• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.473-482
• /
• 2008

In this paper we propose an expert system for content-based image retrieval with object database. The proposed system finds keyword by using knowledge-base and feature of extracted object, and retrieves image by using keyword based image retrieval method. The system can decrease error of image retrieval and save running time. The system also checks whether similar objects exist or not. If not, user can store information of object in object database. Proposed system is flexible and extensible, enabling experts to incrementally add more knowledge and information. Experimental results show that the proposed system is more effective than existing content-based image retrieval method in running time and precision.

• Journal of the Semiconductor & Display Technology
• /
• v.12 no.4
• /
• pp.33-38
• /
• 2013

Image retrieval is one of the most exciting and fastest growing research fields in the area of multimedia technology. As the amount of digital contents continues to grow users are experiencing increasing difficulty in finding specific images in their image libraries. This paper proposes an efficient image descriptor which uses a local color and texture in the non-overlapped block images. To evaluate the performance of the proposed method, we assessed the retrieval efficiency in terms of ANMRR with common image dataset. The experimental trials revealed that the proposed algorithm exhibited a significant improvement in ANMRR, compared to Dominant Color Descriptor and Edge Histogram Descriptor.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.403-408
• /
• 2018

Generally, a large data set is required for learning of deep learning. However, since it is not easy to create large data sets, there are a lot of techniques that make small data sets larger through data expansion such as rotation, flipping, and filtering. However, these simple techniques have limitation on extendibility because they are difficult to escape from the features already possessed. In order to solve this problem, we propose a method to acquire new image data by using existing data. This is done by retrieving and acquiring similar images using existing image data as a query of the content-based image retrieval (CBIR). Finally, we compare the performance of the base model with the model using CBIR.

• 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 Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.75-82
• /
• 2010

The paper proposed CBIRS/EFI with contents based search technique using edge feature information of the object from image information of the object which is uncertain. In order to search specially efficiently case of partial image information of the object, we used the search technique which extracts outline information and color information in feature information of object. In order to experiment this, we extracted side edge feature information of the vehicle for feature information of the object after capture the car image of the underground garage. This is the system which applies a contents base search by the result which analyzes the image which extracts a feature, an original image to search and a last similar measurement result. This system compared in FE-CBIRS systems which are an existing feature extraction contents base image retrieval system and the function which improves the accuracy and an effectiveness of search rate was complemented. The performance appraisal of CBIRS/EFI systems applied edge extraction feature information and color information of the cars. And we compared a color feature search time, a shape characteristic search time and a search rate from the process which searches area feature information. We extracted the case 91.84% of car edge feature extraction rate. And a average search time of CBIRS/EFI is showing a difference of average 0.4-0.9 seconds than FE-CBIRS from vehicle. color search time, shape characteristic search time and similar search time. So, it was proven with the fact that is excellent.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.581-586
• /
• 2004

In this paper, we proposed a content-based image retrieval using a color feature for central region and its optimized comparing bin method. Human's visual characteristic is influenced by existent of central object. So we supposed that object is centrally located in image and then we extract color feature at central region. When the background of image is simple, the retrieval result can be bad affected by major color of background. Our method overcome this drawback as a result of the human visual characteristic. After we transform Image into HSV color space, we extract color feature from the quantized image with 16 level. The experimental results showed that the method using the eight high rank bin is better than using the 16 bin The case which extracts the feature with image's central region was superior compare with the case which extracts the feature with the whole image about 5%.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.280.1-285
• /
• 1998

The earth's environmental problems have attracted serious attention worldwide. Various kinds of environmental data, such as remote sensing data, have become available for examining. Although this data is crucial to understanding such problems, there has become an over-abundance in variety of size, format, and filetype which makes it difficult for researchers to handle. We feel that earth environmental researchers should not be burdened by such cumbersome tasks. Therefore, we are developing a digital library for earth environmental information and a VRML based data visualization system for it. Even now, content-based image retrieval systems have many problems attributed to the degree of difficulty in implementing them. Thus, we are trying to visualize this data so that researchers can utilize it more efficiently, effectively, and easily. A great advantage for VRML users is that people can see environmental data from any perspective above the earth and with any resolution easily. Also by using MPEG-movie, users can observe the changes of data drawn from time series files.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.1 s.33
• /
• pp.93-100
• /
• 2005

This study is to desist and implement an efficient microbial medical image retrieval system based on knowledge and content of them which can make use of more accurate decision on colony as doll as efficient education for new techicians. For this. re first address overall inference to set up flexible search path using rule-base in order U redure time required original microbial identification by searching the fastest path of microbial identification phase based on heuristics knowledge. Next, we propose a color ffature gfraction mtU, which is able to extract color feature vectors of visual contents from a inn microbial image based on especially bacteria image using HSV color model. In addition, for better retrieval performance based on large microbial databases, we present an integrated indexing technique that combines with B+-tree for indexing simple attributes, inverted file structure for text medical keywords list, and scan-based filtering method for high dimensional color feature vectors. Finally. the implemented system shows the possibility to manage and retrieve the complex microbial images using knowledge and visual contents itself effectively. We expect to decrease rapidly Loaming time for elementary technicians by tell organizing knowledge of clinical fields through proposed system.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.18-25
• /
• 2011

Salient object attracts more and more attention from researchers due to its important role in many fields of multimedia processing like tracking, segmentation, adaptive compression, and content-base image retrieval. Usually, a saliency map is binarized into black and white map, which is considered as the binary mask of the salient object in the image. Still, the threshold is heuristically chosen or parametrically controlled. This paper suggests using the global optimal threshold to perform saliency map thresholding. This work also considers the usage of multi-level optimal thresholds and the local adaptive thresholds in the experiments. These experimental results show that using global optimal threshold method is better than parametric controlled or local adaptive threshold method.