• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.11a
• /
• pp.384-387
• /
• 2003

In this paper, the evaluation of image quality was performed for digital radiography which is developing in using amorphous selenium as a photoconductor material for the purpose of offering basic research data and measurement technique about Medical Imaging Quality. So Modulation Transfer Function as a main factor of imaging quality evaluation was investigated by slit method. For measurement of MTF, Nuclear associates. 07-624 Slit camera image was obtained to study the variation of MTF corresponding to changing spatial frequency. And Presampling MTF was estimated by slit camera image with $10\;{\mu}m$ width at Digital Radiography. In this study, the obtained data demonstrates that the clinical value of a direct conversion type digital radiation detector using the amorphous selenium, which is being developed by domestic technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.86-89
• /
• 2015

Quantitative Evaluation of Image Quality using Automatic Exposure Control This it leads, the relationship of control and image between of photographing condition, DR proper use method proposing. Chest phantom acquires Chest PA images which it follows in conditional change, Image evaluation factor (SNR (Signal to Noise Ratio), CNR (Contrast to Noise Ratio), PSNR (Peak Signal to Ratio), RMS (Root Mean Square)). It excepted RMS price, SNR, CNR, PSNR the case which uses AEC it came out being high The fact that the quality of image is better there was a case which does not use AEC. but Price it was slight. Image qualitative it was deficient in AEC use presence. Through this, the overall situation and most efficient use of radiation workers is better suited. But Passive AEC use would be appropriate for use rather than proactive AEC.

• Journal of radiological science and technology
• /
• v.40 no.4
• /
• pp.575-580
• /
• 2017

Because moire artifacts overlap with fine lesions and frequency bands, image processing software that removes moire artifacts can lead to loss of micro lesions. In this study, microscopic lesions such as microcalcification and microfracture were randomly formed on SD (Sprague Dawley) rats and image and optimized grid images were compared and analyzed using reference image and grid suppression software. The images were read by two consecutive radiologists using a McNemar's test. Among the 73 microcalcifications, in the 13 cases after grid suppression, the image of the optimized grid shows the loss of image in 3 cases, and the image after grid suppression shows statistically significant image loss (p=0.021). In all 53 fracture lines, there were 19 cases of image loss after the grid suppression, and only one case of the optimized grid showed no image loss. Therefore, the use of grid suppression software to remove moire artifacts should be carefully considered in the diagnosis of micro lesions.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.207-208
• /
• 2014

본 연구는 Film System의 경우 카세트를 사용하여 환자검사부위와 tube 중심선속, 카세트의 중심이 맞았지만 디텍터의 경우 $17^{{\prime}{\prime}}{\times}17^{{\prime}{\prime}}$ 고정형으로써 디텍터의 중심과 tube의 중심선속, 환자의 검사부위가 맞지 않은체로 검사가 이루어지는 경우가 있어, 디지털 방사선장비에서 중심선속에 따른 화질의 변화를 파악하여 Tube의 중심선속과 환자와의 중심선속 일치에 따른 중요성을 제시하고자 한다.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.07a
• /
• pp.76-77
• /
• 2003

Digital Radiograpy ＆ Fluoroscopy(DRF 또는 DR 또는 DF)는 cone beam을 이용하여 인체를 투과한 X선을 영상증배관(Image Intensifying Tube： IIT)을 통하여 가시광선으로 변환시킨 후 영상을 카메라로 보내고, 이곳에서 발생한 영상정보를 디지털로 처리하여 모니터를 통해 눈에 보이는 영상으로 만드는 방법으로 IIT에 기초한 디지털 방사선 촬영술이라고도 한다. DF 방법은 즉시 영상 표시와 진단이 가능하기 때문에 즉시성이 요구되는 심장이나 두복부 등의 순환기 분야에서 DSA(Digital Subtraction Angiography) 장비로 이용되고 있고, 순환기뿐만 아니라 위를 중심으로 한 소화관(식도, 위, 소장, 대장, 직장)의 분야에서 적용 가능하다. (중략)

• Journal of radiological science and technology
• /
• v.39 no.3
• /
• pp.407-414
• /
• 2016

This study is to minimize the patient dose and maintain the image quality according to change of source to image receptor distance and applying additional filter. In this study, we used the DR system, the tissue-equivalent abdomen phantom and the aluminium filter. The exposure conditions were set to 80 kVp using AEC mode. The collimation size was $16{\times}16inch$. The exposure dose were measured 10 times when the SID was changed with 100, 110, 120 and 130 cm, respectively. The pirana 657 for dosimeter was located on center of radiation irradiation. The acquired images were analyzed by using the image J. In the results, the tube current was increased with increasing the SID but ESD was decreased with increasing the SID. The decrease of ESD attribute to use of filter that remove the photon of lower energy. In the histogram results using image J, there were differences between the ESD and the exposure conditions according to change of SID. However, there were not differences in histogram. Therefore, the exposure dose could reduced when set the longer SID. For pediatric exam, the exposure dose could reduced when used the aluminium filter.

• Journal of Biomedical Engineering Research
• /
• v.28 no.2
• /
• pp.300-305
• /
• 2007

In this study, we have studied the fabrication and the performance evaluation of digital radiation detector of the based on selenium (a-Se) prototype which is widely researched about recently. The detector was fabricated using amorphous selenium in the specification of active area size $7{\times}8.5"$, pixel pitch $139{\mu}m$, and 12 bit ADC. In order for the performance evaluation of the fabricated detector, we used radiation quality RQA 5 that is suggested by the International Electrotechnical Commission (IEC), and evaluated modulation transfer function (MTF), noise power spectrum (NPS), and detective quantum efficiency (DQE). Concerning MTF measurement, we used slit camera (Nuclear Associates, Model : 07-624-2222), and evaluated in the slit method. Also so as to compare the performance evaluation on the detector fabricated in this study, we used Hologic Direct-Ray (DR-1000) and GE Revolution XQ/I system, and evaluated and compared in the same method MTF, NPS, and DQE which are image quality factors. And as a result, the MTF of each detector In Nyquist frequency were evaluated to be 58% (at 3.5 lp/mm) in the case of DR-1000 and 65% (at 2.5 lp/mm) in the case of XQ/I, and that for the detector fabricated in this study was evaluated to be 36% (at 3.51 lp/mm). Also in the case of DQE(0), the detector fabricated in this study, DR-1000 of Hologic company, and XQ/I system of GE company respectively were evaluated as 36%, 32%, and 50%.

• Korean Journal of Food Science and Technology
• /
• v.22 no.4
• /
• pp.369-372
• /
• 1990

Although the measurement of oil globule size distribution is necessary to detect the process of demulsification, the reasonable methodology for its measurement has not been suggested because the solution of soymilk contains insoluble soybean particle and the protein to interfere with the detection of oil globule or oil content. The oil globule size distribution was measured by the homogeneous suspension and cumulative method under gravitational force or centrifugal force, which were modified with Stokes' low. The geometric mean diameter of oil globules in this soymilk was $033{\mu}m\;and\;031{\mu}m$ under gravitational method and centrifugal method, respectively. The differences of oil globule size distribution in the solutions emulsified by different pressures were detected by this method. The mean diameter of the solutions treated at higher pressure was shifted to smaller size and the distribution pattern of the solutions at higher pressure became more compact around the mean diameter.

• Imaging Science in Dentistry
• /
• v.40 no.4
• /
• pp.155-158
• /
• 2010

Digital radiographic systems allow the implementation of a fully digital picture archiving and communication system (PACS), and provide the greater dynamic range of digital detectors with possible reduction of X-ray exposure to the patient. This article reviewed the basic physical principles of digital radiographic imaging system in dental clinics generally. Digital radiography can be divided into computed radiography (CR) and direct radiography (DR). CR systems acquire digital images using phosphor storage plates (PSP) with a separate image readout process. On the other hand, DR systems convert X-rays into electrical charges by means of a direct readout process. DR systems can be further divided into direct and indirect conversion systems depending on the type of X-ray conversion. While a direct conversion requires a photoconductor that converts X-ray photons into electrical charges directly, in an indirect conversion, lightsensitive sensors such as CCD or a flat-panel detector convert visible light, proportional to the incident X-ray energy by a scintillator, into electrical charges. Indirect conversion sensors using CCD or CMOS without lens-coupling are used in intraoral radiography. CR system using PSP is mainly used in extraoral radiographic system and a linear array CCD or CR sensors, in panoramic system. Currently, the digital radiographic system is an important subject in the dental field. Most studies reported that no significant difference in diagnostic performance was found between the digital and conventional systems. To accept advances in technology and utilize benefits provided by the systems, the continuous feedback between doctors and manufacturers is essential.