• Title/Summary/Keyword: ocr

Search Result 476, Processing Time 0.02 seconds

A Design and Implementation of Generative AI-based Advertising Image Production Service Application

  • Chang Hee Ok;Hyun Sung Lee;Min Soo Jeong;Yu Jin Jeong;Ji An Choi;Young-Bok Cho;Won Joo Lee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.5
    • /
    • pp.31-38
    • /
    • 2024
  • In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that provides a generative AI-based automatic advertising image production service. This application utilizes GPT-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered keywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background images and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Additionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as phone numbers and business hours at the edges of promotional materials. This application offers small business owners who face difficulties in advertising production a simple and cost-effective solution.

Application Design for Food Allergy Management (식품 알레르기 관리에 관한 애플리케이션 설계)

  • Ji-Uk Han;Nam-Bin Kim;Ye-Won Lee;Byeong-Seung Yang;Won-Whoi Huh
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.24 no.2
    • /
    • pp.197-203
    • /
    • 2024
  • Food allergies are common and accidents occur annually. However, many people lack knowledge of the severity of allergies and food ingredients. Allergy-related applications currently on the market have problems such as providing information by relying only on certain certified products, food ingredients, and barcodes. This design plans a customized service application for food allergy patients. In this application, after extracting the text of the image using OCR technology, the food ingredients were read and displayed in large letters. In addition, if the user selects an ingredient that cannot be consumed through filtering technology, the restricted food is quickly and conveniently shown when searching for food ingredients. Finally, when scanning a barcode or searching for a product, food ingredient information is provided through barcode scanning and search engine technology that provides ingredient information of the product. Therefore, the purpose of this paper is to design an app in which users with food allergies can easily check food ingredients and avoid allergic reactions using databases and various information search methods.

Evaluation on Undrained Shear Strength considering Consolidation Characteristics for Busan Clay (부산 점토의 압밀특성과 연계한 비배수전단강도 평가)

  • Kim, Ju-Hyun
    • Journal of the Korean Geosynthetics Society
    • /
    • v.16 no.3
    • /
    • pp.41-49
    • /
    • 2017
  • In this study, a series of laboratory and in-situ tests such as FVTs and CPTUs were carried out to evaluate undrained shear strength related to quasi overconsolidated characteristics in the near-surface clay at Busan new port. Using unconfined compression and field vane test results, correlation between undrained shear strength and effective overburden pressure, that is, equation of $10+0.262{\sigma}^{\prime}v_0$ (kPa) was obtained. From oedometer tests, OCR is around 1.9 at depths lower than 7 m and OCR below this depth is very close to unit. As stated by Hanzawa et al. (1983), a natural clay deposit in the near-surface, even in normally consolidated state, is more and less apparently overconsolidated due to aging effects such as chemical bonding. Based on this concept, it can be inferred that intercept of equation is mobilized due to chemical bonding irrespective of effective overburden pressure and strength incremental ratio in normally consolidated state is 0.262. From CPTU results, same trend was confirmed. The further study should be necessary to judge whether upper clay is under overconsolidated state due to chemical bonding or not based on the depositional environment.

Text Extraction In WWW Images (웹 영상에 포함된 문자 영역의 추출)

  • 김상현;심재창;김중수
    • Proceedings of the IEEK Conference
    • /
    • 2000.06d
    • /
    • pp.15-18
    • /
    • 2000
  • In this paper, we propose a method for text extraction in the Web images. Our approach is based on contrast detecting and pixel component ratio analysis in mouse position. Extracted data with OCR can be used for real time dictionary call or language translation application in Web browser.

  • PDF

세계의 프린터 시장 동향 및 예측

  • Korea Optical Industry Association
    • The Optical Journal
    • /
    • s.110
    • /
    • pp.27-31
    • /
    • 2007
  • 일본전자정보기술산업협회(정보단말기획전문위원회)는 지난 3월 8일 '2006년 정보단말장치에 관한 시장보고서' 를 발표하였다. 조사는 디스플레이, 프린터, 고장자기디스크장치, 광디스크장치, 이미지스캐너, OCR 등을 대상으로 행하여 2006년의 실적과 2010년까지의 예측에 대한 것이다. 본 고에서는 그 중에서 프린터 시장, 특히 잉크젯프린터 관련 내용만 옮겨 기술하겠다.

  • PDF

"행정전산화" 발전을 위한 소고

  • Kim, Suk-Hui
    • 정보화사회
    • /
    • s.119
    • /
    • pp.21-23
    • /
    • 1997
  • 행정전산화란 일반 행정 업무, 예를 들면 각종 인, 허가 민원업무외 복잡한 사무를 기존의 서류 처리 형태에서 전산화하고, 수기고지하던 세외수입금 관리업무를 종합 전산화하여 OCR 처리하는 것, 또는 전자 우편이나 전자결재 같은 전형적인 사무자동화(OA) 업무조차도 업무 과정이 아닌 행정전산화의 법제화된 부문으로 취급하여 활용하는 것 등으로 볼 수 있을 것이다.

  • PDF

삼성 전자의 Smart DLS 국내구축 사례

  • 고홍승
    • Proceedings of the Korea Database Society Conference
    • /
    • 1998.09a
    • /
    • pp.279-292
    • /
    • 1998
  • 4. 특징 및 도입효과 4-1. 구축시스템 특징 $.$다양한 입력자료에 대한 원문 검색 - Image, Video, 탁본, WP 등 ㆍ국내 최초로 개발된 OTRS(OCR-generated Text Retrieval System)시스템 -자료 속의 핵심어 위치를 이미지 상에서 확인 ㆍVR 시스템을 통한 WEB Service $.$ IR 시스템을 통한 색인어 검색 및 조건에 의한 검색(중략)

  • PDF

Pattern Classification Model using LVQ Optimized by Fuzzy Membership Function (퍼지 멤버쉽 함수로 최적화된 LVQ를 이용한 패턴 분류 모델)

  • Kim, Do-Tlyeon;Kang, Min-Kyeong;Cha, Eui-Young
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.8
    • /
    • pp.573-583
    • /
    • 2002
  • Pattern recognition process is made up of the feature extraction in the pre-processing, the pattern clustering by training and the recognition process. This paper presents the F-LVQ (Fuzzy Learning Vector Quantization) pattern classification model which is optimized by the fuzzy membership function for the OCR(Optical Character Recognition) system. We trained 220 numeric patterns of 22 Hangul and English fonts and tested 4840 patterns whose forms are changed variously. As a result of this experiment, it is proved that the proposed model is more effective and robust than other typical LVQ models.

Application of Fault Location Method to Improve Protect-ability for Distributed Generations

  • Jang Sung-Il;Lee Duck-Su;Choi Jung-Hwan;Kang Yong-Cheol;Kang Sang-Hee;Kim Kwang-Ho;Park Yong-Up
    • Journal of Electrical Engineering and Technology
    • /
    • v.1 no.2
    • /
    • pp.137-144
    • /
    • 2006
  • This paper proposes novel protection schemes for grid-connected distributed generation (DG) units using the fault location algorithm. The grid-connected DG would be influenced by abnormal distribution line conditions. Identification of the fault location for the distribution lines at the relaying point of DG helps solve the problems of the protection relays for DG. The proposed scheme first identifies fault locations using currents and voltages measured at DG and source impedance of distribution networks. Then the actual faulted feeder is identified, applying time-current characteristic curves (TCC) of overcurrent relay (OCR). The method considering the fault location and TCC of OCR might improve the performance of the conventional relays for DG. Test results show that the method prevents the superfluous operations of protection devices by discriminating the faulted feeder, whether it is a distribution line where DG is integrated or out of the line emanated from the substation to which the DGs are connected.

Robust Recognition of a Player Name in Golf Videos (골프 동영상에서의 강건한 선수명 인식)

  • Jung, Cheol-Kon;Kim, Joong-Kyu
    • 한국HCI학회:학술대회논문집
    • /
    • 2008.02a
    • /
    • pp.659-662
    • /
    • 2008
  • In sports videos, text provides valuable information about the game such as scores and information about the players. This paper proposed a robust recognition method of player name in golf videos. In golf, most of users want to search the scenes which contain the play shots of favorite players. We use text information in golf videos for robust extraction of player information, By using OCR, we have obtained the text information, and then recognized the player information from player name DB. We can search the scenes of favorite players by using this player information. By conducting experiments on several golf videos, we demonstrate that our method achieves impressive performance with respect to the robustness.

  • PDF