check and feature processing modules. The characteristic of this system is that with minimum user intervention, it recognizes basic features such as holes, slots, pockets and clamping parts and thus automatically converts CAD drawing details of press mold into machining data using 2D CAD system instead of using an expensive 3D Modeler. The system is developed by using IBM-PC in the environment of AutoCAD R12, AutoLISP and MetaWare High C. Performance of the system is verified as a good interfacing of CAD and CAM when applied to a lot of sample drawings.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.103-106
• /
• 2005

In this paper, we propose a language modeling approach to improve the performance of a large vocabulary continuous speech recognition system. The proposed approach is based on the active learning framework that helps to select a text corpus from a plenty amount of text data required for language modeling. The perplexity is used as a measure for the corpus selection in the active learning. From the recognition experiments on the task of continuous Korean speech, the speech recognition system employing the language model by the proposed language modeling approach reduces the word error rate by about 6.6 % with less computational complexity than that using a language model constructed with randomly selected texts.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.605-608
• /
• 2002

A text-dependent speaker recognition system using a robust matching process is studied. The feature histogram of LPC cepstral coefficients for matching is used. The matching process uses mixture network with penalty scores. Using probability and shape comparison of two feature histograms, similarity values are obtained. The experiment results will be shown to show the effectiveness of the proposed algorithm.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.373-376
• /
• 2002

This paper represents a survey of a variety thresholding techniques including both global and local thresholding. Several thresholding methods are examined in detail to evaluate their performance based on a given set of test images. We also attempt to evaluate the performance of several thresholding methods for construction field documents image recognition system using a broken line structures, broken symbols and text, blurring of lines, symbols and text, noise in homogeneous areas measure as a criterion functions.

• 정보처리학회논문지B
• /
• 제10B권6호
• /
• pp.673-680
• /
• 2003

이 논문은 문맥 독립 화자인식에 사용될 벡터 양자기의 설계법 개선에 관한 연구이다. 구체적으로 벡터 양자기 코드북 생성 과정에서 특징 벡터 공간을 분할하여, 양자기 설계 시 학습에 필요한 계산 복잡도를 획기적으로 줄이는 방법을 제안한다. 제안된 공간 분할 벡터 양자기 설계법은 저자가 제안한 문맥 종속 화자인식을 위한 준비반복 벡터 양자기 설계법의 벡터 공간에 대한 일반화이다. 공간 분할 벡터 양자기 설계법은 종래의 설계법이 코드북 생성에 반복적 학습 설계를 사용한다는 것과 대조를 이룬다. 또한 공간 분할 벡터 양자기 설계법의 특징은 다음과 같다. 첫째, 이 설계법은 특징 벡터 공간을 분할한 공간 분할 군집을 이용함으로써 반복 학습을 하지 않는다. 둘째, 설계된 각 양자 영역은 공간 분할 군집의 양자 영역을 원용하며, 양자점은 각각의 통계 분포에 대해 최적점으로 설정된다. 셋째, 공간 분할 군집은 특징 벡터 집합에 대해 표본 벡터 생성법(CSVQ1, 2), 특징 벡터 공간에 대해 균일 초격자 구조 생성법(CSYQ3)으로 형성하였다. 수치 실험은 화자 10명이 발성한 50개의 문장에 대해 문맥 독립 화자인식 실험으로 수행되었다. 특징계수는 12차 멜켑스트럼 벡터를 사용하였고 각각의 공간 분할 코드북 생성법에 대해 코드북 크기를 32부터 128까지 변화시키면서 기존의 벡터 양자기 인식법과 비교하였다. 제안된 방법은 표본 벡터 생성법을 사용한 경우 인식률 100%로 기존의 방법과 같은 결과를 보였다. 따라서 제안된 공간 분할 벡터 양자기 설계법은 설계에 필요한 계산량이 획기적으로 줄면서 인식률은 보존되어 문맥 독립 화자 인식에 새로운 대안이 되며 또한 특징 벡터 공간을 설정할 수 있는 다양한 응용에 적용이 가능할 것으로 사료된다.

• 한국동물학회:학술대회논문집
• /
• 한국동물학회 1994년도 한국생물과학협회 학술발표대회
• /
• pp.103.2-103
• /
• 1994

No Abstract, See Full Text