• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.313-315
• /
• 2024

본 논문에서는 이미지 검색기를 통한 랜드마크 인식 방법을 제안한다. 특정 랜드마크 데이터세트에서 라벨링을 하지 않은 비지도 학습을 통해서 이미지에서 랜드마크의 클래스 분류를 위한 특징을 추출한다. 학습된 모델을 랜드마크 데이터세트인 Paris6k 데이터세트와 Oxford5k 데이터세트에 적용하여 랜드마크 인식 정확도를 확인하였다. 성능과 속도를 강화하기 위해 이미지 특징 추출 모델로 ResNet 대신에 YOLO에서 사용된 CSPDarknet-53을 사용하여 모델의 크기를 줄이고 랜드마크 인식 정확도를 높였다. 그리고 모델로부터 추출된 특징의 수를 줄여 이미지 검색 시 소요되는 시간을 감소시켰다. 학습된 모델로 rOxford5k 데이터 세트에 적용 시 mAP 80.37, rParis6k에서 mAP 89.07을 얻었다.

• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.26-33
• /
• 2018

In this paper, we propose an image retrieval algorithm for real-time processing and design it as hardware. The proposed method is based on the classification of BoWs(Bag of Words) algorithm and proposes an image search algorithm using bit stream. K-fold cross validation is used for the verification of the algorithm. Data is classified into seven classes, each class has seven images and a total of 49 images are tested. The test has two kinds of accuracy measurement and speed measurement. The accuracy of the image classification was 86.2% for the BoWs algorithm and 83.7% the proposed hardware-accelerated software implementation algorithm, and the BoWs algorithm was 2.5% higher. The image retrieval processing speed of BoWs is 7.89s and our algorithm is 1.55s. Our algorithm is 5.09 times faster than BoWs algorithm. The algorithm is largely divided into software and hardware parts. In the software structure, C-language is used. The Scale Invariant Feature Transform algorithm is used to extract feature points that are invariant to size and rotation from the image. Bit streams are generated from the extracted feature point. In the hardware architecture, the proposed image retrieval algorithm is written in Verilog HDL and designed and verified by FPGA and Design Compiler. The generated bit streams are stored, the clustering step is performed, and a searcher image databases or an input image databases are generated and matched. Using the proposed algorithm, we can improve convenience and satisfaction of the user in terms of speed if we search using database matching method which represents each object.

• Journal of the Korean Society for information Management
• /
• v.28 no.2
• /
• pp.135-158
• /
• 2011

The ability of the searcher to express their information problem to an information retrieval system is fundamental to the retrieval process. Query by visual example is the principal query paradigm for expressing queries in a content-based image retrieval environment yet there is little empirical evidence to support its efficacy in facilitating query formulation. The aim of this research was to investigate the usability of the query by colour method in supporting a range of information problems in order to contribute to the gap in knowledge regarding the relationship between searchers' information problems and the query methods required to support efficient and effective visual query formulation. The results strongly suggest that the query method does not support visual query formulation and that there is a significant mismatch between the searchers information problems and the expressive power of the retrieval paradigm.

• Journal of Information Management
• /
• v.42 no.3
• /
• pp.71-94
• /
• 2011

Query by visual example is the principal query paradigm for expressing queries in a content-based image retrieval environment. Query by image and query by sketch have long been purported as being viable methods of query formulation yet there is little empirical evidence to support their efficacy in facilitating query formulation. The ability of the searcher to express their information problem to an information retrieval system is fundamental to the retrieval process. The aim of this research was to investigate the query by image and query by sketch methods in supporting a range of information problems through a usability experiment in order to contribute to the gap in knowledge regarding the relationship between searchers' information problems and the query methods required to support efficient and effective visual query formulation. The results of the experiment suggest that query by image is a viable approach to visual query formulation. In contrast, the results strongly suggest that there is a significant mismatch between the searchers information problems and the expressive power of the query by sketch paradigm in supporting visual query formulation. The results of a usability experiment focusing on efficiency (time), effectiveness (errors) and user satisfaction show that there was a significant difference, p<0.001, between the two query methods on all three measures: time (Z=-3.597, p<0.001), errors (Z=-3.317, p<0.001), and satisfaction (Z=-10.223, p<0.001). The results also show that there was a significant difference in participants perceived usefulness of the query tools Z=-4.672, p<0.001.

• Journal of the Korean Society of Costume
• /
• v.34
• /
• pp.91-107
• /
• 1997

For the purpose of this study is the re-searcher investigated the concept and background of kitsch and the character of Kitsch in the paintings with focus on the Surrealism and Pop Art. In this study it was focused that how the shapes and materials was expressed in the modern fashion. Surrealism in paintings is lead thoughts and art movement to humanism of be-having man and pursuit of mental sub-stance of human beings expressing un-conscious word and transforming image in new way by the methods Automatism and Depaysements. Pop Art in paintings is used to objects common and cheap in the popular con-sumer's society. That is to say Pop Art sublimated con-sumptional culture of mass as art. And this phenomenon is appeared in the modern fashion which have influencedon the shapes and materials in design. Kitsch's character was researched in terms of shapes materials in the modern fashion with focus on the Surrealism and Pop Art and their aspect are summarized as follows: 1. In he aspect of shapes it appears that the shapes in the modern fashion is that of play through the method distor-tion or modification of dress. It was un-derstood that the cause of the dreaming and fantasy in the childhood. In the aspect of materials it apepears that the materials in the modern fashion is that of exagerated-decoration through using of object which is various asses-sories flower doll etc. 2. In the aspect of shapes it appears that the shapes in the modern fashion is that of disharmoney disorder and unsuit-ableness. The major cause of that is be-cause of Antistandard fashion I the aspect of materials it appears that the materials in the modern fashion is that of sarcasm pleasantness. It was reviwed that the major cause of the wit or humor comes from the image of the masses makes use of such as plastic fun-ny picture can coin etc.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.465-467
• /
• 2022

Mobile phones have become an essential item nowadays since it provides access to online platform and service fast and easy. Coming to these platforms such as Social Network Service (SNS) for shopping have been a go-to option for many people. However, searching for a specific fashion item in the picture is challenging, where users need to try multiple searches by combining appropriate search keywords. To tackle this problem, we propose a system that could provide immediate access to websites related to fashion items. In the framework, we also propose a deep learning model for an automatic analysis of image contexts using instance segmentation. We use transfer learning by utilizing Deep fashion 2 to maximize our model accuracy. After segmenting all the fashion item objects in the image, the related search information is retrieved when the object is clicked. Furthermore, we successfully deploy our system so that it could be assessable using any web browser. We prove that deep learning could be a promising tool not only for scientific purpose but also applicable to commercial shopping.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.473-480
• /
• 2019

Recently, local game companies have been increasingly producing PC-based game that were popular with users among the existing commercialized games into mobile games through remakes. In this paper, we studied how console-based game influenced mobile augmented reality game . Through this process, we extracted five characteristics of mobile augmented reality, then interpreted and classified the meaning of this. Based on released in 2016, the scope of research is limited to console and mobile games previously released. According to the analysis, showed 50 characteristics and borrowed 78% from its existing Pokemon, 22% from its new production, and contained 24% reality. We also found that the Pokemon game series , and the exotic series had much influence on production. Based on this research data, we hope that augmented reality games for mobile will be made more active using existing game contents. It is also hope that such activities will lead to the growth of the home and abroad game industry.