• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.304-314
• /
• 2007

Content Based Image Retrieval (CBIR) is to store and retrieve images using the feature description of image contents. In order to support more accurate image retrieval, it has become necessary to develop features that can effectively describe image contents. The commonly used low-level features, such as color, texture, and shape features may not be directly mapped to human visual perception. In addition, such features cannot effectively describe a single image that contains multiple objects of interest. As a result, the research on feature descriptions has shifted to focus on higher-level features, which support representations more similar to human visual perception like spatial relationships between objects. Nevertheless, the prior works on the representation of spatial relations still have shortcomings, particularly with respect to supporting rotational invariance, Rotational invariance is a key requirement for a feature description to provide robust and accurate retrieval of images. This paper proposes a high-level feature named 8AB (8 Angular Bin) that effectively describes the spatial relations of objects in an image while providing rotational invariance. With this representation, a similarity calculation and a retrieval technique are also proposed. In addition, this paper proposes a search-space pruning technique, which supports efficient image retrieval using the 8AB feature. The 8AB feature is incorporated into a CBIR system, and the experiments over both real and synthetic image sets show the effectiveness of 8AB as a high-level feature and the efficiency of the pruning technique.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.173-184
• /
• 2002

This paper discuss an index-based subsequence matching that supports time warping in large sequence databases. Time warping enables finding sequences with similar patterns even when they are of different lengths. In earlier work, Kim et al. suggested an efficient method for whole matching under time warping. This method constructs a multidimensional index on a set of feature vectors, which are invariant to time warping, from data sequences. For filtering at feature space, it also applies a lower-bound function, which consistently underestimates the time warping distance as well as satisfies the triangular inequality. In this paper, we incorporate the prefix-querying approach based on sliding windows into the earlier approach. For indexing, we extract a feature vector from every subsequence inside a sliding window and construct a multidimensional index using a feature vector as indexing attributes. For query processing, we perform a series of index searches using the feature vectors of qualifying query prefixes. Our approach provides effective and scalable subsequence matching even with a large volume of a database. We also prove that our approach does not incur false dismissal. To verify the superiority of our approach, we perform extensive experiments. The results reveal that our approach achieves significant speedup with real-world S&P 500 stock data and with very large synthetic data.

• Korean Journal of Food Science and Technology
• /
• v.24 no.2
• /
• pp.165-170
• /
• 1992

The creep behavior of gels made with $30{\sim}45%$ gelatinized rice starch was measured over a wide range of temperature. Compressive creep curves of rice starch gels conformed to a six element mechanical model consisting of one Hookean, two Voigt and one Newtonian component. The creep compliance of gels decreased with increasing starch concentrations. Among viscoelastic constants of the mechanical model, elastic modulus was mainly influenced by the change of starch concentrations. The concentration-invariant compliance curve was obtained by reduction to 38% using reduction parameter $a_{c}$. The creep compliance curves of 45% starch gels increased with temperature, which indicated that rice starch gels became softer and less rigid with increasing temperature. When the compliance at $20^{\circ}C$ was set as a reference curve, creep compliance data for 45% gels at various temperature could be superimposed as a continuous smooth curve. The apparent activation energies of 45% rice starch gels calculated by the modified WLF equation were not intrinsic, but decreased as temperature increased.

• Journal of Biomedical Engineering Research
• /
• v.32 no.3
• /
• pp.237-244
• /
• 2011

In this paper, a feature-based registration technique is proposed for pre-contrast and post-contrast lung CT images. It utilizes three dimensional(3-D) features with their descriptors and estimates feature correspondences by nearest neighborhood matching in the feature space. We design a transformation model between the input image pairs using a free form deformation(FFD) which is based on B-splines. Registration is achieved by minimizing an energy function incorporating the smoothness of FFD and the correspondence information through a non-linear gradient conjugate method. To deal with outliers in feature matching, our energy model integrates a robust estimator which discards outliers effectively by iteratively reducing a radius of confidence in the minimization process. Performance evaluation was carried out in terms of accuracy and efficiency using seven pairs of lung CT images of clinical practice. For a quantitative assessment, a radiologist specialized in thorax manually placed landmarks on each CT image pair. In comparative evaluation to a conventional feature-based registration method, our algorithm showed improved performances in both accuracy and efficiency.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.34-37
• /
• 2006

When tsunami waves propagate across open ocean they are steered by Coriolis force and refraction due to gentle gradients in the bathymetry on scales longer than the wavelength. When the wave encounters steep gradients at the edges of continental shelves and at the coast, the wave becomes non-linear and conservation of momentum produces squirts of surface current at the head of submerged canyons and in coastal bays. HF coastal ocean radar is well-conditioned to observe the current bursts at the edge of the continental shelf and give a warning of 40 minutes to 2 hours when the shelf is 50-200km wide. The period of tsunami waves is invariant over changes in bathymetry and is in the range 2-30 minutes. Wavelengths for tsunamis (in 500-3000 m depth) are in the range 8.5 to over 200 km and on a shelf where the depth is about 50 m (as in the Great Barrier Reef) the wavelengths are in the range 2.5 - 30 km. It is shown that the phased array HF ocean surface radar being deployed in the Great Barrier Reef (GBR) and operating in a routine way for mapping surface currents, can resolve surface current squirts from tsunamis in the wave period range 20-30 minutes and in the wavelength range greater than about 6 km. There is a trade-off between resolution of surface current speed and time resolution. If the radar is actively managed with automatic intervention during a tsunami alert period (triggered from the global seismic network) then it is estimated that the time resolution of the GBR radar may be reduced to about 2 minutes, which corresponds to a capability to detect tsunamis at the shelf edge in the period range 5-30 minutes. It is estimated that the lower limit of squirt velocity detection at the shelf edge would correspond to a tsunami with water elevation of less than 5 cm in the open ocean. This means that the GBR HF radar is well-conditioned for use as a monitor of small and medium scale tsunamis, and has the potential to contribute to the understanding of tsunami genesis research.

• Journal of Korea Game Society
• /
• v.8 no.2
• /
• pp.85-96
• /
• 2008

Recently, research on augmented games as a new game genre has attracted a lot of attention. An augmented game overlaps virtual objects in an augmented reality(AR) environment, allowing game players to interact with the AR environment through manipulating real and virtual objects. However, it is difficult to release existing augmented games to ordinary game players, as the games generally use very expensive and inconvenient 'backpack' systems: To solve this problem, several augmented games have been proposed using mobile devices equipped with cameras, but it can be only enjoyed at a previously-installed location, as a ‘color marker' or 'pattern marker’ is used to overlap the virtual object with the real environment. Accordingly, this paper introduces an augmented game, called augmented galaga based on traditional well-known galaga, executed on mobile devices to make game players experience the game without any economic burdens. Augmented galaga uses real object in real environments, and uses scale-invariant features(SIFT), and Euclidean distance to recognize the real objects. The virtural aliens are randomly appeared around the specific objects, several specific objects are used to improve the interest aspect, andgame players attack the virtual aliens by moving the mobile devices towards specific objects and clicking a button of mobile devices. As a result, we expect that augmented galaga provides an exciting experience without any economic burdens for players based on the game paradigm, where the user interacts with both the physical world captured by a mobile camera and the virtual aliens automatically generated by a mobile devices.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.88-100
• /
• 1999

Detecting human face and facial landmarks automatically in an image is as essential step to a fully automatic face recognition system. In this paper, we present a new approach to detect automatically face and its eyes of input image with scale and rotation variations of faces by using an intensity based template matching with a single log-polar face template. In a template-based matching it is necessary to normalize the scale changes and rotations of an input image to a template ones. The log-polar mapping which simulates space-variant human visual system converts scale changes and rotations of input image into constant horizontal and cyclic vertical shifts in the output plane. Intelligent use of this property allows us to shift of the candidate log-polar faces mapped at various fixation points of an input image to be matched to a template over the log-polar plane. Thus, the proposed method eliminates the need of adapting multitemplate and multiresolution schemes, which inevitably give rise to intensive computation involved to cope with scale and rotation variations of faces. Through this scale and rotation involved to cope with scale and method can lead to detecting face and its eyes simultaneously. Experimental results on a database of 795 images show over 98% detection rate.

• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.42-52
• /
• 2017

Panorama image is a single image obtained by combining images taken at several viewpoints through matching of corresponding points. Existing panoramic image generation methods that find the corresponding points are extracting local invariant feature points in each image to create descriptors and using descriptor matching algorithm. In the case of video sequence, frames may be a lot, so therefore it may costs significant amount of time to generate a panoramic image by the existing method and it may has done unnecessary calculations. In this paper, we propose a method to quickly create a single panoramic image from a video sequence. By assuming that there is no significant changes between frames of the video such as in locally, we use the FAST algorithm that has good repeatability and high-speed calculation to extract feature points and the Lucas-Kanade algorithm as each feature point to track for find the corresponding points in surrounding neighborhood instead of existing descriptor matching algorithms. When homographies are calculated for all images, homography is changed around the center image of video sequence to warp images and obtain a planar panoramic image. Finally, the spherical panoramic image is obtained by performing inverse transformation of the spherical coordinate system. The proposed method was confirmed through the experiments generating panorama image efficiently and more faster than the existing methods.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2006.06a
• /
• pp.117-122
• /
• 2006

In the geophysical monitoring to understand the change of subsurface material properties with time, the time-invariant static subsurface model is commonly adopted to reconstruct a time-lapse image. This assumption of static model, however, can be invalid particularly when fluid migrates very quickly in highly permeable medium in the brine injection experiment. In such case, the resultant subsurface images may be severely distorted. In order to alleviate this problem, we develop a new least-squares inversion algorithm under the assumption that the subsurface model will change continuously in time. Instead of sampling a time-space model into numerous space models with a regular time interval, a few reference models in space domain at different times pre-selected are used to describe the subsurface structure continuously changing in time; the material property at a certain space coordinate are assumed to change linearly in time. Consequently, finding a space-time model can be simplified into obtaining several reference space models. In order to stabilize iterative inversion and to calculate meaningful subsurface images varying with time, the regularization along time axis is introduced assuming that the subsurface model will not change significantly during the data acquisition. The performance of the proposed algorithm is demonstrated by the numerical experiments using the synthetic data of crosshole dc resistivity tomography.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.83-93
• /
• 2013

Recently, the SURF algorithm, which is conjugated for object tracking system as part of many computer vision applications, is a well-known scale- and rotation-invariant feature detection algorithm. The SURF, due to its high computational complexity, there is essential to develop a hardware accelerator in order to be used on an IP in embedded environment. However, the SURF requires a huge local memory, causing many problems that increase the chip size and decrease the value of IP in ASIC and SoC system design. In this paper, we proposed a way to design a SURF algorithm in hardware with greatly reduced local memory by partitioning the algorithms into several Sub-IPs using external memory and a DMA. To justify validity of the proposed method, we developed an example of simplified object tracking algorithm. The execution speed of the hardware IP was about 31 frame/sec, the logic size was about 74Kgate in the 30nm technology with 81Kbytes local memory in the embedded system platform consisting of ARM Cortex-M0 processor, AMBA bus(AHB-lite and APB), DMA and a SDRAM controller. Hence, it can be used to the hardware IP of SoC Chip. If the image processing algorithm akin to SURF is applied to the method proposed in this paper, it is expected that it can implement an efficient hardware design for target application.