• Journal of radiological science and technology
• /
• v.41 no.1
• /
• pp.7-12
• /
• 2018

Patients who visit the emergency room with urinary stones have difficulty lying down in a supine position due to severe pain when performing the KUB test. The purpose of this study was to find methods to reduce the patients' pain and image distortion, and obtain medical images with high diagnostic values. After checking the standard classification of disease and cause of death, the target group consisted of 121 patients who had clearly distinguished stones from computed tomography. Patients with stones in the ureteralvesical junction were excluded. Qualitative image evaluation was performed by confirming the location of the stone in the computed tomography images. and evaluated the rate of visual discrimination of stones possible through KUB and abdominal plain X-ray. Quantitative image evaluation was performed on the KUB, abdominal plain X-ray images. The transverse process of the first lumbar vertebrae served as the standard point, and the length from this point to the lower part of the stone was measured. Results from looking at the rate of visual discrimination of stones possible through KUB and abdominal plain X-ray showed: 94 patients (77.6%) for KUB images and 91 patients (75.2%) for computed tomography images. The standard deviation for KUB and abdominal X-ray was 3 (2.4%). Comparing and analyzing the location from KUB images and abdominal plain X-ray images, the stone position was 10.1 mm in the kidney, 10.5 mm in the ureteropelvic junction, and 9.7 mm in the ureters. It was shown that the stone moved 10 mm on average with significant statistical difference (P<0.05). In cases where the pain is so severe that it is impossible to perform the test in the supine position, an alternative may be to check the stone position by performing a modified KUB test by having the patient stand in a vertical position. In the future, this will provide convenience to both the examiner and the patient when performing the examination, and it will contribute with its reproducibility.

• Journal of Biosystems Engineering
• /
• v.36 no.6
• /
• pp.484-490
• /
• 2011

Defects exist underneath the fruit skin are not easily discernable by using conventional color imaging technique in the visible wavelength ranges. Development of sensitive detection methods for the defects is necessary to ensure accurate quality sorting of fruits. Hyperspectral imaging techniques, which combine the features of image and spectroscopy to acquire spatial and spectral information simultaneously, have demonstrated good potentials for identifying and detecting anomalies on biological substances. In this study, a high spatial resolution hyperspectral reflectance technique was presented as a tool for detecting bruises on apple. The two-band ratio (494 nm / 952 nm) and simple threshold methods were applied to investigate the feasibility of discriminating the bruises from sound tissue of apple. The pixel wise accuracy of the discrimination was 74%. The resultant images processed with selected wavebands and morphologic algorithm distinctively showed the early stages of bruises on apple which were not discernable by naked eyes as well as a conventional color camera. Results demonstrated good potential of the hyperspectral reflectance imaging for detection of bruises on apple.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.173-188
• /
• 2013

In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.37
• /
• pp.127-136
• /
• 1996

Due to the development of technology, urbanization, industrialization, etd. at modern times, even the individual view of value has changed in variety. That means the change of each consumcer's life-style and even that of propensity to consume. In that regard, the modern, commercial space became to be increasingly included to specialization and complication. Such specialization and complication of the commercial space can be thought to be a positive response of enterprises to satisfy the needs or desire of consumers who become diversified. In this study, some new models in the method of the planning and designing of the S.I.P(Shop Identity Program). intended to research into as follows ; - As the background of the advent of the multi-used shopping complex, changes in consumer life-style and propensity to consume according to social and economical changes were intended to be studied through various statistical data literature. - For the study of the characteristics, constituent conditions, and planning operation of the future multi used shopping complex in the marketing aspect of enterprises, it was intended to study centered on the theory of consumer behavior and that of retail marketing. - In the process of the spatial design of the multi-used shopping complex, it was tried that a designing process to materialize a target of the discrimination and orderly arrangement of stores be progressed. In the process of materializing a target based on both corporate image and 'brand' image in designing.

• Journal of Welding and Joining
• /
• v.12 no.3
• /
• pp.109-117
• /
• 1994

Spot welding has wide used with a high work efficiency in the automotive and aerospace industries. Up to the present, the technique mainly used to test spot welds on production lines has been entirely depended upon destructive chisel or peel testing. Therefore, it's being very important assignment to secure the NDE technique which can be evaluate spot weld quality with more efficiency and high reliability. This paper discusses the feasibility of UNDE techniques to evaluate spot weld quality. For the sake of the approach to the quantitative measurement of nugget diameter and the discrimination of a the corona bond from nugget, ultrasonic c-scan image and distribution of reflective echo amplitude was measured by immersion method with the mechanical and the electronic scanning of point-focussed ultrasonic beam(25 MHz). As the results of this study, corona bond which is the most dangerous types of interface defects can be successfully detected, as well as expulsion and voids. Ultrasonic testing results were confirmed and compared by optical microscope and SAM(Scanning Acoustic Microscope) observation of the spot-weld cross section. The results show that the nugget diameter can be successfully measured with the accuracy of 0.8 mm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1111-1116
• /
• 2009

In this paper, we discuss distortion-tolerant pattern recognition using computational integral imaging reconstruction. Three-dimensional object information is captured by the integral imaging pick-up process. The captured information is numerically reconstructed at arbitrary depth-levels by averaging the corresponding pixels. We apply Fisher linear discriminant analysis combined with principal component analysis to computationally reconstructed images for the distortion-tolerant recognition. Fisher linear discriminant analysis maximizes the discrimination capability between classes and principal component analysis reduces the dimensionality with the minimum mean squared errors between the original and the restored images. The presented methods provide the promising results for the classification of out-of-plane rotated objects.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.257-262
• /
• 2008

컴퓨팅 기술의 발전에 따라 선박의 안전항해를 지원하기 위해 Radar, GPS 등 다양한 장비들이 계량, 개발되고 있으며 그들은 선박 항해에 필요한 많은 정보를 제공하고 있다. 하지만 여전히 선박 충돌사고는 끊이지 않고 있으며, 선박 대형화에 힘입어 그 피해도 커지고 있는 실정이다. 이러한 선박 충돌사고는 앞에서 언급한 선박 항해 안전 장비의 성능제약을 받는 야간이나, 해상 환경 악화 시 두드러지게 발생하고 있으며, 특히 제한적인 상황에서 인간의 눈에만 의지해서 항해를 하고 있기 때문이기도 하다. 그래서 이러한 상황에서 Vision기술을 사용하여 카메라를 활용 상대선박을 자동으로 식별하는 시스템을 제안하고자 한다. 이는 선박들이 법적으로 야간이나 각종 장비들이 제한을 받는 상황에서 근처의 다른 선박에게 상황을 전달하기 위해서 등화(불빛)와 형상물을 사용해야한다는 점에서 착안하였다. 제안 시스템을 실제 해상 환경에서 실험하기에 제한점이 많아 프로토타입을 구현하여 실험실 환경에서 실험하고 사용자 평가를 실시하였다. 즉, LED를 가상 등화로 하여 선박에 설치된 것과 동일한 색상과 동일한 위치에 배치하고 이를 카메라를 활용하여 인식 실험을 하였으며 약 90%의 인식률을 보였다. 그리고 이러한 실험화면을 활용하여 항해업무 종사자 15명을 대상으로 사용자 평가를 실시하였으며 대부분의 사람들이 제안된 체계가 해상에서 유용하다고 답변하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.2
• /
• pp.16-22
• /
• 2001

In this paper we mose a new scheme for recognition of deformed letters by extracting feature vectors based on Gibbs distributions which are well suited for representing the spatial continuity. The extracted feature vectors are comprised of 2-D conditional moments which are invariant under translation, rotation, and scale of an image. The Algorithm for pattern recognition of deformed letters contains two parts: the extraction of feature vector and the recognition process. (i) We extract feature vector which consists of an improved 2-D conditional moments on the basis of estimated conditional Gibbs distribution for an image. (ii) In the recognition phase, the minimization of the discrimination cost function for a deformed letters determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, recognition experiments with a generated document was conducted. on Workstation. Experiment results reveal that the proposed scheme has high recognition rate over 96%.

• Korean Journal of Remote Sensing
• /
• v.20 no.3
• /
• pp.197-205
• /
• 2004

Wetlands are lands with a mixture of water, herbaceous or woody vegetation and wet soil. And linear spectral mixture analysis (LSMA) is one of the most often used methods in handling the spectral mixture problem. This study aims to test LSMA is an enhanced routine for classification of wetland land-covers in Paldang reservoir and vicinity (paldang Reservoir) using Landsat TM and ETM+ imagery. In the LSMA process, reference endmembers were driven from scatter-plots of Landsat bands 3, 4 and 5, and a series of endmember models were developed based on green vegetation (GV), soil and water endmembers which are the main indicators of wetlands. To consider phenological characteristics of Paldang Reservoir, a soil endmember was subdivided into bright and dark soil endmembers in spring and a green vegetation (GV) endmember was subdivided into GV tree and GV herbaceous endmembers in fall. We found that LSMA fractions improved the classification accuracy of the wetland land-cover. Four endmember models provided better GV and soil discrimination and the root mean squared (RMS) errors were 0.011 and 0.0039, in spring and fall respectively. Phenologically, a fall image is more appropriate to classify wetland land-cover than spring's. The classification result using 4 endmember fractions of a fall image reached 85.2 and 74.2 percent of the producer's and user's accuracy respectively. This study shows that this routine will be an useful tool for identifying and monitoring the status of wetlands in Paldang Reservoir.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.