• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.6
• /
• pp.111-118
• /
• 1996

A content-based image retrieval system is designed and implemetned using the color featurees which are histogram intersection and color pairs. The preprocessor for the image retrieval manage linearly the existing HSI(hue, saturation, saturation, intensity). Hue and intensity histogram thresholding for each color attribute is performed to split the chromatic and achromatic regions respectively. Grouping te indexes produced by the histogram intersection is used to save the retrieval times. Each image is divided into the cells of 32$\times$32 pixels, and color pairs are used to represent the query during retrievals. The recall/precision of histogram intersection is 0.621/0.663 and recall/precision of color pairs is 0.438/0.536. And recall/precision of proposed method is 0.765/0.775/. It is shown that the proposed method using histogram intersection and color pairs improves the retrieval rates.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.683-688
• /
• 2008

The emotional information processing is to simulate and recognize human sensibility, sensuality or emotion, to realize natural and harmonious human-machine interface. This paper proposes an emotion-based image retrieval method. In this method, user can choose a linguistic query among some emotional adjectives. Then the system shows some corresponding representative images that are pre-evaluated by experts. Again the user can select a representative one among the representative images to initiate traditional content-based image retrieval (CBIR). By this proposed method any CBIR can be easily expanded as emotion-based image retrieval. In CBIR of our system, we use several color and texture visual descriptors recommended by MPEG-7. We also propose a fuzzy similarity measure based on Choquet integral in the CBIR system. For the communication between system and user, a relevance feedback mechanism is used to represent human subjectivity in image retrieval. This can improve the performance of image retrieval, and also satisfy the user's individual preference.

• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.7C
• /
• pp.719-725
• /
• 2003

The content-based image retrieval system extracts features of color, shape and texture from raw images, and builds the database with those features in the indexing process. The search in the whole retrieval system is defined as a process which finds images that have large similarity to query image using the feature database. This paper proposes a new two-stage search method in the content-based image retrieval system. The method is that the features are condensed and stored by the property of Cauchy-Schwartz inequality in order to reduce the similarity computation time which takes a mostly response time from entering a query to getting retrieval results. By the extensive computer simulations, we have observed that the proposed two-stage search method successfully reduces the similarity computation time while maintaining the same retrieval relevance as the conventional exhaustive search method. We also have observed that the method is more effective as the number of images and dimensions of the feature space increase.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3790-3803
• /
• 2018

Content-based image retrieval is an approach used to query images based on their semantics. Semantic based retrieval has its application in all fields including medicine, space, computing etc. Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders. Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. Convolutional autoencoders are basis to extract semantic features due to its property of image generation from low level semantic representations. These representations of images are more effective than simple feature extraction and can preserve better semantic information. Proposed activation and loss functions helped to minimize classification error and produce better hash codes. Most widely used datasets have been used for verification of this approach that outperforms the existing methods.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.1
• /
• pp.81-91
• /
• 2005

In this paper we present a novel approach for image retrieval using color and edge information. We take into account the HSI(Hue, Saturation and Intensity) color space instead of RGB space, which emphasizes more on visual perception. In our system colors in an image are clustered into a small number of representative colors. The color feature descriptor consists of the representative colors and their percentages in the image. An improved cumulative color histogram distance measure is defined for this descriptor. And also, we have developed an efficient edge detection technique as an optional feature to our retrieval system in order to surmount the weakness of color feature. During the query processing, both the features (color, edge information) could be integrated for image retrieval as well as a standalone entity, by specifying it in a certain proportion. The content-based retrieval system is tested to be effective in terms of retrieval and scalability through experimental results and precision-recall analysis.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.1
• /
• pp.8-18
• /
• 2008

In this paper, we propose an efficient algorithm using wavelet transform for still image database retrieval. Especially, it uses only the lowest frequency sub-band in multi-level wavelet transform so that a retrieval system uses a smaller quantity of memory and takes a faster processing time. We extract different textured features, statistical information such as mean, variance and histogram, from low frequency sub-band. Then we measure the distances between the query image and the images in a database in terms of these features. To obtain good retrieval performance, we use the first feature (mean and variance of wavelet coefficients) to filter out most of the unlikely images. The rest of the images are considered to be candidate images. Then we apply the second feature (histogram of wavelet coefficient) to rank all the candidate images. To evaluate the algorithm, we create various distorted image databases using MIT VisTex texture images and PICS natural images. Through simulations, we demonstrate that our method can achieve performance satisfactorily in terms of the retrieval accuracy as well as the both memory requirement and computational complexity. Therefore it is expected to provide good retrieval solution for JPEG-2000 using wavelet transform.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.134-144
• /
• 1996

In this paper, we propose a new access method, called the HG-tree, to support indexing and retrieval by image content in large image databases. Image content is represented by a point in a multidimensional feature space. The types of queries considered are the range query and the nearest-neighbor query, both in a multidimensional space. Our goals are twofold: increasing the storage utilization and decreasing the area covered by the directory regions of the index tree. The high storage utilization and the small directory area reduce the number of nodes that have to be touched during the query processing. The first goal is achieved by absorbing splitting if possible, and when splitting is necessary, converting two nodes to three. The second goal is achieved by maintaining the area occupied by the directory region minimally on the directory nodes. We note that there is a trade-off between the two design goals, but the HG-tree is so flexible that it can control the trade-off. We present the design of our access method and associated algorithms. In addition, we report the results of a series of tests, comparing the proposed access method with the buddy-tree, which is one of the most successful point access methods for a multidimensional space. The results show the superiority of our method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.4
• /
• pp.26-31
• /
• 2004

Due to the recent explosive progress of Web, We can easily access a large number of images from m. In this paper, we describe our approach of developing a general purpose content based image retrieval system over the H using a Web agent. The Web agent extracts text information of images from the links and file contents in HTML. The proposed system retrieves the images from database using the query by sketch and the query by example on Web browser. Experimental results demonstrate the effectiveness of the new approach.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.375-378
• /
• 2000

In this paper, we propose a novo] content-based image retrieval system using both Hidden Markov Model(HMM) and an improved chain code. The Gaussian Mixture Model(GMM) is applied to statistically model a color information of the image, and Deterministic Annealing EM(DAEM) algorithm is employed to estimate the parameters of GMM. This result is used to segment the given image. We use an improved chain code, which is invariant to rotation, translation and scale, to extract the feature vectors of the shape for each image in the database. These are stored together in the database with each HMM whose parameters (A, B, $\pi$) are estimated by Baum-Welch algorithm. With respect to feature vector obtained in the same way from the query image, a occurring probability of each image is computed by using the forward algorithm of HMM. We use these probabilities for the image retrieval and present the highest similarity images based on these probabilities.