• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.4
• /
• pp.391-397
• /
• 2011

Conventional film radiographic test has been generally and widely used in the inspection on the weldment for quality assurance. On the other hand, since the analog RT is well known for typical time and cost consuming method with complex process of inspection, the industry has researched various ways how to improve radiographic test technology. In this study, we verified the fact that digital RT provides a lot more benefit in effectively detecting defects, ever film details, through digital processing of image enhancement, compared to film RT. As a result, we reached conclusion that digital RT is positively able to replace the film RT in industry in part or in whole.

• Journal of Sensor Science and Technology
• /
• v.7 no.5
• /
• pp.334-341
• /
• 1998

In this paper, we present a new interpolation scheme for image enhancement using nonlinear operator. In general, interpolation techniques are based on linear operators which are essentially lowpass filters, hence, they tend to blur fine details in the original image. In our approach, the operator itself balances the strength of its sharpening and noise suppressing components according to the properties of the input image data.

• The International Journal of Costume Culture
• /
• v.7 no.1
• /
• pp.1-16
• /
• 2004

Pop art, an artistic trend which was actively popular centering around popularization of America in the 1960's, appears as punk style in the 1970's and as one of diversified style in the 1980's, and have co-existed in the third culture and pluralistic combination since the 1990's. The image of pop art includes complexity, familiarity and popularity as well as extension of media, and so directly influences the fashion in the end of the 20th century. Especially, sportslook show up by the virtue of rising lower cultural area such as street fashion becoming influential and change in life style, which was recreated as clothes by developing characteristics of design including style, details and colors showed in active sports wear. This study is aimed to ana analyze the image of pop art showed again in the modern fashion in the end of the 20th century and graffiti-art which was well known to the general public after the 1980's. Through this analysis, I will study characteristics of pop art showed in sportslook which is the mainstream in modern fashion and graffiti of Keith Haring. Consequently, I suggested a functional, esthetic and future-oriented sports look design which comprises the image of the graffiti-art of Keith Haring by using Design CAD(photoshop & primavision) enabling to attempt variously and to derive quickly the output of design and textile.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.10
• /
• pp.468-476
• /
• 2002

Digital images are easily corrupted by noise during the data transmission, data capture and data processing. A technical method of noise analyzing and adaptive filtering for reducing of quantum noise in medical radio-fluoroscopy images is presented. By adjusting the characteristics of the filter according to local statistics around each pixel of the image as moving windowing, it is possible to suppress noise sufficiently while preserve edge and other significant information required in diagnosis. We proposed adaptive weighed median(AWM) filters based on local statistics. We showed two ways of realizing the AWM filters. One is a simple type of AWM filter, which is constructed by Homogeneous factor(HF). Homogeneous factor(HF) from the noise models that enables the filter to recognize the local structures of the image is introduced, and an algorithm for determining the HF fitted to the diagnostic systems with various inner statistical properties is proposed. We show by the experimented that the performances of proposed method is superior to these of other filters and models in preserving small details and suppressing the noise at homogeneous region. The proposed algorithms were implemented by Visual C++ language on a IBM-PC Pentium 550 for testing purposes and the effects and results of the filter in the various levels of noise and images were proposed by comparing the values of NMSE(normalized mean square error) with the value of the other existing filtering methods.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.871-886
• /
• 2011

This paper proposes a powerful SVM-ASM filter, the adaptive switching median(ASM) filter based on support vector machines(SVMs), to effectively reduce impulse noise in corrupted images while preserving image details and features. The proposed SVM-ASM filter is composed of two stages: SVM impulse detection and ASM filtering. SVM impulse detection determines whether the pixels are corrupted by noise or not according to an optimal discrimination function. ASM filtering implements the image filtering with a variable window size to effectively remove the noisy pixels determined by the SVM impulse detection. Experimental results show that the SVM-ASM filter performs significantly better than many other existing filters for denoising impulse noise even in highly corrupted images with regard to noise suppression and detail preservation. The SVM-ASM filter is also extremely robust with respect to various test images and various percentages of image noise.

• Applied Microscopy
• /
• v.46 no.2
• /
• pp.93-99
• /
• 2016

The thickness of specimen is an important factor in microscopic researches. Thicker specimen contains more information, but it is difficult to obtain well focused image with precise details due to optical limit of conventional microscope. Recently, a microscope unit that combines improved illumination system, which allows real time three-dimensional (3D) image and automatic z-stack merging software. In this research, we evaluated the usefulness of this unit in observing thick samples; Golgi stained nervous tissue and ground prepared bone, tooth, and non-transparent small sample; zebra fish teeth. Well focused image in thick samples was obtained by processing z-stack images with Panfocal software. A clear feature of neuronal dendrite branching pattern could be taken. 3D features were clearly observed by oblique illumination. Furthermore, 3D array and shape of zebra fish teeth was clearly distinguished. A novel combination of two channel oblique illumination and z-stack imaging process increased depth of field and optimized contrast, which has a potential to be further applied in the field of neuroscience, hard tissue biology, and analysis of small organic structures such as ear ossicles and zebra fish teeth.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.10
• /
• pp.1014-1022
• /
• 2014

In mechatronic systems using electric signals to drive control systems, driving signals including the frequency band of the unwanted signals, such as resonant frequencies and noise frequencies, can affect the accuracy of the controlled system and can cause serious damage to the system due to the resonance phenomenon of the mechatronic system. An LOS (Line of Sight) control unit is used to automatically rotate the gimbal system with a video imaging system generally mounted on modern aerial vehicles. However, it still suffers from natural frequency variation problems due to variations of operational temperature. To prevent degradation in performance, this paper proposes an adaptive filtering technique based on real-time noise analysis and adaptive notch-filtering for LOS control systems, and verifies how our proposed method maintains the LOS stabilization performance. Additionally, this filtering technique can be applied to the image noise filtering of the video imaging system. It is designed to reduce image noises generated by switching circuits or power sources. The details of design procedures of the proposed filtering technique and the experiments for the performance verification are described in this paper.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1183-1202
• /
• 2017

Image restoration has been carried out by texture synthesis mostly for large regions and inpainting algorithms for small cracks in images. In this paper, we propose a new approach that allows for the simultaneous fill-in of different structures and textures by processing in a wavelet domain. A combination of structure inpainting and patch-based texture synthesis is carried out, which is known as patch-based inpainting, for filling and updating the target region. The wavelet transform is used for its very good multiresolution capabilities. The proposed algorithm uses the wavelet domain subbands to resolve the structure and texture components in smooth approximation and high frequency structural details. The subbands are processed separately by the prioritized patch-based inpainting with isophote energy driven texture synthesis at the core. The algorithm automatically estimates the wavelet coefficients of the target regions of various subbands using optimized patches from the surrounding DWT coefficients. The suggested performance improvement drastically improves execution speed over the existing algorithm. The proposed patch optimization strategy improves the quality of the fill. The fill-in is done with higher priority to structures and isophotes arriving at target boundaries. The effectiveness of the algorithm is demonstrated with natural and textured images with varying textural complexions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.