• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.5
• /
• pp.183-189
• /
• 2002

In this paper, we propose an algorithm to extract the E-mail address in calling card images. Firstly, text regions are separated from background. in the image. To do this, the properties of e-mail addresses and the texture features in the image is used. And then, each text region is explored to find the candidates of e-mail region. Finally, each candidate is divided into characters to find at-symbol(@), that is, e-mail region. The experimental results show hit-ratio over 93.3％ for the various kind of calling cards containing different fonts, background images, caricatures.

• Journal of Korea Multimedia Society
• /
• v.15 no.2
• /
• pp.204-214
• /
• 2012

This paper proposes an image segmentation for a vision-based automated defect inspection system on surface image of TFT-LCD(Thin Film Transistor Liquid Crystal Display) panels. TFT-LCD images have non-uniform brightness, which is hard to finding defective regions. Although there are several methods or proposed algorithms, it is difficult to divide the defect with high reliability because of non-uniform properties in the image. Kamel and Zhao disclosed a method which based on logical stage algorithm for segmentation of graphics and character. This method is a one of the local segmentation method that has a advantage. It is that characters and graphics are well segmented in an image which has non-uniform property. As TFT-LCD panel image has a same property, so this paper proposes new algorithm to segment regions of defects based on Kamel and Zhao's algorithm. Our algorithm has an advantage that there are a few ghost objects around the defects. We had experiments to prove performance in real TFT-LCD panel images, and comparing with the FFT(Fast Fourier Transform) method which is used a bandpass filter.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1329-1338
• /
• 2021

There are rarely effective methods to help visually impaired people when they want to know the expiration date of products excepted to only Braille. In this study, we developed an expiration date notification system based on YOLO and OCR for visually impaired people. The handicapped people can automatically know the expiration date of a specific product by using our system without the help of a caregiver, fast and accurately. The proposed system is worked by four different steps: (1) identification of a target product by scanning its barcode; (2) segmentation of an image area with the expiration date using YOLO; (3) classification of the expiration date by OCR: (4) notification of the expiration date by TTS. Our system showed an average classification accuracy of about 86.00% when blindfolded subjects used the proposed system in real-time. This result validates that the proposed system can be potentially used for visually impaired people.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.85-98
• /
• 2005

Recently, a lot of researches about mobile vision using Personal Digital Assistant(PDA) has been attempted. Many CPUs for PDA are integer CPUs, which have no floating-computation component. It results in slow computation of the algorithms peformed by vision system or image processing, which have much floating-computation. In this paper, in order to resolve this weakness, we propose the Client(PDA)/server(PC) architecture which is connected to each other with a wireless LAN, and we construct the system with pipelining processing using two CPUs of the Client(PDA) and the Server(PC) in image sequence. The Client(PDA) extracts tentative text regions using Edge Density(ED). The Server(PC) uses both the Multi-1.aver Perceptron(MLP)-based texture classifier and Connected Component(CC)-based filtering for a definite text extraction based on the Client(PDA)'s tentativel99-y extracted results. The proposed method leads to not only efficient text extraction by using both the MLP and the CC, but also fast running time using Client(PDA)/server(PC) architecture with the pipelining processing.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.541-543
• /
• 1998

본 논문에서는 선형적으로 기울어진 문서 영상의 기울기를 검출하기 위한 단순하면서도 효과적인 알고리즘을 제안한다. 문서 내의 인접한 두 행 사이에는 일정한 두께의 공백 행이 존재하며, 그 공백 행의 기울기는 실제 문서의 기울어진 정도를 반영한다는 사실에 기인한다. 먼저, 간단한 모폴로지 연산을 이용하여 문자행 영역과 공백행 영역을 분리한 후, 이를 일정 간격으로 수직 샘플링하여 수직선 상에 있는 모든 공백행의 중심점(행간점)을 찾는다. 전체 영상으로부터 동일한 공백 행상에 있는 임의의 두 행간점간에 계산된 기울기들의 분포를 보면 실제 문서의 기울기에서 최대 값을 가진다. 제안한 알고리즘을 다양한 형태의 가로쓰기 문서(검출 가능한 최대 기울기 : $\pm$45$^{\circ}$)에 적용하여 0.5$^{\circ}$의 오차범위 내에서 정확한 결과를 얻을 수 있음을 보인다.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.391-401
• /
• 2022

As deep learning-based object detection and recognition research have been developed recently, the scope of application to industry and real life is expanding. But deep learning-based systems in the construction system are still much less studied. Calculating materials in the construction system is still manual, so it is a reality that transactions of wrong volumn calculation are generated due to a lot of time required and difficulty in accurate accumulation. A fast and accurate automatic drawing recognition system is required to solve this problem. Therefore, we propose an AI-based automatic drawing recognition accumulation system that detects and recognizes steel materials in construction drawings. To accurately detect steel materials in construction drawings, we propose data augmentation techniques and spatial attention modules for improving small object detection performance based on YOLOv4. The detected steel material area is recognized by text, and the number of steel materials is integrated based on the predicted characters. Experimental results show that the proposed method increases the accuracy and precision by 1.8% and 16%, respectively, compared with the conventional YOLOv4. As for the proposed method, Precision performance was 0.938. The recall was 1. Average Precision AP_0.5 was 99.4% and AP_0.5:0.95 was 67%. Accuracy for character recognition obtained 99.9.% by configuring and learning a suitable dataset that contains fonts used in construction drawings compared to the 75.6% using the existing dataset. The average time required per image was 0.013 seconds in the detection, 0.65 seconds in character recognition, and 0.16 seconds in the accumulation, resulting in 0.84 seconds.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.275-278
• /
• 2020

In this paper, we proposed a deep learning based character recognition system through virtual data generation. In order to secure the learning data that takes the largest weight in supervised learning, virtual data was created. Also, after creating virtual data, data generalization was performed to cope with various data by using augmentation parameter. Finally, the learning data composition generated data by assigning various values to augmentation parameter and font parameter. Test data for measuring the character recognition performance was constructed by cropping the text area from the actual image data. The test data was augmented considering the image distortion that may occur in real environment. Deep learning algorithm uses YOLO v3 which performs detection in real time. Inference result outputs the final detection result through post-processing.

• Journal of Navigation and Port Research
• /
• v.28 no.8
• /
• pp.727-733
• /
• 2004

In the car license plate recognition system, it is very important to extract the part of the license plate from the car image. In this paper, I use ACL algorithm to extract the license plate image from car image. The ACL algorithm is used to color and luminance information, either. Therefore in this paper, suggested algorithm is called ACL algorithm The ACL algorithm uses color, luminance information and the rate of license plate information Each of these information are used to exact area of license plate. The result of experiment to extract the car license plate with ACL algorithm is 97% extraction rate. The result of experiment with ACL algorithm for the character region, character recognition is 92% extraction rate.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.339-342
• /
• 2014

현재 차량의 출입통제 및 주정차 단속 등이 차량 번호판 자동 인식 시스템을 통해 자동화 되고 있다. 본 논문은 촬영 각도에 따라 기울어지거나 왜곡된 번호판에 대해서도 잘 동작하는 번호판 영역 추출 알고리즘을 제안한다. 번호판의 배경과 문자의 밝기 대비가 커서 그 분포가 이원 양상을 보인다는 점을 이용하여 번호판의 중심부와 대략적인 후보 영역을 추출한다. 이후 허프 변환을 통하여 번호판의 네 모서리에 해당하는 직선을 검출한다. 이들 네 직선의 교점이 번호판의 꼭짓점이 된다. 네 꼭짓점의 좌표를 이용하여 왜곡된 번호판을 실제 번호판의 가로와 세로 비율에 맞는 정규화 된 모양으로 변환한다. 차량의 측면 1m~3m 사이의 다양한 거리에서 촬영한 이미지로 실험한 결과 일반적인 실외 조명 아래에서 차체의 색에 관계없이 번호판 영역 추출에 성공하였다.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1113-1118
• /
• 2002

In recognition system of the car license plate, the most important is to extract the image of the license plate from a car image. In this paper, we use ACL (Adaptive Color Luminance) algorithm to extract the license plate image from a car image. The ACL algorithm that uses color and luminance information of a car image is used to extract the image of the license plate. In this paper, color, luminance and other related information of a car image are used to extract the image of the license plate from that of a car. In this reason, we call it the ACL algorithm. The ACL algorithm uses color, luminance information and other related information of a license plate. These informations are avaliable to exact the image of the license plate. The rate of extracting the image of the license plate from a car is 97%. The experimental result of the ACL algorithm for the character region is 92%.