• Journal of KIISE:Databases
• /
• v.33 no.4
• /
• pp.372-383
• /
• 2006

Among the approaches to image database management, content-based image retrieval (CBIR) is viewed as having the best support for effective searching and browsing of large digital image libraries. Typical CBIR systems allow a user to provide a query image, from which low-level features are extracted and used to find 'similar' images in a database. However, there exists the semantic gap between human visual perception and low-level representations. An effective methodology for overcoming this semantic gap involves relevance feedback to perform feature re-weighting. Current approaches to feature re-weighting require the number of components for a feature representation to be the same for every image in consideration. Following this assumption, they map each component to an axis in the n-dimensional space, which we call the metric space; likewise the feature representation is stored in a fixed-length vector. However, with the emergence of features that do not have a fixed number of components in their representation, existing feature re-weighting approaches are invalidated. In this paper we propose a feature re-weighting technique that supports features regardless of whether or not they can be mapped into a metric space. Our approach analyses the feature distances calculated between the query image and the images in the database. Two-sided confidence intervals are used with the distances to obtain the information for feature re-weighting. There is no restriction on how the distances are calculated for each feature. This provides freedom for how feature representations are structured, i.e. there is no requirement for features to be represented in fixed-length vectors or metric space. Our experimental results show the effectiveness of our approach and in a comparison with other work, we can see how it outperforms previous work.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.53-59
• /
• 2009

Multi-view video is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method by presentation of efficient layered depth image using real distance comparison, solution of overlap problem, and interpolation. In experimental results, confirmed high compression performance.

• Journal of Broadcast Engineering
• /
• v.1 no.1
• /
• pp.74-83
• /
• 1996

In this paper, an effective color image retrieval algorithm is proposed based on the graph representation. Also we propose a color constancy algorithm to remove the effect of illumination change. Illumination condition of an image can be transformed to that of reference image using the proposed color constancy algorithm, so that the effect of dirrerent lighting is significantly alleviated. Then, we represent a color image as a graph with several nodes and edges in the histogram space, and finally two images are matched by compared two graphs representing them. The simulation results show that the proposed 3-step algorithm performs well for various conditions, including different lighting, translation, rotation, and scaling of the object in the image. In addition, the proposed algorithm is very fast compared to the geometry-based matching technique.

• Journal of Fashion Business
• /
• v.13 no.5
• /
• pp.149-160
• /
• 2009

The purpose of this research is to analyze how contemporary hairstyles are expressed based on the recurrence and non-recurrence of simulation. The results of this study can be summarized as follows : 1) Recurrence appeared as imitation which re-expresses the image of past hairstyles, change which borrows unordinary objects from previous hairstyles, and expansion which extends the volume in hairstyles. 2) For nonrecurrence, there were an absence of hairstyles which rid reality, a sub-culture as a disband of fixed perceptions, a combination with other genres, an ambiguity of hairstyles appearing as a fusion effect and a Kitsch phenomenon, an ambiguity of hairstyles where a totally different third image appears through dichotomy concepts combined.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1731-1737
• /
• 2016

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.51 no.1
• /
• pp.46-54
• /
• 2002

Plasma Display Panel (PDP) is required to be both the determination of white point of each gray level and the inverse gamma correction since no-balanced RGB cell and linear property of PDP, respectively. However, these two methods cause degradation of grey level representation and undesirable false contour in the dark areas on PDP. In this paper, we implemented real time image processor of the proposed error diffusion algorithm and unsharp masking operation to protect the blurring image caused by the error diffusion. Experimental results showed drastic improvements of gray level representation and reduction of undesirable false contour.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2346-2362
• /
• 2016

As one of the most important issues in computer vision and image processing, online object tracking plays a key role in numerous areas of research and in many real applications. In this study, we present a novel tracking method based on the proposed structured sparse representation model, in which the tracked object is assumed to be sparsely represented by a set of object and background templates. The contributions of this work are threefold. First, the structure information of all the candidate samples is utilized by a joint sparse representation model, where the representation coefficients of these candidates are promoted to share the same sparse patterns. This representation model can be effectively solved by the simultaneous orthogonal matching pursuit method. In addition, we develop a tracking algorithm based on the proposed representation model, a discriminative candidate selection scheme, and a simple model updating method. Finally, we conduct numerous experiments on several challenging video clips to evaluate the proposed tracker in comparison with various state-of-the-art tracking algorithms. Both qualitative and quantitative evaluations on a number of challenging video clips show that our tracker achieves better performance than the other state-of-the-art methods.

• International Journal of Costume and Fashion
• /
• v.5 no.2
• /
• pp.68-77
• /
• 2005

In contemporary advertising market, one of main trends is to speak surrealistic visual language which provides 'enjoyable spectacles'. Specially, in the beginning of 21st century, there discovered more and more exhibitions and discourses about surrealism reinterpreted from the viewpoint of postmodernism. Surrealism as a creative style of expression based upon free association, has been a great inspiration for fashion ads for commercial communication as well as fashion design since its origin. However, there has been ignored the idea of analyzing surrealistic image expressed in fashion ads in spite of their flood. Accordingly, the purpose of this study is to grasp its cultural meaning through analyzing aesthetic characteristics of surrealistic image expressed in fashion ads. It will provide a better understanding of surrealistic image in fashion ads reflecting popular taste and preference directly as popular visual culture, focusing on post modern context. A case study of surrealistic fashion ads limits to TV or print commercials and digital ads as image ads stimulating visual expressions. The Results can be summarized as follows. Surrealism is an avant garde style which deconstructs the established meaning system as well as the existing formalistic order and then put them together in the frame of 'dream' and 'unconsciousness'. Defamiliarization questioning the whole edifice of representation can be adapted to. By means of paradox and metaphor, unfamiliar new visual world can be represented. The plastic characteristics of surrealistic image in fashion ads are founded as surrealistic styling of time and space, distortion of object by methods of automatism, depaysement, parody and trompe-l'oeil which bring about the deconstruction of gestalt. Aesthetic values of surrealistic fashion ads appear as dualistic representation, allegoric symbolism, fantastic romanticism. Ultimately they lead to marvelous. mysterious, humorous visual effects. Foster reinterpreted these effects of surrealism from Freud's 'Uncanny Concept'. 'Uncanny' means the phenomenon recurring to familiar being defamiliarized by repression. Surrealistic fashion ads strengthen this shocking effect more and more dramatically in company with our post modern needs for fantastic adventure and thrilling spectacle. It can be thought that surrealistic fashion ads reflects uncanny as an alternative which can relieve us of our stress and anxiety and which realize our potential desire in contemporary post industrial stage.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2946-2952
• /
• 2014

Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.35-38
• /
• 2000

The method of Content-based Triangular Mesh Image representation in moving pictures makes better performance in prediction error ratio and visual efficiency than that of classical block matching. Specially if background and objects can be separated from image, the objects are designed by Irregular mesh. In this case this irregular mesh design has an advantage of increasing video coding efficiency. This paper presents the techniques of mesh generation, motion estimation using these mesh, uses image warping transform such as Affine transform for image reconstruction, and evaluates the content based mesh design through computer simulation.