• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.6
• /
• pp.701-709
• /
• 2019

Recently, heart rate signal, which is one of biological signals, have been used in various fields related to healthcare. Conventionally, most of the proposed heart rate signal detection methods are contact type methods, but there is a problem of discomfort that the subject have to contact with the device. In order to solve the problem, detection study by non-contact method has been progressed recently. The detected heart rate signal can be used for finger vein liveness detection and various application using heart rate. In this paper, we propose a method to obtain heart rate signal by using finger vein imaging system. The proposed method detected the signal from the changes of the brightness value in the time domain of the infrared finger vein images and converted it into the frequency domain using the image processing algorithm. After the conversion, we removed the noise not related to the heart rate signal through band-pass filtering. In order to evaluate the accuracy of the signal, we analyzed the correlation with the signal obtained simultaneously with the finger vein acquisition device and contact type PPG sensor approved by KFDA. As a result, it was possible to confirm that the heart rate signal detected in non-contact method through the finger vein image coincides with the waveform of actual heart rate signal.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.3
• /
• pp.291-298
• /
• 2016

In this paper, we studied about the radiated emission of EFT(Electrical Fast Transient)/Burst signal, referenced IEC-61000-4-4 of the international EMC standard and its effect on EUT(Equipment Under the Test) when EFT/Burst signal (Conducted noise) induced on a power cable to EUT. Firstly, we set up test sample by the standard and +4 kV standard signal is induced by EFT/Burst signal generator with 1 m length power cable for 1 minute. Consequently, we found not only induced EFT/Burst signal along power line, but also directly radiated emission signal from EFT/Burst signal generator (Radiated emission noise of EFT/Burst). The radiated emission signal of EFT/Burst was 30 dB which is higher than limit of CISPR 22 which is international EMC standard. Moreover, we measured the electric field strength by changing distance from maximum radiated emission point to electric field strength tester. As a result, this electric field strength was 23 V/m which is higher than international EMC standard test level(CISPR 24). Therefore, it was confirmed that the probability of malfunction may be high when radiated emission of EFT/Burst noise exists near the EUT.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.5
• /
• pp.485-492
• /
• 2009

The thermal fatigue crack(TFC) is one of the life-limiting mechanisms at the nuclear power plant operating conditions. In order to evaluate the structural integrity, various non-destructive test methods such as radiographic test, ultrasonic test and eddy current are used in the industrial field. However, these methods have restrictions that defect detection is possible after the crack growth. For this reason, acoustic emission testing(AET) is becoming one of powerful inspection methods, because AET has an advantage that possible to monitor the structure continuously. Generally, every mechanism that affects the integrity of the structure or equipment is a source of acoustic emission signal. Therefore the noise filtering is one of the major works to the almost AET researchers. In this study, acoustic emission signal was collected from the pipes which were in the successive thermal fatigue cycles. The data were filtered based on the results from previous experiments. Through the data analysis, the signal characteristics to distinguish the effective signal from the noises for the TFC were proven as the waveform difference. The experiment results provide preliminary information for the acoustic emission technique to the continuous monitoring of the structure failure detection.

• Journal of the Korean Society of Radiology
• /
• v.3 no.3
• /
• pp.37-40
• /
• 2009

In this study, we made a high efficiency x-ray detecting sensor using the lead oxide(PbO) that are used in direct method of x-ray detector. PbO with nano size particles is produced by sol-gel method for high efficiency. The produced PbO with nano size is deposited on ITO(Induim Tin Oxide) glass in several temperature using the PIB(particle-in-binder) method. The thickness of the deposited PbO is about $200{\mu}m$. Through the measurement of dark current, sensitivity and SNR(Signal To Noise Ratio), an electrical properties of the produced PbO film are analyzed. Therefore, we show that an electrical properties are changed according to a temperature and that the PbO film that was treated at $500^{\circ}C$ in O2 atmosphere is the most high efficiency x-ray detecting sensor.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Korean Journal of Optics and Photonics
• /
• v.33 no.4
• /
• pp.146-158
• /
• 2022

The detector of a focal-plane-array mid-wave infrared (MWIR) camera has different response characteristics for each detector pixel, resulting in nonuniformity between detector pixels. In addition, image nonuniformity occurs due to heat generation inside the camera during operation. To solve this problem, in the process of camera manufacturing it is common to use a gain-and-offset table generated from a blackbody to correct the difference between detector pixels. One method of correcting nonuniformity due to internal heat generation during the operation of the camera generates a new offset value based on input frame images. This paper proposes a technique for dividing an input image into block image patches and generating offset values using only homogeneous patches, to correct the nonuniformity that occurs during camera operation. The proposed technique may not only generate a nonuniformity-correction offset that can prevent motion marks due to camera-gaze movement of the acquired image, but may also improve nonuniformity-correction performance with a small number of input images. Experimental results show that distortion such as flow marks does not occur, and good correction performance can be confirmed even with half the number of input images or fewer, compared to the traditional method.

• Journal of radiological science and technology
• /
• v.32 no.4
• /
• pp.453-460
• /
• 2009

The purpose of this study was to determine the dose distribution and image quality according to slice thickness and BC(beam collimation) in the gantry aperture. CT scans were performed with a 64-slice MDCT(Brilliance 64, Philips, Cleveland, USA) scanner. To determine the dose distribution according to BC, a ionization chamber was placed at isocenter and 5, 10, 15, 20, 25 and 30 cm positions from the isocenter in the 12, 3, 6 and 9 o'clock directions. The dose distribution for phantom scan was also measured using CT head and body dose phantom with five holes at the center of the phantom and the positions of the 12, 3, 6 and 9 o'clock directions. The image noise measurement for different BCs was performed using an AAPM CT phantom. Water-filled block of the phantom was moved by 5 cm or 10 cm to the 12 o'clock direction, and the image noise was measured at the center of the phantom, and the points of 12, 3, 6 and 9 o'clock direction respectively. Some points were placed beyond the scan field of view (SFOV), so that measurement was not possible at that points. The results are as follows: The CTDIw showed a larger decrease as the source goes farther from the iso-center or the BC became wider. The CTDIw depends on the BC width more than the number of the channel of a detector array. The value of CTDIW decreased with increasing BC, but the value decreased 16.6~31.9% in the head phantom scan in air scan and 51.0~64.5% in the body phantom scan. The value of the noise was 3.9~5.9 in the head and 5.3~7.4 in the body except for BC of $2{\times}0.5\;mm$, regardless of the degree of deviation from the iso-center. When a subject was located within the SFOV, the position did not significantly affect image quality even if the subject was out of the center.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.90-96
• /
• 2010

The focusing system is an important factor to determine the imaging quality of a digital imaging system. The focusing system consist of measuring the focusing index with high frequency energy of an image and controlling the movement of the focusing lens based on the computed focusing index. The computation of the focusing index is a key aspect in implementing the focusing system and the noise of the image cause the error in the sharpness evaluation of the image. To reduce this error, the noise under the low illumination condition is considered. A noise insensitive focusing index using adaptive weights is proposed in this paper. This measure determines the sharpness of an image using the spatially adaptive weights based on the local statistics of the image and noise. Experimental results under the condition without and with the noise verify the performance of the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2975-2981
• /
• 2014

Micro-magnetic detection system is used to detect small particles in an automatic transmission valve body, which signal noise and time-delay may occurs in process of signal transmitting and filtering. In this paper, we present the design and implement of a micro-magnetic detection system based on wireless sensor networks in conveyer belt. Micro-magnetic detection system consists of five modules which are magnetic sensor detector, signal processing unit, wireless sensor networks, system control unit and system monitoring unit. Our experimental results show that the proposed wireless micro-magnetic detection system improves both accuracy and time delay compared to the wired system; therefore, it may apply for wireless micro-magnetic detection system by analysis of packet reception rate.