• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.4
• /
• pp.1-10
• /
• 2000

The error diffusion technique is frequently utilized for the digital Imaging output devices to convert continuous level Image into bi-level Image It Yields the binary image with the high frequency emphasis that gives a pleasing perception to human eyes But, due to the non-homogeneous distribution of dots, It exhibits undesirable patterns that degenerate the perceived quality Various techniques have been proposed to Improve the Image quality by the error diffusion techniques In this paper, the cause of non-homogeneity of dot distribution is analyzed first. A threshold modulation technique that employs a simple sinusoidal function is proposed in this paper The proposed method achieves the homogeneous dot distribution by forcing the minor pixels on the binary Image to maintain the principal distance defined according to their gray levels. It also minimizes the void and clusters of minor pixels.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.2
• /
• pp.50-59
• /
• 2000

Stereo vision is a technique extracting depth information from stereo images, which are two images that view an object or a scene from different locations. The most important procedure in stereo vision, which is called stereo matching, is to find the same points in stereo images. It is difficult to match stereo images in real time because stereo matching requires heavy calculation. In this Paper we design a digital VLSI to Process stereo matching in real time, which we call stereo image match processor (SIMP). For implementation of real time stereo matching, sliding memory and minimum selection tree are presented. SIMP is designed with pipeline architecture and parallel processing. SIMP takes 64 gray level 64$\times$64 stereo images and yields 8 level 64 $\times$64 disparity map by 3 bit disparity and 12 bit address outputs. SIMP can process stereo images with process speed of 240 frames/sec.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.1
• /
• pp.77-82
• /
• 2004

In this paper we present a barcode reader to decode two-dimensional symbology PDF417 and propose a novel method to extract the bar-space Patterns directly from the gray-level barcode image, which employs the location and the distance between extreme points of each row or column of the barcode image. This algerian proves to be very robust from the high convolutional distortion environments such as defocussing and warping, even under badly illuminating condition. If the scanned barcode image is a result of the convolution of a Gaussian-shaped point spread function with a hi-level image, popular image segmentation methods such as image thresholding can not distinguish between very narrow bar-space patterns. The Proposed algorithm shows improved Performance over current barcode readers.

• Journal of Mechanical Science and Technology
• /
• v.15 no.7
• /
• pp.1041-1050
• /
• 2001

Control of bone cement volume (PMMA) may be critical for preventing complications in vertebroplasty, the percutaneous injection of PMMA into vertebra. The purpose of this study was to predict the optimal volume of PMMA injection based on CT images. For this, correlation between PMMA volume and textural features of CT images was examined before and after surgery to evaluate the appropriate PMMA amount. The gray level run length analysis was used to determine the textural features of the trabecular bone. Extimation of PMMA volume was done using 3D visualization with semi-automatic segmentation on postoperative CT images. Then, finite element (FE) models were constructed based on the CT image data of patients and PMMA volume. Appropriate material properties for the trabecular bone were assigned by converting BMD to elastic modulus. Structural reinforcement due to the changes in PMMA volume and BMD was assessed in terms of axial displacement of the superior endplate. A strong correlation was found between the injected PMMA volume and the area of the intertrabecular space and that of trabecular bone calculated from the CT images (r=0.90 and -0.90, respectively). FE results suggested that vertebroplasty could effectively reinforce the osteoporotic vertebra regardless of BMD or PMMA volume. Effectiveness of additional PMMA injection tended to decrease. For patients with BMD well lower than 50mg/ml, injection of up to 30% volume of the vertebral body is recommended. However, less than 30% is recommended otherwise to avoid any complications from excessive PMMA because the strength has already reached the normal level.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.14-20
• /
• 2003

This paper presents a text extraction method of camera based document image. It is more difficult to recognize camera based document image in comparison with scanner based image because of segmentation problem due to variable lighting condition and versatile fonts. Both document binarization and character extraction are important processes to recognize camera based document image. After converting color image into grey level image, gray level normalization is used to extract character region independent of lighting condition and background image. Local adaptive binarization method is then used to extract character from the background after the removal of noise. In this character extraction step, the information of the horizontal and vertical projection and the connected components is used to extract character line, word region and character region. To evaluate the proposed method, we have experimented with documents mixed Hangul, English, symbols and digits of the ETRI database. An encouraging binarization and character extraction results have been obtained.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.737-744
• /
• 2005

In this paper, we propose a three-level color clustering algerian for the binarization of text regions extracted from natural scene images. The proposed algorithm consists of three phases of color segmentation. First, the ordinary images in which the texts are well separated from the background, are binarized. Then, in the second phase, the input image is passed through a high pass filter to deal with those affected by natural or artificial light. Finally, the image Is passed through a low pass filter to deal with the texture in texts and/or background. We have shown that the proposed algorithm is more effective used gray-information binarization algorithm. To evaluate the effectiveness of the proposed algorithm we use a commercial OCR software ARMI 6.0 to observe the recognition accuracies on the binarized images. The experimental results on word and character recognition show that the proposed approach is more accurate than conventional methods by over $35\%$.

• Journal of KIISE:Software and Applications
• /
• v.34 no.11
• /
• pp.991-1000
• /
• 2007

A new robust approach to detect vehicles in a single frame of traffic scenes is presented. The method is based on the multi-level shadow classification, which has been shown to have the capability of extracting correct shadow shapes regardless of the operating conditions. The rationale of this classification is supported by the fact that shadow regions underneath vehicles usually exhibit darker gray level regardless of the vehicle brightness and illuminating conditions. Classified shadows provide string clues on the presence of vehicles. Unlike other schemes, neither background nor temporal information is utilized; thereby the performance is robust to the abrupt change of weather and the traffic congestion. By a simple evidential reasoning, the shadow evidences are combined with bright evidences to locate correct position of vehicles. Experimental results show the missing rate ranges form 0.9% to 7.2%, while the false alarm rate is below 4% for six traffic scenes sets under different operating conditions. The processing speed for more than 70 frames per second could be obtained for nominal image size, which makes the real-time implementation of measuring the traffic parameters possible.

• Current Optics and Photonics
• /
• v.3 no.2
• /
• pp.119-127
• /
• 2019

A new secret-key-sharing cryptosystem using optical phase-shifting digital holography is proposed. The proposed secret-key-sharing algorithm is based on the Diffie-Hellman key-exchange protocol, which is modified to an optical cipher system implemented by a two-step quadrature phase-shifting digital holographic encryption method using orthogonal polarization. Two unknown users' private keys are encrypted by two-step phase-shifting digital holography and are changed into three digital-hologram ciphers, which are stored by computer and are opened to a public communication network for secret-key-sharing. Two-step phase-shifting digital holograms are acquired by applying a phase step of 0 or ${\pi}/2$ in the reference beam's path. The encrypted digital hologram in the optical setup is a Fourier-transform hologram, and is recorded on CCDs with 256 quantized gray-level intensities. The digital hologram shows an analog-type noise-like randomized cipher with a two-dimensional array, which has a stronger security level than conventional electronic cryptography, due to the complexity of optical encryption, and protects against the possibility of a replay attack. Decryption with three encrypted digital holograms generates the same shared secret key for each user. Schematically, the proposed optical configuration has the advantage of producing a kind of double-key encryption, which can enhance security strength compared to the conventional Diffie-Hellman key-exchange protocol. Another advantage of the proposed secret-key-sharing cryptosystem is that it is free to change each user's private key in generating the public keys at any time. The proposed method is very effective cryptography when applied to a secret-key-exchange cryptosystem with high security strength.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.99-112
• /
• 2019

Cracks on pavement surfaces are critical signs and symptoms of the degradation of pavement structures. Image-based pavement crack detection is a challenging problem due to the intensity inhomogeneity, topology complexity, low contrast, and noisy texture background. In this paper, we address the problem of pavement crack detection and segmentation at pixel-level based on a Deep Neural Network (DNN) using gray-scale images. We propose a novel DNN architecture which contains a modified U-net network and a high-level features network. An important contribution of this work is the combination of these networks afforded through the fusion layer. To the best of our knowledge, this is the first paper introducing this combination for pavement crack segmentation and detection problem. The system performance of crack detection and segmentation is enhanced dramatically by using our novel architecture. We thoroughly implement and evaluate our proposed system on two open data sets: the Crack Forest Dataset (CFD) and the AigleRN dataset. Experimental results demonstrate that our system outperforms eight state-of-the-art methods on the same data sets.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.26 no.1
• /
• pp.88-97
• /
• 2012

DSOM(Diagnosis System of Oriental Medicine), questionnaire for oriental medical(medicine) diagnosis is an online survey system containing 152 questions for female, 149 questions for male that asking the basic symtoms of 16 pathogenic factors(病機). The result of DSOM denotes reliability according to the level of major symptoms of each pathogenic factor. Standard level of reliability is equal to all 16 pathogenic factor basically except phlegm(痰). In case of phlegm(痰) we give different weight depending on whether the factor includes gray color under the orbit(痰飮氣) or not. To examine reliability of DSOM, statistical analysis has been done to the data of felmale 10101, male 1564 except for bad responses and stored between 1st April 2000 to 3rd June 2011. Based on the study, the conclusions were as follows. Reliability of DSOM. For female, all pathogenic factors showed over 85% confidence level except for phlegm 82.6%. For male, all pathogenic factors showed more than 90% confidence level except two factors, phlegm(痰) indicates 87.% and damp(濕) indicates 89.8%. HH rates among pathogenic factors were more than 50 points. For female, HH rates of other 14 pathogenic factors were all over 80% except for heat(熱) 78.2% and insufficiency of Yang(陽虛) 75.3%. For male HH rates of all pathogenic factors were more than 80% except HH rates of heat 78.2% and damp 77.8%. Research based on a degree of satisfaction of reliability derived from pathogenic factors with scores of HH results in for all 16 pathogenic factors showed over 85% of relatively high level of satisfaction for both sexes whose reliability standard come under 5~4 points. Comparing appearance frequency of pathogenic factors for both sexes. Male only displays higer than female in heat(熱). Whereas female were higher than male for other 15 pathogenic factors and the difference was biggest in heart(心) and least in insufficiency of Yin(陰虛). Comparing appearance frequency order of pathogenic factors for both sexes. Female outdistanced male in blood stasis(血瘀) coldness(寒) blood-deficiency(血虛) phlegm(痰), while male outdistance female in heat(熱) insufficiency of Yin(陰虛) deficiency of qi(氣虛). Male had lower average of each pathogenic factors than female except heat(熱) as well as deficiency of qi(氣虛).