• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.505-516
• /
• 2000

Cellular Neural Networks(CNN) is a nonlinear information-processing system that has a locally connected characteristic and is widely used in the real-time high speed image processing. In this paper, a practical system approach of time-multiplexing CNN implementations suitable for processing large and complex images using small CNN arrays is presented and $6\times6$ CNN hardware is designed for the processing of a large image. While previous implementations are mostly suitable for black and white applications because of the thresholded outputs, our approach is especially suitable for applications in gray image processing due to the analog nature of the state node. CNN chip is designed using a 0.65${\mu}{\textrm}{m}$ 2P2M(double poly, double metal) N-Well CMOS process technology. It contains about 15,400 devices on an area of about $1.85\times1.75$ md. The designed $6\times6$ CNN is tested for the edge detection of a large image input and it's performance is verified.

• Journal of Korean Dental Science
• /
• v.13 no.1
• /
• pp.21-27
• /
• 2020

Purpose: The aim of this study was to investigate the types and frequency of the various incidental findings (IFs) on magnetic resonance images (MRI) taken from the patients with temporomandibular disorder (TMD) symptoms. Materials and Methods: Temporomandibular joint (TMJ) MRI taken from 1,013 patients with TMD symptoms were evaluated retrospectively. IF was defined as imaging features that were accidentally or unexpectedly found, rather than degenerative bony changes of TMJ complex or disc derangement. They were classified into two groups as TMJ site-specific findings and unexpected findings at other regions. The frequency of the sub groups was analyzed. Result: A total of 26 (2.57%) cases with IFs were classified into 13 cases with TMJ site-specific findings and 13 cases with unexpected findings at other region. TMJ site-specific findings included synovial chondromatosis in 6 cases, synovial cyst in 6 cases and osteochondroma in one case. Unexpected findings included salivary gland tumor in 3 cases, developmental cyst in 3 cases, vascular malformation in 2 cases, mastoiditis in 4 cases and sialadenitis on parotid gland in one case. Conclusion: When diagnosing TMD through TMJ MRI, clinicians should carefully read the image, considering the possibility of IFs because TMJ MRI can provide pathologic information in TMJ region and other oral and maxillofacial region.

• Journal of the Korean Society of Costume
• /
• v.64 no.6
• /
• pp.47-64
• /
• 2014

A variety of traditional costumes have been developed in Asia due to different natural and cultural environments and they are still worn by people in many areas. Traditional costumes in Asia have been formed under the influence of various ideologies, as well as technology and social structure. Three Asian religions(Buddhism, Hinduism and Islam), which have undeniably strong influence on traditional Asian cultures, have great effects on the styles of traditional costume in each region of Asia. The purpose of this study is to compare the characteristics and aesthetic values of traditional Asian costumes. To do this, the author used images of traditional costumes, which were taken in person by the author, in each region of Asia as reference. Unlike the traditional costumes in the West, which expose the body shape, traditional Asian costumes have nonstructural features in construction, form and wearing rules. They are also decorated with religious symbols and other ornaments, which is different from functional and non-decorative modern clothes. Each traditional Asian costume has unique characteristics. The costume under the influence of Buddhism shows the beauty of concealment that features trans-spatiality and abundant silhouette. On the other hand, the Hindu costume shows the beauty of symbolization represented by very colorful and complex ornaments, while costume in the Islam regions shows the beauty of restraint with clothes that wrap up the body in accordance with its strict religious discipline. Asian religions also represent philosophy, culture as well as an ethnic group. They have influenced entire Asian cultures including the arts, aesthetics and social structure and decided the style of costumes.

• Journal of the Korean Society of Radiology
• /
• v.6 no.4
• /
• pp.299-303
• /
• 2012

Shoulder MRArthrography was performed to get an accurate diagnosis about complex anatomical structure in shoulder joint. We carried out how the changes of anatomical rotations in shoulder joint could bring certain diagnosis effects on MRI images for various shoulder humerus positions; Neutral position, Internal rotation position and External rotation position. In addition, we prepared an aid tool in oder to maintain the right posture of a patient. This aid tool was made by adapting Modeling Design Program. By virtue of this aid, we obtained the following result. Shoulder MR Arthrography by the External rotation position for anatomical structure diagnosis was the most suitable in diagnostic evaluations of important anatomical structures in shoulder joint such as Biceps tendon, Supera-spiatus tendon, Sub-scapularis tendon, Labrum and Sub-acromial space.

• Journal of IKEEE
• /
• v.6 no.1 s.10
• /
• pp.72-79
• /
• 2002

This paper presents an efficient face detection algorithm for color images with a complex background. The presented algorithm utilizes the color information and eigenface that is calculated by PCA-LDA (Principle Component Analysis - Linear Discriminant Analysis). The method of using the color information is faster than any other methods. Eigenface includes average information of the whole test faces. Therefore eigenface can decide that the candidate region is a face. The whole process is composed of two steps. First, it finds first face candidates region of skin tone using a color information in image. We can get a size and position of face candidate region. Second, we compare first face candidate region with eigenface, so decide that an image whether include a face or not. The advantages of the proposed approach include that increasing the detection speed by deciding a size and position of first face candidates region. Also, Betting 97% of the detection rate by comparing the eigenfaces calculated in PCA-LDA.

• Journal of International Society for Simulation Surgery
• /
• v.4 no.1
• /
• pp.9-12
• /
• 2017

Purpose Surgery for separating craniopagus twins involves many critical issues owing to complex anatomical features. We demonstrate a 3D printed model and virtual reality (VR) technologies that could provide valuable benefits for surgical planning and simulation, which would improve the visualization and perception during craniopagus surgery. Material & Methods We printed a 3D model extracted from CT images of craniopagus patients using segmentation software developed in-house. Then, we imported the 3D model to create the VR environment using 3D simulation software (Unity, Unity Technologies, CA). We utilized the HTC Vive (HTC & Valve Corp) head-mount-display for the VR simulation. Results We obtained the 3D printed model of craniopagus patients and imported the model to a VR environment. Manipulating the model in VR was possible, and the 3D model in the VR environment enhanced the application of user-friendly 3D modeling in surgery for craniopagus twins. Conclusion The use of the 3D printed model and VR has helped understand complicated anatomical structures of craniopagus patients and has made communicating with other medical surgeons in the field much easier. Further, interacting with the 3D model is possible in VR, which enhances the understanding of the craniopagus surgery as well as the success rate of separation surgery while providing useful information on diagnosing and surgery planning.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.29 no.1 s.139
• /
• pp.23-34
• /
• 2005

The purpose of this study is to spread the public recognition for the style of Islamic dress has been ignorantly left and provide this as the basic data for Islamic fashion design. This treatise restricts the Islamic scope into the southeast Asia and confuted the study referring to Islam related books, treatise, domestic and foreign fashion magazines as well as newspaper articles, Internet and screen materials. The study results are as follows: Commonly Islam as a term of religious scope means complex cultural body based on Islam. 1. The Islamic social and cultural images were categorized as (1) conservative and sexual (2) simple, static, decorative and rhythmical (3) dark, violent, bright and amusing image. 2. Islamic nations' style of dress was characterized (1) surface decorative dress (2) practical outer garment (3) trousers style. 3. Both men and women basically put on trousers in children's stories and animations. In case of women, they wear skirts and according a social standing, tunic and caftan style jackets. As for men and women, Dey both wear turbans or chadors but in particular, wealthy classes put on a distinguishable turbans and chadors with splendid accessories. 4. The characteristics of Islamic fashion are lace decoration around a sleeve and the waist or blouse and harem pants with a elastic cord. In addition, they are splendid necklace and ring earings looking old, accessories with big pendants and dragging belts. These examples are shown in collections and streets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• Journal of Sensor Science and Technology
• /
• v.29 no.1
• /
• pp.59-62
• /
• 2020

Currently, increasing attention is being paid to relaxor-based ferroelectric single crystals in photoacoustic images, especially for high-end applications. Among the crystals are (1-x)Pb(Mg_1/3Nb_2/3)O₃-xPbTiO₃ (PMN-100xPT) single crystals located near their morphotropic phase boundary (x = 0.30-0.35) because of their ultrahigh piezoelectric and electromechanical coupling properties. The alternating current poling (ACP) treatment, rather than the conventional direct current poling treatment, has recently been spotlighted due to its effectiveness in enhancing the piezoelectric properties. So far, it has been suggested that the enhanced piezoelectricity originates from either a domain miniaturization to nanodomains or from an electric-field-induced monoclinic symmetry. In this study, we demonstrate by thermally stimulated depolarization current measurements that the effect of ACP is too complex to be explained using a single mechanism and that the proposed electric-field-induced monoclinic symmetry is unlikely to exist.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.6
• /
• pp.68-73
• /
• 2009

One of the traditional optical methods to monitor a tool is a CCD sensor-based vision system which captures an aspect of the tool in real time. In the case using the CCD sensor, specific lens-modules are necessary to monitor the tool with higher resolution than its pixel size, and a microprocessor is required to attain desired data from captured images. Thus theses additional devices make the entire measurement system complex. Another method is to use a pair of an optical source and a detector per measuring axis. Since the method is based on the intensity modulation, the structure of the measurement system is simper than the CCD sensor-based vision system. However, in the case measuring the three dimensional position of the tool, it is difficult to apply to micro machine-tools because there may not be space to integrate three pairs of an optical source and a detector. In this paper, in order to develop a tool-origin measurement system which is employed in micro machine-tools, the improved method to measure a tool origin in x, y and z axes is introduced. The method is based on the intensity modulation and employs one pair of an optical source radiating divergent beams and a quadrant photodiode to detect a three dimensional position of the tool. This paper presents the measurement models of the proposed tool-origin sensor. The models were verified experimentally The verification results show that the proposed method is possible and the induced models are available for design.