• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.355-360
• /
• 2018

We propose a method to connect partial image in whole image to partial image in whole image of other internet site. For this study, we have developed four partial image generation methods and retrieval methods. A method of 'image segmentation' that cuts out only partial images that want to provide information from the whole image, a method of 'creating an image block' that finds outermost points of a cut-out partial image, a method of 'Stamp transformation of outer points', which connects outer points and registers them as the most similar image stamp, and a retrieval method that connects image stamps with other image stamps are developed. We suggested a image search UI that can use image stamps in various ways.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.764-768
• /
• 2015

Requirement of effective image handling methods such as image retrieval has been increasing with the rising production and consumption of multimedia data. In this paper, a method of constructing more effective descriptor is proposed for robust keypoint based image retrieval. The proposed method uses information embedded in the first order and second order derivative images, in addition to the scale space image, for the descriptor construction. The performance of multi-image descriptor is evaluated in terms of the similarities in keypoints with a public domain image database that contains various image transformations. The proposed descriptor shows significant improvement in keypoint matching with minor increase of the length.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.803-810
• /
• 2005

Information retrieval is one of the most challenging areas in which the ontology technology is effectively used. Among them image retrieval using the image meta data and ontology is the one that can substitute the keyword-based image retrieval. In the paper, the retrieval of visual media such as the art image and photo picture is handled. It is assumed that there are more than one service providers of the visual media and also there is one central service broker that mediates the user's query. Given the user's query the first step that must be done in the service broker is to get the list of candidate service providers that fit the query. This is done by defining various ontologies such as the service ontology and matching the query against the ontology and providers. A novel matching method based on the ASN.1. The experiment shows that the method is more effective than existing tree-based and interval-based methods. Ontology merging issue is also handled that can happen when the service providers register their service into the service broker. An effective method is also proposed.

• Journal of Internet Computing and Services
• /
• v.4 no.4
• /
• pp.1-8
• /
• 2003

As the multimedia information retrieval system is advanced, the study of multimedia information retrieval is changing the method of low-level content based image retrieval to the semantical concept based retrieval. in this paper, we apply the theory of ontology to overcome the conceptual heterogeneity in the annotation based image retrieval. And we solve the some problems that happen when the ontology apply. As a result of our study, we try to apply the domain ontology to settle the conceptual heterogenity. In the experimental result, we knew that the semantic distance among the words is pretty dose when we apply the domain ontology than the wordnet. And in this paper, we show the possibility of the semantic image retrieval as we apply the domain ontology in the annotation based image retrieval.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.113-120
• /
• 2004

In this paper, we propose an efficient feature extraction and image retrieval algorithm for content-based retrieval method. First, we extract the object using Gaussian edge detector for input image which is key frames of MPEG video and extract the object features that are location feature, distributed dimension feature and invariant moments feature. Next, we extract the characteristic color feature using the proposed HAQ(Histogram Analysis md Quantization) algorithm. Finally, we implement an retrieval of four features in sequence with the proposed matching method for query image which is a shot frame except the key frames of MPEG video. The purpose of this paper is to propose the novel content-based image retrieval algerian which retrieves the key frame in the shot boundary of MPEG video belonging to the scene requested by user. The experimental results show an efficient retrieval for 836 sample images in 10 music videos using the proposed algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8B
• /
• pp.1391-1399
• /
• 2000

In this paper, we discussed the region-based image retrieval method using image segmentation. We proposed a segmentation method which can reduce the effect of a irregular light sources. The image segmentation method uses a region-merging, and candidate regions which are merged were selected by the energy values of high frequency bands in discrete wavelet transform. The content-based image retrieval is executed by using the segmented region information, and the images are retrieved by a color, texture, shape feature vector. The similarity measure between regions is processed by the Euclidean distance of the feature vectors. The simulation results shows that the proposed method is reasonable.

• 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.

• Journal of KIISE:Software and Applications
• /
• v.29 no.12
• /
• pp.940-946
• /
• 2002

This paper proposes an image retrieval method to use the modified color correlogram. For retrieving images with less effect of the size variation of the regions in an image, the modified color correlogram is extracted by normalizing auto-correlogram and cross-correlogram of the color correlogram from a color image, and the similarity of two images is calculated by putting the less weight to the auto-correlogram of the modified color correlogram. Because proposed method uses the information of the color correlogram more effectively, we can get better results than that of color correlogram method. In the experiments, the performance of the proposed method is better as compared with that of the color cerrelogram method.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.651-656
• /
• 2001

Histogram intersection method, that counts the occurrence of color pixels, is one of the easy and simple color image retrieval methods. The method has an appropriate global property but does not contain the knowledge of shape for images. The absence of spatial information makes it difficult to discriminate images of the similar histogram. The application of one-dimensional projection to each image enables to obtain shape or spatial information of image. But in this case there is another problem having different length of the projection vector according to the size of each image. Thus this paper proposes a method that uses relative distances between peaks and their maximum value in the projection vector. In order to verify retrieval performance, the experimental results between the histogram intersection method, the projection only method, and the proposed one are compared and analyzed.