• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.602-613
• /
• 2023

High-quality image datasets are in high demand for various applications. With many online sources providing manually collected datasets, a persisting challenge is to fully automate the dataset collection process. In this study, we surveyed an automatic image dataset generation field through analyzing a collection of existing studies. Moreover, we examined fields that are closely related to automated dataset generation, such as query expansion, web scraping, and dataset quality. We assess how both noise and regional search engine differences can be addressed using an automated search query expansion focused on hypernyms, allowing for user-specific manual query expansion. Combining these aspects provides an outline of how a modern web scraping application can produce large-scale image datasets.

• Fashion & Textile Research Journal
• /
• v.17 no.5
• /
• pp.731-740
• /
• 2015

Mobile (smartphone) search engine marketing is increasingly important. Accordingly, the development of visual apparel search technology to obtain easier and faster access to visual information in the apparel field is urgently needed. This study helps establish a proper classifying system for an apparel search after an analysis of search techniques for apparel search applications and existing domestic and overseas apparel sites. An annotation technique is developed in accordance with visual attributes and apparel categories based on collected data obtained by web crawling and apparel images collecting. The categorical composition of apparel is divided into wearing, image and style. The web evaluation site traces the correlations of the apparel category and apparel factors as dependent upon visual attributes. An appraisal team of 10 individuals evaluated 2860 pieces of merchandise images. Data analysis consisted of correlations between apparel, sleeve length and apparel category (based on an average analysis), and correlation between fastener and apparel category (based on an average analysis). The study results can be considered as an epoch-making mobile apparel search system that can contribute to enhancing consumer convenience since it enables an effective search of type, price, distributor, and apparel image by a mobile photographing of the wearing state.

• Journal of the Korean Society for information Management
• /
• v.27 no.2
• /
• pp.37-60
• /
• 2010

The purpose of this study is to investigate image search query reformulation patterns in relation to image attribute categories. A total of 592 sessions and 2,445 queries from the Excite Web search engine log data were analyzed by utilizing Batley's visual information types and two facets and seven sub-facets of query reformulation patterns. The results of this study are organized with two folds: query reformulation and categorical transition. As the most dominant categories of queries are specific and general/nameable, this tendency stays over various search stages. From the perspective of reformulation patterns, while the Parallel movement is the most dominant, there are slight differences depending on initial or preceding query categories. In examining categorical transitions, it was found that 60-80% of search queries were reformulated within the same categories of image attributes. These findings may be applied to practice and implementation of image retrieval systems in terms of assisting users' query term selection and effective thesauri development.

• Proceedings of the CALSEC Conference
• /
• 1999.07b
• /
• pp.575-586
• /
• 1999

The advent of the Internet and the enormous increase in volume of electronically stored information (SGML, Image, Sound, etc.) has led to substantial work on IR(Information Retrieval). To service on the WWW, construction and retrieval technology of SGML, which is the fundamental standard data format for CALS/EC, is needed specially. Due to such a change, it becomes essential to change the existing paradigm of conventional information retrieval systems and to adopt new Internet service system with search engine, SGML browser and advanced Internet technology on WWW. KIPRIS(Korea Industrial Property Rights Information Service), which is the specialized and integrated Internet service systems in the field of industrial property rights information service, is trying to be a guide for our country to establish its technological competitiveness with providing the online service of high quality. The objective of the paper identifies features and technologies of KIPRIS IR(Information Retrieval) system based on WWW as follows. First, it describes the development background and process of KIPRIS. Second, it presents a fundamental technology that consists of IR(Information Retrieval) concept, BRS(Bibliographical Retrieval System) search engine, SGML implementation technologies and the Internet/WWW technologies. Third, it provides information about system configuration, architecture, and the features and characteristics of KIPRIS. Finally, the implemented KIPRIS system is introduced.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.12
• /
• pp.1601-1608
• /
• 2001

Digital library is the most important database system that needs information retrieval engine for natural language documents and multimedia data. This paper describes the experimental results of information retrieval engine and browser based on natural language processing. It includes lexical analysis, syntax processing, stemming, and keyword indexing for the natural language text. With the experimental database ‘Earth and Space Science’ that has lots of images and titles and their descriptive text in natural language, text-based search engine was tested. Combined with content-based image search engine, it is expected to be a multimedia information retrieval system in digital library

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.493-506
• /
• 2018

This paper proposes the OOPP(Optimized Online Portfolio Platform) design for the job seekers to search for the job competency necessary for employment and to write and manage portfolio online efficiently. The OOPP consists of three modules. First, JDCM(Job Data Collection Module) stores the help-wanted advertisements of job information sites in a spreadsheet. Second, CSM(Competency Statistical Model) classifies core competencies for each job by text-mining the collected help-wanted ads. Third, OBBM(Optimize Browser Behavior Module) makes users to look up data rapidly by improving the processing speed of a browser. In addition, The OBBM consists of the PSES(Parallel Search Engine Sub-Module) optimizing the computation of a Search Engine and the OILS(Optimized Image Loading Sub-Module) optimizing the loading of image text, etc. The performance analysis of the CSM shows that there is little difference in accuracy between the CSM and the actual advertisement because its data accuracy is 99.4~100%. If Browser optimization is done by using the OBBM, working time is reduced by about 68.37%. Therefore, the OOPP makes users look up the analyzed result in the web page rapidly by analyzing the help-wanted ads. of job information sites accurately.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2002.11a
• /
• pp.412-416
• /
• 2002

멀티미디어 검색 시스템들은 아직까지 내용 기발에 의한 검색기술이 실용적으로 쓰일 만큼 높은 성능을 보이고 있지 않기 때문에 텍스트에 의한 검색만을 지원하고 있는 실정이다. HTML 문서에 나타나는 텍스트 중 이미지 아래에 붙은 표제나 이미지 링크에 붙어 있는 텍스트를 골라내어 이미지의 색인 정보로 이용하여 텍스트를 추출하는 기법을 제안하였다. 텍스트를 추출하기 위해 N-Gram 색인 방법을 사용하였으며 한편 검색 효율을 높이기 위해서 질의 의도가 큰 단어에 가중치를 부여하였다.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.11a
• /
• pp.412-416
• /
• 2002

멀티미디어 검색 시스템들은 아직까지 내용 기반에 의한 검색기술이 실용적으로 쓰일 만큼 높은 성능을 보이고 있지 않기 때문에 텍스트에 의한 검색만을 지원하고 있는 실정이다. HTML 문서에 나타나는 텍스트 중 이미지 아래에 붙은 표제나 이미지 링크에 붙어 있는 텍스트를 골라내어 이미지의 색인 정보로 이용하여 텍스트를 추출하는 기법을 제안하였다. 텍스트를 추출하기 위해 N-Gram 색인 방법을 사용하였으며 한편 검색 효율을 높이기 위해서 질의 의도가 큰 단어에 가중치를 부여하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.51-53
• /
• 1999

기존의 웹 이미지 검색 엔진은 웹 이미지를 검색할 때 웹 이미지의 특징과, 웹 이미지를 포함한 HTML 문서의 텍스트를 이용한다. 그러나, 텍스트는 문맥에 따라 의미가 달라질 수 있으므로, 검색 대상을 미리 분류하면 검색 효율을 높일 수 있다. 본 논문은 웹 문서의 텍스트에서 이미지와 관련이 있는 이미지 설명 텍스트를 자동으로 추출하고, 검색 효율을 높이기 위하여 웹 이미지를 자동으로 분류하는 지능적 웹 이미지 검색 엔진을 제안한다. 지능적 웹 이미지 검색 엔진은 분류와 용어, 용어와 용어 사이의 연관도를 이용하여 분류의 정확도를 높인다.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.