• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.133-138
• /
• 2012

Queries entered in a search box are the results of users' activities to actively seek information. Therefore, search logs are important data which represent users' information needs. The purpose of this study is to examine if there is a relationship between the results of queries automatically classified and the categories of documents accessed. Search sessions were identified in 2009 NDSL(National Discovery for Science Leaders) log dataset of KISTI (Korea Institute of Science and Technology Information). Queries and items used were extracted by session. The queries were processed using an automatic classifier. The identified queries were then compared with the subject categories of items used. As a result, it was found that the average similarity was 58.8% for the automatic classification of the top 100 queries. Interestingly, this result is a numerical value lower than 76.8%, the result of search evaluated by experts. The reason for this difference explains that the terms used as queries are newly emerging as those of concern in other fields of research.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.20-27
• /
• 2003

In this paper, we implemented a content-based image retrieval system that user can choose a wanted query region of object and retrieve similar object from image database. Query image is induced to wavelet transformation after divided into hue components and gray components that hue features is extracted through color autocorrelogram and dispersion in hue components. Texture feature is extracted through autocorrelogram and GLCM in gray components also. Using features of two components, retrieval is processed to compare each similarity with database image. In here, weight value is applied to each similarity value. We make up for each defect by deriving features from two components beside one that elevations of recall and precision are verified in experiment results. Moreover, retrieval efficiency is improved by weight value. And various features of database images are indexed automatically in feature library that make possible to rapid image retrieval.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.2
• /
• pp.1-8
• /
• 2003

This paper proposes an object-based image retrieval technique based on the dominant color pair information. Most of existing methods for content based retrieval extract the features from an image as a whole, instead of an object of interest. As a result, the retrieval performance tends to degrade due to the background colors. This paper proposes an object based retrieval scheme, in which an object of interest is used as a query and the similarity is measured on candidate regions of DB images where the object may exist. From the segmented image, the dominant color pair information between adjacent regions is used for selecting candidate regions. The similarity between the query image and DB image is measured by using the color correlogram technique. The dominant color pair information is robust against translation, rotation, and scaling. Experimental results show that the performance of the proposed method has been improved by reducing the errors caused by background colors.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.92-103
• /
• 2010

In this paper, a method for the recognition of dynamic hand gestures in various backgrounds using Dynamic Space Time Warping(DSTW) algorithm is proposed. The existing method using DSTW algorithm compares multiple candidate hand regions detected from every frame of the query sequence with the model sequences in terms of the time. However the existing method can not exactly recognize the models because a false path can be generated from the candidates including not-hand regions such as background, elbow, and so on. In order to solve this problem, in this paper, we use the invariant moments extracted from the candidate regions of hand and compare the similarity of invariant moments among candidate regions. The similarity is utilized as a weight and the corresponding value is applied to the matching cost between the model sequence and the query sequence. Experimental results have shown that the proposed method can recognize the dynamic hand gestures in the various backgrounds. Moreover, the recognition rate has been improved by 13%, compared with the existing method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.171-180
• /
• 2003

A content-based image retrieval(CBIR) system builds the image database using low-level features such as color, shape and texture and provides similar images that user wants to retrieve when the retrieval request occurs. What the user is interest in is a response time in consideration of the building time to build the index database and the response time to obtain the retrieval results from the query image. In a content-based image retrieval system, the similarity computing time comparing a query with images in database takes the most time in whole response time. In this paper, we propose the two-phase search method with the clustering technique of feature vector in order to minimize the similarity computing time. Experimental results show that this two-phase search method is 2-times faster than the conventional full-search method using original features of ail images in image database, while maintaining the same retrieval relevance as the conventional full-search method. And the proposed method is more effective as the number of images increases.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.5
• /
• pp.628-638
• /
• 1999

In this paper, we presents a method of retrieving 24 bpp RGB images based on color-spatial features. For each image, it is subdivided into regions by using similarity of color after converting RGB color space to CIE L*u*v* color space that is perceptually uniform. Our segmentation algorithm constrains the size of region because a small region is discardable and a large region is difficult to extract spatial feature. For each region, averaging color and center of region are extracted to construct color-spatial features. During the image retrieval process, the color and spatial features of query are compared with those of the database images using our similarity measure to determine the set of candidate images to be retrieved. We implement a content-based color image retrieval system using the proposed method. The system is able to retrieve images by user graphic or example image query. Experimental results show that Recall/Precision is 0.80/0.84.

• Journal of KIISE:Databases
• /
• v.36 no.1
• /
• pp.22-29
• /
• 2009

The World Wide Web has emerged as largest media which provides even a single user to market their products and publish desired information; on the other hand the user can access what kind of information abundantly enough as well. As a result web holds large amount of related information distributed over multiple web pages. The current search engines search for all the entered keywords in a single webpage and rank the resulting set of web pages as an answer to the user query. But this approach fails to retrieve the pair of web pages which contains more relevant information for users search. We introduce a new search paradigm which gives different weights to the query keywords according to their order of appearance. We propose a new arc weight measure that assigns more relevance to the pair of web pages with alternate keywords present so that the pair of web pages which contains related but distributed information can be presented to the user. Our measure proved to be effective on the similarity search in which the experimentation represented the e~arc ranking measure outperforming the conventional ones.

• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.283-303
• /
• 2007

Recently, the study of efficient way to store and retrieve enormous music data is becoming the one of important issues in the multimedia database. Most general method of MIR (Music Information Retrieval) includes a text-based approach using text information to search a desired music. However, if users did not remember the keyword about the music, it can not give them correct answers. Moreover, since these types of systems are implemented only for exact matching between the query and music data, it can not mine any information on similar music data. Thus, these systems are inappropriate to achieve similarity matching of music data. In order to solve the problem, we propose an Efficient Query-By-Humming System (EQBHS) with a content-based indexing method that efficiently retrieve and store music when a user inquires with his incorrect humming. For the purpose of accelerating query processing in EQBHS, we design indices for significant melodies, which are 1) frequent melodies occurring many times in a single music, on the assumption that users are to hum what they can easily remember and 2) melodies partitioned by rests. In addition, we propose an error tolerated mapping method from a note to a character to make searching efficient, and the frequent melody extraction algorithm. We verified the assumption for frequent melodies by making up questions and compared the performance of the proposed EQBHS with N-gram by executing various experiments with a number of music data.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1247-1253
• /
• 2015

An inverted index structure is widely used for efficient string similarity search. One of the main requirements of similarity search is a fast response time; to this end, most techniques use an in-memory index structure. Since the size of an inverted index structure usually very large, however, it is not practical to assume that an index structure will fit into the main memory. To alleviate this problem, we propose a novel technique that reduces the size of an inverted index. In order to reduce the size of an index, the proposed technique rearranges data strings so that the data strings containing the same q-grams can be placed close to one other. Then, the technique encodes those multiple strings into a range. Through an experimental study using real data sets, we show that our technique significantly reduces the size of an inverted index without sacrificing query processing time.