• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.451-454
• /
• 2003

A new query method, called query by visual keys, is proposed to aim easy operation and efficient region-based image retrieval (RBIR). Visual keys are constructed from representative regions/subimages in a given image database, and the database is indexed with visual keys. A system on PC is presented, where text retrieval techniques are applied to the image retrieval with visual keys. Experimental results show that one retrieval is done within 4ms and that the proposed system achieves the comparable retrieval precision (with user-friendly operation and low computational cost) to conventional region based image retrieval systems

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.211-214
• /
• 2000

In this paper, we propose a regular-texture image retrieval approach relating In curvature. Maximum curvature and minimum curvature are computed from the query and each regular-texture image in the database. Seven features are computed from curvature characterizing statistical properties of the corresponding image. Each regular-texture image in the database is then represented as the seven CM (curvature measurement)-features. Query comparison and matching can be done using the corresponding CM-features. Experimental results on Brodatz texture show that the proposed approach is effective.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.455-461
• /
• 2002

Object-based image retrieval method is addressed. A new image segmentation algorithm and image comparing method between segmented objects are proposed. For image segmentation, color and texture features are extracted from each pixel in the image. These features we used as inputs into VQ (Vector Quantization) clustering method, which yields homogeneous objects in terns of color and texture. In this procedure, colors are quantized into a few dominant colors for simple representation and efficient retrieval. In retrieval case, two comparing schemes are proposed. Comparing between one query object and multi objects of a database image and comparing between multi query objects and multi objects of a database image are proposed. For fast retrieval, dominant object colors are key-indexed into database.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.129-132
• /
• 2000

In this paper, a multimedia database retrieval system is proposed using MPEG-7 meta data. Multimedia content based retrieval system is implemented with the MPEG-7 meta data extraction and matching technique. MPEG-7 descriptors and descriptor schemes are stored into the database with other meta data. When a query image is given, the descriptors and descriptor schemes of the query image are extracted and compared with the descriptors and descriptor schemes in the database. Finally, images having more similarity are retrieved.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.1-14
• /
• 2007

Character images for the background screen of cell phones are one of the fast growing sectors of the mobile content market. However, character image buyers currently experience tremendous difficulties in searching for desired images due to the awkward image search process. Content-based image retrieval (CBIR) widely used for image retrieval could be a good candidate as a solution to this problem, but it needs to overcome the limitation of the mobile Internet environment where an initial query set (IQS) cannot be easily provided as in the PC-based environment. We propose a new approach, IQS-AutoGen, which automatically generates an initial query set for CBIR on the mobile Internet. The approach applies the collaborative filtering (CF), a well-known recommendation technique, to the CBIR process by using users' preference information collected during the relevance feedback process of CBIR. The results of the experiment using a PC-based prototype system show that the proposed approach successfully satisfies the initial query requirement of CBIR in the mobile Internet environment, thereby outperforming the current image search process on the mobile Internet.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.603-614
• /
• 1999

As multimedia application services on high-speed information network have been rapidly developed, the need for the video information management system that provides an efficient way for users to retrieve video data is growing. In this paper, we propose a video data model that integrates free annotations, image features, and spatial-temporal features for video purpose of improving content-based retrieval of video data. The proposed video data model can act as a generic video data model for multimedia applications, and support free annotations, image features, spatial-temporal features, and structure information of video data within the same framework. We also propose the video query language for efficiently providing query specification to access video clips in the video data. It can formalize various kinds of queries based on the video contents. Finally we design and implement the query processing engine for efficient video data retrieval on the proposed metadata model and the proposed video query language.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1902-1911
• /
• 1999

In this paper we present a content-based image retrieval algorithm using the visual feature vectors which describe the spatial characteristics of objects. The proposed technique uses the Gaussian mixture model(GMM) to represent multi-colored objects and the expectation maximization(EM) algorithm is employed to estimate the maximum likelihood(ML) parameters of the model. After image segmentation is performed based on GMM, the shape and color features are extracted from each object using Fourier descriptors and color histograms, respectively. Image retrieval consists of two steps: first, the shape-based query is carried out to find the candidate images whose objects have the similar shapes with the query image and second, the color-based query is followed. The experimental results show that the proposed algorithm is effective in image retrieving by using the spatial and visual features of segmented objects.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.960-968
• /
• 2018

The mobile visual search service uses a query image to acquire linkage information through pre-constructed DB search. From the standpoint of this purpose, it would be more useful if you could perform a search on a web-based keyword search system instead of a pre-built DB search. In this paper, we propose a representative query extraction algorithm to be used as a keyword on a web-based search system. To do this, we use image classification labels generated by the CNN (Convolutional Neural Network) algorithm based on Deep Learning, which has a remarkable performance in image recognition. In the query extraction algorithm, dictionary meaningful words are extracted using Wikipedia, and hierarchical categories are constructed using WordNet. The performance of the proposed algorithm is evaluated by measuring the system response time.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.9
• /
• pp.2315-2332
• /
• 1997

In this paper, we implement a content based image retrieval system for image searching by visual features from the image databases on WWW (world wide web). The image retrieval system finds the images that contain the most similar color regions after the system automatically extracts color features from the input image. We can select one of two query methods which use a full image of $4{\times}4$ 16 sketched color region. The image similarity is calculated on the histogram intersection distance and the histogram Euclidean distance. As the experimental results show that the two different query types provide the precision/recall 0.84/0.92 and 0.85/0.93 respectively, this retrieval system has been able to obtain high performance and validity.