• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2634-2636
• /
• 2001

This paper proposes a new method of retrieving images from large image databases. The method is based on VQ(Vector Quantization) of local texture information at interest points automatically detected in an image. The texture features are extracted by Gabor wavelet filter bank, and rearranged for rotation. These features are classified by VQ and then construct a pattern histogram. Retrievals are performed by just comparing pattern histograms between images. Experimental results have shown the robustness of the proposed method to image rotation, small scale change, noise addition and brightness change and also shown the possibility of the retrieval by a partial image.

• Journal of KIISE:Databases
• /
• v.34 no.3
• /
• pp.193-205
• /
• 2007

Increasing amount of digital images requires more accurate and faster way of image retrieval. So far, image retrieval method includes content-based retrieval and keyword based retrieval, the former utilizing visual features such as color and brightness and the latter utilizing keywords which describe the image. However, the effectiveness of these methods as to providing the exact images the user wanted has been under question. Hence, many researchers have been working on relevance feedback, a process in which responses from the user are given as a feedback during the retrieval session in order to define user’s need and provide improved result. Yet, the methods which have employed relevance feedback also have drawbacks since several feedbacks are necessary to have appropriate result and the feedback information can not be reused. In this paper, a novel retrieval model has been proposed which annotates an image with a keyword and modifies the confidence level of the keyword in response to the user’s feedback. In the proposed model, not only the images which have received positive feedback but also the other images with the visual features similar to the features used to distinguish the positive image are subjected to confidence modification. This enables modifying large amount of images with only a few feedbacks ultimately leading to faster and more accurate retrieval result. An experiment has been performed to verify the effectiveness of the proposed model and the result has demonstrated rapid increase in recall and precision while receiving the same number of feedbacks.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.446-454
• /
• 2009

Among various region detector and shape feature extraction method, MSER(Maximally Stable Extremal Region) and SIFT and its variant methods are popularly used in computer vision application. However, since SIFT is sensitive to the illumination change and MSER is sensitive to the scale change, it is not easy to apply the image similarity retrieval. In this paper, we present a Scale and Rotation Invariant Region Feature(SRIRF) descriptor using scale pyramid, MSER and affine normalization. The proposed SRIRF method is robust to scale, rotation, illumination change of image since it uses the affine normalization and the scale pyramid. We have tested the SRIRF method on various images. Experimental results demonstrate that the retrieval performance of the SRIRF method is about 20%, 38%, 11%, 24% better than those of traditional SIFT, PCA-SIFT, CE-SIFT and SURF, respectively.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.509-516
• /
• 2004

Semantic interpretation of image is incomplete without some mechanism for understanding semantic content that is not directly visible. For this reason, human assisted content-annotation through natural language is an attachment of textual description to image. However, keyword-based retrieval is in the level of syntactic pattern matching. In other words, dissimilarity computation among terms is usually done by using string matching not concept matching. In this paper, we propose a method for computerized semantic similarity calculation In WordNet space. We consider the edge, depth, link type and density as well as existence of common ancestors. Also, we have introduced method that applied similarity measurement on semantic image retrieval. To combine wi#h the low level features, we use the spatial color distribution model. When tested on a image set of Microsoft's 'Design Gallery Line', proposed method outperforms other approach.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.67-73
• /
• 2011

The image retrieval generally shows the same or similar images to a query image as a result. In the case of rotated image, however, its performance tends to be debased significantly. We propose a method to ensure a reliable image retrieval of rotated images as follows; First, to obtain feature points of query/DB images by Harris Corner Detector; and then, utilizing the feature points, to find the object's axis and query/DB images into rotation invariant images with Principal Components Analysis algorithm. We have experimented with 6,000 natural images which are 256 pixels in diameter. They are 1,000 Wang's images and their rotated images by $30^{\circ}$, $45^{\circ}$, $90^{\circ}$, $135^{\circ}$ and $180^{\circ}$. The simulation results show that the proposed method retrieves rotated images more effectively than the conventional method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.724-732
• /
• 2001

In this paper, a new method of feature extraction of major objects to represent an image using Vector Quantization(VQ) is proposed. The principal features of the image, which are used in a content-based image retrieval system, are color, texture, shape and spatial positions of objects. The representative color and texture features are extracted from the given image using VQ(Vector Quantization) clustering algorithm with a general feature extraction method of color and texture. Since these are used for content-based image retrieval and searched by objects, it is possible to search and retrieve some desirable images regardless of the position, rotation and size of objects. The experimental results show that the representative feature extraction time is much reduced by using VQ, and the highest retrieval rate is given as the weighted values of color and texture are set to 0.5 and 0.5, respectively, and the proposed method provides up to 90% precision and recall rate for 'person'query images.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.480-483
• /
• 2005

This study has proposed a method of content-based image retrieval in order to overcome disadvantages of color histogram. The existing histogram method has a weak point that reduces accuracy because of quantization error, and more. In order to solve this, we convert color information to HSV and quantize Hue factor being net color information and calculate histogram and then use this for retrieval feature that is robust in brightness, movement, and rotation. As a result of experimenting, the method proposed has showed better precision than the existing method.

• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1312-1320
• /
• 2004

Recently, even if a lot of visual feature representations have been studied and systems have been built, there is a limit to existing content-based image retrieval mechanism in its availability. One of the limits is the gap between a user's high-level concepts and a system's low-level features. And human beings' subjectivity in perceiving similarity is excluded. Therefore, correct visual information delivery and a method that can retrieve the data efficiently are required. Relevance feedback can increase the efficiency of image retrieval because it responds of a user's information needs in multimedia retrieval. This paper proposes an efficient CBIR introducing positive and negative relevance feedback with threshold value and pre-fetching to improve the performance of conventional relevance feedback mechanisms. With this Proposed feedback strategy, we implement an image retrieval system that improves the conventional retrieval system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.434-441
• /
• 2001

We present an image retrieval method for improving retrieval performance by the effective fusion of spatial histogram and wavelet moments. In this method, the similarity for spatial histograms and the similarity for wavelet moment are effectively fused in the computation of the similarity between a query image and DB image. That is, the wavelet moments feature represented in multi-resolution and the spatial histogram feature robust to translation and rotation are used to improve retrieval performance. In order to evaluate the performance of the proposed method, we use Brodatz texture DB, MPEG-7 T1 DB, and Corel Draw Photo DB. Experimental results show that the proposed method yields 5.3% and 13.8% better Performances for Brodatz DB, and 15.5% and 3.2% better Performances for Corel Draw Photo DB over the histogram method and the wavelet moment method, respectively.