• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.25-37
• /
• 2024

This study proposes a novel automation system that integrates Optical Character Recognition (OCR) and Retrieval-Augmented Generation (RAG) technologies to enhance the efficiency of the ESG (Environmental, Social, and Governance) document review process. The proposed system improves text recognition accuracy by applying an ensemble model-based image preprocessing algorithm and hybrid information extraction models in the OCR process. Additionally, the RAG pipeline optimizes information retrieval and answer generation reliability through the implementation of layout analysis algorithms, re-ranking algorithms, and ensemble retrievers. The system's performance was evaluated using certificate images from online portals and corporate internal regulations obtained from various sources, such as the company's websites. The results demonstrated an accuracy of 93.8% for certification reviews and 92.2% for company regulations reviews, indicating that the proposed system effectively supports human evaluators in the ESG assessment process.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.2
• /
• pp.135-145
• /
• 2023

Recently, as deep learning technology has developed, various deep learning technologies have been introduced in handwritten recognition, greatly contributing to performance improvement. The recognition accuracy of handwritten Hangeul recognition has also improved significantly, but prior research has focused on recognizing 520 Hangul characters or 2,350 Hangul characters using SERI95 data or PE92 data. In the past, most of the expressions were possible with 2,350 Hangul characters, but as globalization progresses and information and communication technology develops, there are many cases where various foreign words need to be expressed in Hangul. In this paper, we propose a model that recognizes and combines the consonants, medial vowels, and final consonants of a Korean syllable using a multi-label classification model, and achieves a high recognition accuracy of 98.38% as a result of learning with the public data of Korean handwritten characters, PE92. In addition, this model learned only 2,350 Hangul characters, but can recognize the characters which is not included in the 2,350 Hangul characters

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.324-332
• /
• 2014

This paper presents a programmable System-On-a-chip for various embedded applications that need Neural Network computations. The system is fully implemented into Field-Programmable Gate Array (FPGA) based prototyping platform. The SoC consists of an embedded processor core and a reconfigurable hardware accelerator for neural computations. The performance of the SoC is evaluated using real image processing applications, such as optical character recognition (OCR) system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.10
• /
• pp.2059-2063
• /
• 2009

This paper presents a programmable System-On-a-chip (SoC) for various embedded smart applications that need Neural Network computations. The system is fully implemented into a prototyping platform based on Field Programmable Gate Array (FPGA). The SoC consists of an embedded processor core and a reconfigurable hardware accelerator for neural computations. The performance of the SoC is evaluated using a real image processing application, an optical character recognition (OCR) system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.427-430
• /
• 2019

Object detection is applied in various field. Autonomous driving, surveillance, OCR(optical character recognition) and aerial image etc. We will look at the algorithms that are using to object detect. These algorithms are divided into two methods. The one is R-CNN algorithms [2], [5], [6] which based on region proposal. The other is YOLO [7] and SSD [8] which are one stage object detector based on regression/classification.

• Journal of Korea Multimedia Society
• /
• v.18 no.8
• /
• pp.943-949
• /
• 2015

A reader usually spends a lot of time browsing and searching word meaning in a dictionary, internet or smart applications in order to find the unknown words. In this paper, we propose a method to compensate this drawback. The proposed method introduces a vocabulary upon recognizing a word or group of words that was captured by a smart phone camera. Through this proposed method, organizing and editing words that were captured by smart phone, searching the dictionary data using bisection method, listening pronunciation with the use of speech synthesizer, building and editing of vocabulary stored in database are given as the features. A smart phone application for organizing English words was established. The proposed method significantly reduces the organizing time for unknown English words and increases the English learning efficiency.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.439-444
• /
• 2008

본 논문은 한영 혼용 문서에서의 문자 분할을 위한 효율적인 언어 인식기를 고안하였다. 한영 혼용 문서를 스캔한 후, OCR(광학 문자 판독, Optical Character Recognition)을 할 때, 문자 분할의 중요성은 상당히 크다. 인식 없이 문자를 분할하는 external segmentation 방법에서는, 인식할 언어가 한글 혹은 영어인가에 따라 문자 분할 방법이 달라진다. 그러므로, 한영 혼용 이미지를 인식하기 위해서 문자 분할을 하기 전에 언어를 미리 결정해야 한다. 본 논문에서는 문자 분할 방법을 효율적으로 하기 위한 언어 인식기를 제안하고 그 방법을 적용하였다. 그 결과 한영 혼용된 책 이미지에서 94.09%의 문자 분할 성공률을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.810-812
• /
• 2015

문자인식 즉 OCR(Optical Character Recognition)기술은 광학적으로 인식할 수 있는 문자를 컴퓨터가 읽을 수 있도록 하는 기술을 뜻한다. 문자인식의 근간이 되는 방법은 스트링 매칭 기법이 사용되어 왔지만 한글의 경우 자음, 모음, 자음 조합으로 만 가지 유형이 넘고, 더욱이 상용한자와 영어를 섞어 쓰기 때문에 오인식되는 경우가 많다. 본 논문에서는 한글이 수직선, 수평선, 사선과 같이 방향성이 강한 선소들로 구성되어 있다는 점을 이용하여 한글의 인식률을 높이는 방법을 제안하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1807-1822
• /
• 2023

Innovation and rapid increased functionality in user friendly smartphones has encouraged shutterbugs to have picturesque image macros while in work environment or during travel. Formal signboards are placed with marketing objectives and are enriched with text for attracting people. Extracting and recognition of the text from natural images is an emerging research issue and needs consideration. When compared to conventional optical character recognition (OCR), the complex background, implicit noise, lighting, and orientation of these scenic text photos make this problem more difficult. Arabic language text scene extraction and recognition adds a number of complications and difficulties. The method described in this paper uses a two-phase methodology to extract Arabic text and word boundaries awareness from scenic images with varying text orientations. The first stage uses a convolution autoencoder, and the second uses Arabic Character Segmentation (ACS), which is followed by traditional two-layer neural networks for recognition. This study presents the way that how can an Arabic training and synthetic dataset be created for exemplify the superimposed text in different scene images. For this purpose a dataset of size 10K of cropped images has been created in the detection phase wherein Arabic text was found and 127k Arabic character dataset for the recognition phase. The phase-1 labels were generated from an Arabic corpus of quotes and sentences, which consists of 15kquotes and sentences. This study ensures that Arabic Word Awareness Region Detection (AWARD) approach with high flexibility in identifying complex Arabic text scene images, such as texts that are arbitrarily oriented, curved, or deformed, is used to detect these texts. Our research after experimentations shows that the system has a 91.8% word segmentation accuracy and a 94.2% character recognition accuracy. We believe in the future that the researchers will excel in the field of image processing while treating text images to improve or reduce noise by processing scene images in any language by enhancing the functionality of VGG-16 based model using Neural Networks.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.284-287
• /
• 2003

In recent years, most of the researches on pattern recognition are for medical diagnosis or for characters recognition. In fact its applications are very wide. In this paper, the pattern recognition is employed by linguistic translation, i.e. the output of Pattern Recognition is translated into another language. In this paper, it focuses on several fields: (1) System overview-explicate the functions of each part individually; (2) Criteria on the system-discuss the difficulties in each part; (3) System implementation-discuss how to design the approaches for constructing the system. Furthermore, intelligent approaches are considered be use on the system in different parts. They are discussed in the late paper, and also we concentrate on user interface, which can make a serious of processes in order, and easy control-just only pressing a few buttons. It is a new and creative attempt in digital system.