• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.273-280
• /
• 2013

This paper presents novel OCS-LBP (Oriented Center Symmetric Local Binary Patterns) based on orientation of pixel gradient and image retrieval system based on BoF (Bag-of-Feature) and random forest classifier. Feature vectors extracted from training data are clustered into code book and each feature is transformed new BoF feature using code book. BoF features are applied to random forest for training and random forest having N classes is constructed by combining several decision trees. For testing, the same OCS-LBP feature is extracted from a query image and BoF is applied to trained random forest classifier. In contrast to conventional retrieval system, query image selects similar K-nearest neighbor (K-NN) classes after random forest is performed. Then, Top K similar images are retrieved from database images that are only labeled K-NN classes. Compared with other retrieval algorithms, the proposed method shows both fast processing time and improved retrieval performance.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.677-681
• /
• 2006

In this paper, we suggest the GUI Management Tool, named K-Manager, for management and service of science and technology information that stored in distributed retrieval databases. Generally, it must be adapted retrieval database system for web based S&T contents service. But, It is inconvenient contents manager or the system administrator controls information easily, because it does not support the S&T information management process like TOAD, which can use for the relation database, in information retrieval database system. Using K-Manager, content manager can process the S&T content and system manager can manage the databases easily. The proposed tool active controls information effectively which is stored in the distributed retrieval database which guarantee the safety management of the contents stored in database and operate retrieval with efficient performances. Our tool consists of two sub systems, one is content manager, the other is database manager for YESKISTI based on KRISTAL-IRMS.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_1
• /
• pp.947-960
• /
• 2017

Soil moisture plays an important role to affect the Earth's radiative energy balance and water cycle. In general, satellite observations are useful for estimating the soil moisture content. Passive microwave satellites have an advantage of direct sensitivity on surface soil moisture. However, their coarse spatial resolutions (10-36 km) are not suitable for regional-scale hydrological applications. Meanwhile, in-situ ground observations of point-based soil moisture content have the disadvantage of spatially discontinuous information. This paper presents an experimental soil moisture retrieval using Sentinel-1 SAR (Synthetic Aperture Radar) with 10m spatial resolution for cropland in South Korea. We developed a soil moisture retrieval algorithm based on the technique of linear regression and SVR (support vector regression) using the ground observations at five in-situ sites and Sentinel-1 SAR data from April to October in 2015-2017 period. Our results showed the polarization dependency on the different soil sensitivities at backscattered signals, but no polarization dependence on the accuracies. No particular seasonal characteristics of the soil moisture retrieval imply that soil moisture is generally more affected by hydro-meteorology and land surface characteristics than by phenological factors. At the narrower range of incidence angles, the relationship between the backscattered signal and soil moisture content was more distinct because the decreasing surface interference increased the retrieval accuracies under the condition of evenly distributed soil moisture (during the raining period or on the paddy field). We had an overall error estimate of RMSE (root mean square error) of approximately 6.5%. Our soil moisture retrieval algorithm will be improved if the effects of surface roughness, geomorphology, and soil properties would be considered in the future works.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2574-2586
• /
• 1999

Since a SGML document is composed of elements, the primitive unit of information, SGML information retrieval should support retrieval on element as well as document. In addition, SGML index organization should support the partial insertion and deletion of document for the dynamic environment. For this, we propose a SGML index organization suited to structured-based retrieval for dynamic environment. Based on the proposed index organization, we design a SGML index manager to support content-based and structure-based retrieval efficiently. We implement the SGML index manager based on O2 storage system and compare the performance of our SGML index manager with the conventional SGML index manager. According to the performance comparison, it is shown that the proposed index structure achieves better retrieval performance than the conventional K-ary complete tree.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2003.05a
• /
• pp.101-106
• /
• 2003

This paper introduces the basic concept of computational modeling of perception processes for multimedia data. Such processes are modeled as hierarchical inter-and relationships amongst information in physical, physiological, psychological and cognitive layers in perception. Based on our framework, this paper gives the , algorithms for content-based retrieval for multimedia database systems.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.434-445
• /
• 2009

Content-based image retrieval(CBIR) is the retrieval technique which uses the contents of images. However, in contrast to text data, multimedia data are ambiguous and there is a big difference between system's low-level representation and human's high-level concept. So it doesn't always mean that near points in the vector space are similar to user. We call this the semantic-gap problem. Due to this problem, performance of image retrieval is not good. To solve this problem, the relevance feedback(RF) which uses user's feedback information is used. But existing RF doesn't consider user's region-of-interest(ROI), and therefore, irrelevant regions are used in computing new query points. Because the system doesn't know user's ROI, RF is proceeded in the image-level. We propose a new ROI RF method which guides a user to select ROI from relevant images for the retrieval of complex satellite image, and this improves the accuracy of the image retrieval by computing more accurate query points in this paper. Also we propose a pruning technique which improves the accuracy of the image retrieval by using images not selected by the user in this paper. Experiments show the efficiency of the proposed ROI RF and the pruning technique.

• The Journal of Engineering Research
• /
• v.4 no.1
• /
• pp.55-67
• /
• 2002

This paper contains links and facts to a number of projects on "content-based access to image databases" around the world today. The main focus is on what kind of image features are used but also the user interface and the users possibility to interact with the system.

• Journal of the Korean Society for information Management
• /
• v.15 no.3
• /
• pp.73-93
• /
• 1998

Conventional full-text information retrieval system has been proved with high recall ratio and low precision ratio. One of the disadvantages of full-text IR system is that it is not designed to reflect the user's information need. It is due to the fact that full-text IR system has been designed based on physical and logical structure of document without considering the content of document. The purpose of the study is to develop more effective full-text IR system by resolving such disadvantages of conventional system. The study has developed new method of designing full-text IR system by using Content Structure Markup Language(CSML) other than conventioanal SGML.

• Journal of KIISE:Databases
• /
• v.36 no.5
• /
• pp.366-373
• /
• 2009

In this paper, we propose a similarity search algorithm for image databases. One of the central problems regarding content-based image retrieval (CBIR) is the semantic gap between the low-level features computed automatically from images and the human interpretation of image content. Many search algorithms used in CBIR have used the Minkowski metric (or $L_p$-norm) to measure similarity between image pairs. However those functions cannot adequately capture the aspects of the characteristics of the human visual system as well as the nonlinear relationships in contextual information. Our new search algorithm tackles this problem by employing new similarity measures and ranking strategies that reflect the nonlinearity of human perception and contextual information. Our search algorithm yields superior experimental results on a real handwritten digit image database and demonstrates its effectiveness.

• Journal of Broadcast Engineering
• /
• v.2 no.1
• /
• pp.74-83
• /
• 1997

We have proposed a composite feature measure which combines the color and shape features of an image for image retrieval. We improved the performance of retrieval based on the efficient color quantization using the Lloyd-Max quanizer and on the Histogram matrix matching method which considers the spatial correlation of quantized color group. We also supplemented the color information using shape information with the Improved Moment Invarlants. We have tested our technique on Image database consisting of 200 actual trademark images. Our experimental results showed that our approach improved the performance compared to the previous method under the various situations such as rotation images, translation images, noise added images, gamma corrected images and so on. The efficiency of retrieval is found to be very high and experimental results are