• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.12
• /
• pp.90-97
• /
• 1999

Recently, there have been many researches to automate processing and analysing image data in medical field, due to the advance of image processing techniques, the fast communication network and high performance hardware. In this paper, we design and implement the system based on the multi-layer neural network model to be able to analyze, differentiate and count blood cells in the peripheral blood image. To do these, we segment red and white-blood cell in blood image acquired from microscope with CCD(Charge-coupled device) camera and then apply the various feature extraction algorithms to classify. In addition to, we reduce multi-variate feature number using PCA(Principle Component Analysis) to construct more efficient classifier. So, in this paper, we are sure that the proposed system can be applied to a pathological guided system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2137-2142
• /
• 2016

The electrical current generated by heart creates not only electric potential but also a magnetic field. In this study, the signals obtained magnetocardiogram(MCG) using 61 channel superconducting quantum interference device(SQUID) system, and the clinical significance of various feature parameters has been developed MCG. Neural network algorithm was used to perform the classification of ischemic heart disease. The MCG signal was obtained to facilitate the extraction of parameters through a process of pre-processing. The data used to research the normal group 10 and ischemic heart disease group 10 with visible signs of stable angina patients. The available clinical indicators were extracted by characteristic point, characteristic interval parameter, and amplitude ratio parameter. The extracted parameters are determined to analysis the significance and clinical parameters were defined. It is possible to classify ischemic heart disease using the MCG feature parameters as a neural network input.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.997-1006
• /
• 2019

To overcome the difficulties and inefficiencies of the existing power analysis attack, we try to extract the secret key embedded in a cryptographic device using attack model based on MLP(Multi-Layer Perceptron) method. The target of our proposed power analysis attack is the AES-128 encryption module implemented on an 8-bit processor XMEGA128. We use the divide-and-conquer method in bytes to recover the whole 16 bytes secret key. As a result, the MLP-based power analysis attack can extract the secret key with the accuracy of 89.51%. Additionally, this MLP model has the 94.51% accuracy when the pre-processing method on power traces is applied. Compared to the machine leaning-based model SVM(Support Vector Machine), we show that the MLP can be a outstanding method in power analysis attacks due to excellent ability for feature extraction.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.8
• /
• pp.11-19
• /
• 2019

Against advanced image-related crimes, a high level of digital forensic methods is required. However, feature-based methods are difficult to respond to new device features by utilizing human-designed features, and deep learning-based methods should improve accuracy. This paper proposes a deep learning model to identify camera models based on DenseNet, the recent technology in the deep learning model field. To extract camera sensor features, a HPF feature extraction filter was applied. For camera model identification, we modified the number of hierarchical iterations and eliminated the Bottleneck layer and compression processing used to reduce computation. The proposed model was analyzed using the Dresden database and achieved an accuracy of 99.65% for 14 camera models. We achieved higher accuracy than previous studies and overcome their disadvantages with low accuracy for the same manufacturer.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.29 no.2
• /
• pp.387-396
• /
• 1999

In dentistry. RadioVisioGraphy was introduced as a first electronic dental x-ray imaging modality in 1989. Thereafter. many types of direct digital radiographic system have been produced in the last decade. They are based either on charge-coupled device(CCD) or on storage phosphor technology. In addition. new types of digital radiographic system using amorphous selenium. image intensifier etc. are under development. Advantages of digital radiographic system are elimination of chemical processing, reduction in radiation dose. image processing, computer storage. electronic transfer of images and so on. Image processing includes image enhancement. image reconstruction. digital subtraction, etc. Especially digital subtraction and reconstruction can be applied in many aspects of clinical practice and research. Electronic transfer of images enables filmless dental hospital and teleradiology/teledentistry system. Since the first image management and communications system(IMACS) for dentomaxillofacial radiology was reported in 1992. IMACS in dental hospital has been increasing. Meanwhile. researches about computer-assisted diagnosis, such as structural analysis of bone trabecular patterns of mandible. feature extraction, automated identification of normal landmarks on cephalometric radiograph and automated image analysis for caries or periodontitis. have been performed actively in the last decade. Further developments in digital radiographic imaging modalities. image transmission system. imaging processing and automated analysis software will change the traditional clinical dental practice in the 21st century.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1102-1105
• /
• 2004

In this paper, the problem of a viewer's head tracking in a desktop-based interactive stereoscopic display system is considered. A fast and low-cost approach to the problem is important for such a computing environment. The system under consideration utilizes a shuttle glass for stereoscopic display. The proposed method makes use of an image taken from a single low-cost video camera. By using a simple feature extraction algorithm, the obtained points corresponding to the image of the user-worn shuttle glass are used to estimate the glass center, its local 'yaw' angle, as measured with respect to the glass center, and its global 'yaw' angle as measured with respect to the camera location. With these estimations, the stereoscopic image synthetic program utilizes those values to interactively adjust the two-view stereoscopic image pair as displayed on a computer screen. The adjustment is carried out such that the so-obtained stereoscopic picture, when viewed from a current user position, provides a close-to-real perspective and depth perception. However, because the algorithm and device used are designed for fast computation, the estimation is typically not precise enough to provide a flicker-free interactive viewing. An error concealment method is thus proposed to alleviate the problem. This concealment method should be sufficient for applications that do not require a high degree of visual realism and interaction.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.566-574
• /
• 2021

The arc is one of factors causing electrical fires. Over past decades, various researches have been carried out to detect arc occurrences. Even though frequency analysis, wavelet and statistical features have been used, arc detection performance is degraded due to diverse arc waveforms. On the contray, Deep neural network (DNN) direcly utilizes raw data without feature extraction, based on end-to-end learning. However, a disadvantage of the DNN is processing complexity, posing the difficulty of being migrated into a termnial device. To solve this, this paper proposes an arc detection method using a logistic regression that is one of simple machine learning methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.85-90
• /
• 2021

In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models' validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.5
• /
• pp.359-363
• /
• 2017

The LED (Liquid Emitting Diode) frame device is a big part of the representative display industry in Korea. LED is an essential part for TV, monitor, notebook, and mobile phone. In Japan, Taiwan, China and other countries, investment in LEDs has been strengthened, and productivity has become an important issue. However, as the size of the parts becomes smaller, the inconsistent inspection by the human eye becomes a problem of reliability, so that the automatic inspection process becomes an essential issue in the field of LED module inspection. In this paper, we investigate defects in visual inspection process using computer vision technology. The inspection of the LED frame is made quickly and accurately, thereby improving the efficiency of the process and shortening the inspection time. As a result of applying the inspection system to the field, we confirmed that it is possible to inspect quickly and accurately.