• International Journal of Contents
• /
• v.10 no.4
• /
• pp.1-10
• /
• 2014

In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.

• Journal of the Korean Chemical Society
• /
• v.59 no.3
• /
• pp.215-224
• /
• 2015

Unsymmetrical tetradentate Schiff base N-(2-hydroxy-5-methylacetophenone)-N'-(2-hydroxy acetophenone) ethylene diamine (H₂L) and its complexes with Cr(III), Mn(II), Fe(III), Co(II), Ni(II) and Cu(II) have been synthesized and characterized by elemental analyses, magnetic susceptibility measurements, IR, electronic spectra and thermogravimetric analyses. ¹H, ¹³C-NMR and FAB Mass spectra of ligand clearly indicate the presence of OH and azomethine groups. Elemental analyses of the complexes indicate that the metal to ligand ratio is 1:1 in all complexes. Infrared spectra of complexes indicate a dibasic quadridentate nature of the ligand and its coordination to metal ions through phenolic oxygen and azomethine nitrogen atoms. The thermal behavior of these complexes showed the loss of lattice water in the first step followed by decomposition of the ligand in subsequent steps. The thermal data have also been analyzed for the kinetic parameters by using Horowitz-Metzger method. The dependence of the electrical conductivity on the temperature has been studied over the temperature range 313-403 K and the complexes are found to show semiconducting behavior. XRD and SEM images of some representative complexes have been recorded. The antimicrobial activity of the ligand and its complexes has been screened against various microorganisms and all of them were found to be active against the test organisms. The Fe(III) and Ni(II) complex have been tested for the catalytic oxidation of styrene.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.872-877
• /
• 2012

We proposes the method to detect the Hangul character region from natural image using topological structural feature of Hangul grapheme. First, we transform a natural image to a gray-scale image. Second, feature extraction performed with edge and connected component based method, Edge-based method use a Canny-edge detector and connected component based method applied the local range filtering. Next, if features are not corresponding to the heuristic rule of Hangul character, extracted features filtered out and select candidates of character region. Next, candidates of Hangul character region are merged into one Hangul character using Hangul character merging algorithm. Finally, we detect the final character region by Hangul character class decision algorithm. Experimental result, proposed method could detect a character region effectively in images that contains a complex background and various environments. As a result of the performance evaluation, A proposed method showed advanced results about detection of Hangul character region from mobile image.

• Fashion & Textile Research Journal
• /
• v.14 no.4
• /
• pp.519-531
• /
• 2012

This study comprehends the various expressions of Lady Gaga's fashion style based on Craig Owens's Allegory theory. This study analyzed four application elements of Borrow, Site Specificity, Accumulate of Strategy, and Hybridization in addition, it studied all aspects of the aesthetic value of Lady GaGa (an influential popular culture icon). It was classified in the external representation of the fashion style for the aesthetic value. The results are summarized as follows: First, 'Borrow' of the singers of the 80's music and fashion style present from her elders and visual homage to shock artists. It influenced her fans with a difference in viewpoint for a star's fashion that subsequently resulted in a deformation of form, playful kitsch style, and mixed gender. Second, 'Site specificity' presents an extreme make over through an intentional and grotesques fashion style to extend physical territory and defenseless. The results remove stereotypes and reveal deconstructive performances. Third, 'Accumulate of strategy' simultaneously presents voluptuous beauty, futurism, and avant-garde style. This shows the countercultural tendency through the random repetition of fashion images and layerd coordination. Finally, 'Hybridization' presents multiful fashion style through a collaboration with world-famous designers and cosmetic brands. She expressed a diverse and complex fashion style composed of an art form that combines a high-tech cyborg image. The aesthetic values of Lady Gaga' fashion style are 'ambivalence virtuality', 'Transcendental mixed gender', 'plural textuality', and 'unexpected play culture'.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.spc8
• /
• pp.2981-2987
• /
• 2011

A comparative study of the photodynamic and antioxidant activities of methyl pheophorbide-a (MPa, 1) and its transition metal(II) complexes (2-5) is described. Four transition metal complexes (palladium(II): 2, zinc(II): 3, cobalt(II): 4 and copper(II): 5) of MPa were prepared by reaction between the corresponding transition metal and 1, respectively, and were characterized by $^1H$-NMR and UV-vis spectroscopic and mass spectrometric analyses. In vitro results show a photodynamic therapy (PDT) efficacy with A549 cells might be attributed to a heavy atom effect of the transition metal complexes of MPa. Among them, 4 and 5 showed higher photodynamic activity than that of 1 at the concentration of 5 ${\mu}M$ at 24 h incubation after photoirradiation. The images of morphological change for 2-5 show evidence for the PDT effect with A549 cells. And the all transition metal complexes of MPa showed higher antioxidant activity than that of MPa, in which 4 showed the highest antioxidant activity.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.6
• /
• pp.22-34
• /
• 2010

Existing image scalers generally adopt simple interpolation methods such as bilinear method to take cost-benefit, or highly complex architectures to achieve high quality resulting images. However, demands for a low power, low cost, and high performance image scaler become more important because of emerging high quality mobile contents. In this paper we propose the novel low power hardware architecture for a high quality raster scan image scaler. The proposed scaler architecture enhances the existing cubic interpolation look-up table architecture by reducing and optimizing memory access and hardware components. The input data buffer of existing image scaler is replaced with line memories to reduce the number of memory access that is critical to power consumption. The cubic interpolation formula used in existing look-up table architecture is also rearranged to reduce the number of the multipliers and look-up table size. Finally we analyze the optimized parameter sets of look-up table, which is a trade-off between quality of result image and hardware size.

• Journal of architectural history
• /
• v.20 no.6
• /
• pp.77-98
• /
• 2011

The aim of this study is to identify the floor plan types of folk houses or traditional vernacular dwellings found in Nagan Folk Village located in Joellanamdo province. Examining the floor plans appeared among 36 vernacular folk houses presumably built in the 19th century in the village by means of the changes in the number of bays of Anche, the mail block of the house, the study was also able to construct a spatial compositional process of floor plan development. The floor plan examination revealed that the basic floor plan type in Nagan folk housing was '一' shape, a typical southern dwelling based on the existing classification. This basic type is consisted of three bays or rooms: Jeongji (kitchen), Anbang (large room), and Jageunbang (small room). New spaces or rooms are added to this three room house to expand the house as the residential functions become more complex, such as more living and storage spaces. The expansion appears to have two direction. On the one hand, it has been taken place by inserting Marea, an open wooden floor living space between Anbang and Jageunbang to meet the extended living demand. On the other, Jeongjibang, a second kitchen/storage has been attached to Jeongji outward for extra cooking and storage. This two-way expansion shows the trend of symmetric expansion between cooking, storing space and dwelling space. It can be implied that the arrangement of house rooms has been structurally formulated and shared by the farmer-builders in the 19th century in Nagan village who appeared to be influenced by fixed images for housing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.227-232
• /
• 2018

In a Hough transform that is a representative algorithm for the straight line detection, a great number of edge pixels generated from noisy or complex images cause enormous amount of computation and pseudo straight lines. This paper proposes a two step straight line detection algorithm to improve the conventional Hough transform. In the first step, the proposed algorithm divides an image into non-overlapping blocks and detects the information related to the straight line of the edge pixels in the block using a principal component analysis (PCA). In the second step, it detects the straight lines by performing the Hough transform limited slope area to the pixels associated with the straight line. Simulation results show that the proposed algorithm reduces average of ${\rho}$ computation by 94.6% and prevents the pseudo straight lines although some additional computation is needed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.1
• /
• pp.41-48
• /
• 2009

This Paper introduces representation and coding schemes of multiview texture and depth data for complex three-dimensional scenes. We represent input color and depth images using compressed texture and depth map pairs. The proposed X-codec encodes them further to increase compression ratio in a near-lossless way. Our system resolves two problems. First, rendering time and output visual quality depend on input image resolutions rather than scene complexity since a depth image-based rendering techniques is used. Second, the random access problem of conventional image-based rendering could be effectively solved using our image block-based compression schemes. From experimental results, the proposed approach is useful to graphics applications because it provides multiview rendering, selective decoding, and scene manipulation functionalities.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.509-517
• /
• 2001

Full-search algorithm requires large amount of computation which causes time delay or very complex hardware architecture for real time implementation. In this paper, we propose a fast motion estimator based on bit-plane matching, which reduce the computational complexity and the hardware cost. In the proposed motion estimator, the conventional motion estimation algorithms are applied to the binary images directly extracted from the video sequence. Furthermore, in the proposed VLSI motion estimator, we employ a Pair of processing cores that calculate the motion vector continuously By controlling the data flow in a systolic fashion using the internal shift registers in the processing cores, we avoid using SRAM (local memory) so that we remove the time overhead for accessing the local memory and adopt lower-cost fabrication technology. We modeled and tested the proposed motion estimator in VHDL, and then synthesized the whole system which has been integrated in a 0.6-$\mu$m triple-metal CMOS chip of size 8.15 X 10.84$\textrm{mm}^2$.