• Journal of the Korean Society for information Management
• /
• v.1 no.1
• /
• pp.78-99
• /
• 1984

In this paper, the automatic keyword classification which is one of the automatic construction methods of retrieval thesaurus is experimented to the Korean language on the basis that the use of retrieval thesaurus would increase the efficiency of information retrieval in the natural language retrieval system searching machine-readable data base. Furthermore, this paper proposes the application methods. In this experiment, the automatic keyword classification was based on the assumption that semantic relationships between terms can be found out by the statistical patterns of terms occurring in a text.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.2
• /
• pp.9-15
• /
• 2000

In this paper, we proposed a content-based image retrieval method using color and object's complexity for indexing of image database. Generally, the retrieval methods using color feature can not sufficiently include the spatial information in the image. So they are reduced retrieval efficiency. Then we combined object's complexity which extracted from chain code and the conventional color feature. As a result, experiments shooed that the proposed method which considers the shape feature improved performance in conducting content-based search.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2407-2424
• /
• 2022

Recently, Transformer has made great progress in video retrieval tasks due to its high representation capability. For the structure of a Transformer, the cascaded self-attention modules are capable of capturing long-distance feature dependencies. However, the local feature details are likely to have deteriorated. In addition, increasing the depth of the structure is likely to produce learning bias in the learned features. In this paper, an improved Transformer structure named TransDCS (Transformer with Dynamic Convolution and Shortcut) is proposed. A Multi-head Conv-Self-Attention module is introduced to model the local dependencies and improve the efficiency of local features extraction. Meanwhile, the augmented shortcuts module based on a dual identity matrix is applied to enhance the conduction of input features, and mitigate the learning bias. The proposed model is tested on MSRVTT, LSMDC and Activity-Net benchmarks, and it surpasses all previous solutions for the video-text retrieval task. For example, on the LSMDC benchmark, a gain of about 2.3% MdR and 6.1% MnR is obtained over recently proposed multimodal-based methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.39-44
• /
• 2006

In this paper, search result list synthesis method is proposed using borda count method for still image retrieval based on MPEG-7 descriptors. MPEG-7 standardizes descriptors that extract feature information from media data. In many cases, using a single descriptor lacks of correctness, it is suggested to use multiple descriptors to enhance retrieval efficiency. In this paper, retrieval efficiency enhancement is achieved by combining multiple search results which are from each descriptor. In combining search result, newly calculated borda count method is proposed. Comparing current frequency compensated calculation, rank considered frequency compensation is used to score animage in database. This combining method is considered in Content based image retrieval system with relevance feedback algorithm which uses high level information from system user. In each relevance iteration step, adoptive borda count method is used to calculate score of images.

• Journal of the Korean Society for Library and Information Science
• /
• v.46 no.2
• /
• pp.133-156
• /
• 2012

This study aims to develop and evaluate the authority data-based academic retrieval system that may provide search tools and additional information for search of academic papers with users. To evaluate the usability of authority data-based academic paper search system, this work studied 60 subjects who had experienced the academic paper service to measure their satisfaction on both search efficiency and system usability and additionally analyzed whether the difference between search efficiency and system availability is significant in the experimental search system among user groups. As a result, the authority data-based academic paper search system was analyzed to show a higher search efficiency and user satisfaction than the ordinary system.

• Clinical and Experimental Reproductive Medicine
• /
• v.44 no.1
• /
• pp.22-27
• /
• 2017

Objective: Azoospermia owing to testicular disorders is the most severe manifestation of male infertility. The main concern for patients with nonobstructive azoospermia (NOA) is the probability of successful sperm retrieval following testicular sperm extraction (TESE). Therefore, the goal of this study was to determine predictive factors correlated with sperm retrieval. Methods: We assessed the testicular histopathological patterns, the choice of TESE surgical procedure, hormone levels, and chromosomal abnormalities in patients with NOA (n=170). The histopathology specimens were analyzed based on the histopathological patterns of hypospermatogenesis, maturation arrest, and Sertoli cell-only syndrome. Results: The mean rate of sperm retrieval was 48.8%. The rate of sperm retrieval was significantly higher in the hypospermatogenesis group than in the other groups (p<0.001). There was a positive correlation between micro-TESE (vs. conventional TESE) and the sperm retrieval rate (odds ratio, 8.077; p<0.01). A logistic regression model demonstrated that high levels of follicle-stimulating hormone (FSH) and small testicular volume were significantly associated with lower chances of successful sperm retrieval. Conclusion: Some parameters, including testicular histopathology patterns, FSH levels, testicular volume, and method of TESE surgery, may be able to predict the chances of obtaining spermatozoa in patients with NOA. However, despite the efficiency of some predictive models, the hope of retrieving any functioning spermatozoa may be sufficient to disregard predictive factors of the success of intracytoplasmic sperm injection in these patients.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.47-54
• /
• 1998

With the increasing popularity of the use of large-volume image database in various application, it becomes imperative to build an efficient and fast retrieval system to browse through the entire database. We present a new method for a content-based image retrieval by using a variable block size and block matching algorithm. Proposed approach is reflecting image features that exploit visual cues such as color and space allocation of image and is getting the fast retrieval time by automatical convergence of retrieval times which adapt to wanting similarity value. We have implemented this technique and tested it for a database of approximately 150 images. The test shows that a 1.9 times fast retrieval time compare to J & V algorithm at the image retrieval efficiency 0.65 and that a 1.83 times fast retrieval time compare to predefined fixed block size.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.579-586
• /
• 2002

The edge descriptor proposed by MPEG-7 standard is a representative approach for the contents-based image retrieval using the edge information. In the edge descriptor, the edge information is the edge histogram derived from a gray-level value image. This paper proposes a new method which extracts color edge information from color images and a new approach for the contents-based image retrieval based on the color edge histogram. The poposed method and technique are applied to image retrieval of the e-catalogue. For the evaluation, the results of image retrieval using the proposed approach are compared with those of image retrieval using the edge descriptor by MPEG-7 and the statistics shows the efficiency of the proposed method. The proposed color edge model is made by combining the R,G,B channel components vectorially and by characterizing the vector norm of the edge map. The color edge histogram using the direction of the color edge model is subsequently used for the contents-based image retrieval.

• Journal of Advanced Navigation Technology
• /
• v.12 no.6
• /
• pp.691-698
• /
• 2008

We present a novel method for face detection and recognition methods applicable to video retrieval. The person matching efficiency largely depends on how robustly faces are detected in the video frames. Face regions are detected in video frames using viola-jones features boosted with the Adaboost algorithm After face detection, PCA (Principal Component Analysis) follows illumination compensation to extract features that are classified by SVM (Support Vector Machine) for person identification. Experimental result shows that the matching efficiency of the ensembled architecture is quit satisfactory.

• Asian-Australasian Journal of Animal Sciences
• /
• v.21 no.3
• /
• pp.353-357
• /
• 2008

A series of studies has been conducted to establish a base infrastructure for an ovarian follicle culture system in the porcine and this study was designed to develop an effective retrieval protocol of preantral follicles. Five different methods using collagenase type I (A) or IV (B, C1, C2 and C3), which employed different treatment durations and/or conditions, were employed and sliced ovarian tissue of prepubertal gilts was provided for the retrieval. A significant increase in total number of follicles retrieved was detected when collagenase IV (methods B or C) was used. In total, more ovarian follicles were retrieved by method B undertaking agitation and method C2 without the agitation than method C1 and C3, while the number of preantral follicles collected was the largest in method B. Neither incubation in 5% $CO_2$ in air atmosphere instead of the agitation nor increased duration of enzymatic treatment up to 120 minutes improved the efficiency of follicle retrieval. There were no differences in the number of follicles retrieved from intact ovaries and from used ovaries for oocyte collection. These results demonstrate the collagenase IV treatment with agitation is effective for retrieving porcine preantral follicles from the ovaries.