• ETRI Journal
• /
• 제33권2호
• /
• pp.240-250
• /
• 2011

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제15권3호
• /
• pp.579-586
• /
• 2020

There is a large amount of multimedia data on the web page, and a method of extracting semantic information from low level visual information for accurate retrieval is being studied. However, most of these techniques extract one of information from a single image, so it is difficult to extract semantic information when multiple objects are combined in the image. In this paper, each low-level feature is extracted to extract various objects and backgrounds in an image, and these are divided into predefined backgrounds and objects using SVM. The objects and backgrounds divided in this way are constructed with ontology, infer the semantic information of location and association using inference engine. It's possible to extract the semantic information. We propose this method process the complex and high-level semantic information in image.

• Journal of KIISE:Software and Applications
• /
• 제35권1호
• /
• pp.22-32
• /
• 2008

To overcome the weakness of the image retrieval system using the existing Ontology and the distributed image based on the database having a simple structure, HERMES was suggested to ensure the self-control of various image suppliers and support the image retrieval based on semantic, the mentioned framework could not solve the problems which are not considered the deterioration in the capacity and scalability when many users connect to broker server simultaneously. In this paper the tables are written which in the case numerous users connect at the same time to the supply analogous level of services without the deterioration in the capacity installs Broker servers and then measures the performance time of each inner Broker Component through Monitoring System and saved and decides the ranking in saved data. As many Query performances are dispersed into several Servers User inputted from the users Interface with reference to Broker Ranking Table, Load Balancing system improving reliability in capacity is proposed. Through the experiment, the scheduling technique has proved that this schedule is faster than existing techniques.

• KIISE Transactions on Computing Practices
• /
• 제22권6호
• /
• pp.290-295
• /
• 2016

Recently, folksonomy-based image-sharing sites where users cooperatively make and utilize tags of image annotation have been gaining popularity. Typically, these sites retrieve images for a user request using simple text-based matching and display retrieved images in the form of photo stream. However, these tags are personal and subjective and images are not categorized, which results in poor retrieval accuracy and low user satisfaction. In this paper, we propose a categorization scheme for folksonomy images which can improve the retrieval accuracy in the tag-based image retrieval systems. Consequently, images are classified by the semantic similarity using text-information and image-information generated on the folksonomy. To evaluate the performance of our proposed scheme, we collect folksonomy images and categorize them using text features and image features. And then, we compare its retrieval accuracy with that of existing systems.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제8권3호
• /
• pp.409-414
• /
• 2013

With the increase of multimedia information such as images, researches have been realized on how to extract the high-level semantic information from low-level visual information, and a variety of techniques have been proposed to generate this information automatically. However, most of these technologies extract the semantic information between single images, it's difficult to extract semantic information when a combination of multiple objects within the image. In this paper, we extract the visual features of objects within the image and training images stored in the DB and the features of each object are defined by measuring the similarity. Using ontology reasoner, each object feature within images infers the semantic information by positional relation and associative relation. With this, it's possible to infer semantic information between objects within images, we proposed a method for inferring more complicated and a variety of high-level semantic information.

• Journal of the Korea Society of Computer and Information
• /
• 제11권4호
• /
• pp.1-7
• /
• 2006

Recently, studies of relevance feedback to increase the performance of image retrieval has been activated. In this Paper a new region weighting method in region based image retrieval with relevance feedback is proposed to reduce the semantic gap between the low level feature representation and the high level concept in a given query image. The new weighting method determines the importance of regions according to the spatial locations of regions in an image. Experimental results demonstrate that the retrieval quality of our method is about 18% in recall better than that of area percentage approach. and about 11% in recall better than that of region frequency weighted by inverse image frequency approach and the retrieval time of our method is a tenth of that of region frequency approach.

• Journal of Korea Multimedia Society
• /
• 제7권1호
• /
• pp.132-144
• /
• 2004

With the rapid development of internet technology, the number of internet users and the amount of multimedia information on the internet is ever increasing. Recently, the web sites, such as e-business sites and shopping mall sites, deal with lots of image information. As a result, it is required to support content- based image retrieval efficiently on such image data. This paper proposes an intelligent image retrieval system, which adopts XML, technology. To support object-based col)tent retrieval on product catalog images containing multiple objects, we describe a multi -level metadata structure which represents the local features, global features, and semantics of image data. To enable semantic-based and content-based retrieval on such image data, we design a XML-Schema for the proposed metadata and show how to represent such metadata using XML- documents. We also describe how to automatically transform the retrieval results into the forms suitable for the various user environments, such as web browser or mobile browser, using XSLT The proposed scheme can be easily implemented on any commercial platforms supporting XML technology. It can be utilized to enable efficient image metadata sharing between systems, and it will contribute in improving the retrieval correctness and the user's satisfaction on content-based e-catalog image retrieval.

• The Transactions of the Korea Information Processing Society
• /
• 제6권12호
• /
• pp.3559-3568
• /
• 1999

The information overload with many information resources is an inevitable problem in modern electronic life. It is more difficult to search some information with user's information needs from an uncontrolled flood of many digital information resources, such as the internet which has been rapidly increased. So, many information retrieval systems have been researched and appeared. In text retrieval systems, they have met with user's information needs. While, in image retrieval systems, they have not properly dealt with user's information needs. In this paper, for resolving this problem, we proposed the intelligent user interface for image retrieval. It is based on HCOS(Human-Computer Symmetry) model which is a layed interaction model between a human and computer. Its' methodology is employed to reduce user's information overhead and semantic gap between user and systems. It is implemented with machine learning algorithms, decision tree and backpropagation neural network, for user adaptation capabilities of intelligent image retrieval system(IIRS).

• The Journal of the Korea institute of electronic communication sciences
• /
• 제18권3호
• /
• pp.413-420
• /
• 2023

For a long time, researchers have presented excellent results in the field of image retrieval due to many studies on CBIR. However, there is still a semantic gap between these search results for images and human perception. It is still a difficult problem to classify images with a level of human perception using a small number of images. Therefore, this paper proposes an image classification model using deep learning-based transfer learning to minimize the semantic gap between images of people and search systems in image retrieval. As a result of the experiment, the loss rate of the learning model was 0.2451% and the accuracy was 0.8922%. The implementation of the proposed image classification method was able to achieve the desired goal. And in deep learning, it was confirmed that the CNN's transfer learning model method was effective in creating an image database by adding new data.