• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.186-191
• /
• 2019

In this paper, we propose a implementation approach of the high-speed feature extraction algorithm. The proposed method is based on the block type classification algorithm which reduces the computation time when target macro block is divided to smooth block type that has no image features. It is quantitatively identified that occurs at 29.5% of the total image using 200 standard test images with $64{\times}64$ macro block size. This means that within a standard test image containing various image information, 29.5% can reduce the complexity of the operation. When the proposed approach is applied to the Canny edge detection, the required latency of the edge detection can be completely eliminated, such as 2D derivative filter, gradient magnitude/direction computation, non-maximal suppression, adaptive threshold calculation, hysteresis thresholding. Also, it is expected that operation time of the feature detection can be reduced by applying block type classification algorithm to various feature extraction algorithms in this way.

• Investigative Magnetic Resonance Imaging
• /
• v.10 no.1
• /
• pp.1-7
• /
• 2006

Purpose : Recent development of diffusion tensor imaging enables the evaluation of the microstructural characteristics of the brain white matter. However, optimal imaging parameters for diffusion tensor imaging, particularly concerning the number of diffusion gradient direction, have not been studied thoroughly yet. The purpose of this study was to evaluate the influence of the number of diffusion gradient direction on the fiber tracking of the white matter. Materials and methods : 13 healthy volunteers (ten men and three women, mean age 30 years, age range 23-37 years) were included in this study. Diffusion tensor imaging was performed with different numbers of diffusion gradient direction as 6, 15, and 32, keeping the other imaging parameters constant. The imaging field ranged from 1 cm below the pons to 2-3 cm above the lateral ventricle, parallel to the anterior commissure-posterior commissure line. FA (fractional anisotropy) maps were created via image postprocessing, and then FA and its standard deviation were calculated in the genu and the splenium of the corpus callosum on each of FA maps. Fiber tracking of the corticospinal tract in the brain was performed and the number of the reconstructed fibers of the tract was measured. FA, standard deviation of FA and the number of the reconstructed fibers were compared statistically between the different diffusion gradient directions. Results : FA is not statistically significantly different between the different diffusion gradient directions. By increasing the number of diffusion gradient direction, standard deviation of FA decreased significantly, and the number of the reconstructed fibers increased significantly. Conclusion : The higher number of diffusion gradient direction provided better quality of fiber tracking.

• Journal of radiological science and technology
• /
• v.28 no.1
• /
• pp.25-32
• /
• 2005

Purpose : To evaluate the degree of the artifact which is caused by the mascara and the eye shadow when acquiring MR images and compare the difference of the image distortion according to the change of various pulse sequence. Material and Method : The popular domestic mascara and eye shadow products were selected from three different companies respectively and divided into two groups mascara (M1, M2, M3 ), eye shadow (E1, E2, E3). Self-designed quadrature type saddle coil which has 4 cm inside diameter, 8 cm length and which is for both Tx and Rx was used. MR image was acquired respectively after applying the mascara to the tape from study 1, the eye shadow to the tape from study 2 and adding the eye shadow to the mascara from study 3. The FSE(fast spin echo), the SE(spin echo), the GE(gradient echo) were used as pulse sequences. The degree of the image distortion which was measured from each sequence was analyzed in quality and quantity. Result : The mascara and the eye shadow caused the artifacts to the MR images partially and induced the image distortion. There was a little difference in terms of the degree of artifact according to the change of pulse sequence. From the study 3 in which the eye shadow was applied to the mascara, on the axial plane image, the width of artifact was 16.73 mm in the GE pulse sequence, 6.64 mm in the SE pulse sequence, and 6.19 mm in the FSE pulse sequence. The degree of the artifact appeared highly in order of the GE, the SE and the FSE. On the sagittal plane image, the length of artifact was 22.84 mm in the GE, 17.81 mm in the SE and it appeared highly with the SE and the FSE technique order. Conclusion : When examining the eyeball and the brain of a woman with the mascara and the eye shadow, we have to consider that the artifact caused by them can have an effect on the image diagnosis. We concluded that it is more suitable for a brain and a eyeball T2 emphasizing image to use the FSE technique than the GE technique.

• The KIPS Transactions:PartD
• /
• v.10D no.7
• /
• pp.1171-1176
• /
• 2003

In this paper, we propose an effective bar code detection algorithm using the feature analysis and the labeling. After computing the direction of pixels using four line operators, we obtain the histogram about the direction of pixels by a block unit. We calculate the difference between the maximum value and the minimum value of the histogram and consider the block that have the largest difference value as the block of the bar code region. We get the line passing by the bar code region with the selected block but detect blocks of interest to get the more accurate line. The largest difference value is used to decide the threshold value to obtain the binary image. After obtaining a binary image, we do the labeling about the binary image. Therefore, we find blocks of interest in the bar code region. We calculate the gradient and the center of the bar code with blocks of interest, and then get the line passing by the bar code and detect the bar code. As we obtain the gray level of the line passing by the bar code, we grasp the information of the bar code.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.471-476
• /
• 2016

In this paper, recognition system for continuous human action is explained by using motion history image and histogram of oriented gradient with spotter model based on depth information, and the spotter model which performs action spotting is proposed to improve recognition performance in the recognition system. The steps of this system are composed of pre-processing, human action and spotter modeling and continuous human action recognition. In pre-processing process, Depth-MHI-HOG is used to extract space-time template-based features after image segmentation, and human action and spotter modeling generates sequence by using the extracted feature. Human action models which are appropriate for each of defined action and a proposed spotter model are created by using these generated sequences and the hidden markov model. Continuous human action recognition performs action spotting to segment meaningful action and meaningless action by the spotter model in continuous action sequence, and continuously recognizes human action comparing probability values of model for meaningful action sequence. Experimental results demonstrate that the proposed model efficiently improves recognition performance in continuous action recognition system.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.375-385
• /
• 2016

Recently, several implantable hearing aids such as cochlear implant, middle ear implant, etc., which have a module receiving power and signal from outside the body, are frequently used to treat the hearing impaired patients. Most of implantable hearing aids are adopted permanent magnet pairs to couple between internal and external devices for the enhancement of power transmission. Generally, the internal device which containing the magnet in the center of receiving coil is implanted under the skin of human temporal bone. In case of MRI scanning of a patient with the implantable hearing aid, however, homogeneous magnetic fields of the MRI might be interfered by the implanted magnet. For the above reasons, the MR image is degraded by large area of artifact, so that diagnostics are almost impossible in deteriorated region. In this paper, we proposed an external coil system that can reduce the artifact of MR image due to the internal coupling magnet. By finite element analysis estimating area of MR artifact according to varying current and shape of the external coil, optimal coil parameters were extracted. Finally, the effectiveness of the proposed external coil system was verified by confirming the artifact at real MRI scan.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.77-85
• /
• 2010

Fingerprint image quality checking is one of the most important issues in on-line fingerprint recognition because the recognition performance is largely affected by the quality of fingerprint images. In the past, many related fingerprint quality checking methods have typically considered the local quality of fingerprint. However, It is necessary to estimate the global quality of fingerprint to judge whether the fingerprint can be used or not in on-line recognition systems. Therefore, in this paper, we propose both local and global-based methods to calculate the fingerprint quality. Local fingerprint quality checking algorithm considers both the condition of the input fingerprints and orientation estimation errors. The 2D gradients of the fingerprint images were first separated into two sets of 1D gradients. Then，the shapes of the PDFs(Probability Density Functions) of these gradients were measured in order to determine fingerprint quality. And global fingerprint quality checking method uses neural network to estimate the global fingerprint quality based on local quality values. We also analyze the matching performance using FVC2002 database. Experimental results showed that proposed quality check method has better matching performance than NFIQ(NIST Fingerprint Image Quality) method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2441-2449
• /
• 2015

In this digital information era, utilization of images are essential for various media, and the edge is an important characteristical information of an object in images that includes the size, location, direction and etc. Many domestic and international studies are being conducted in order to detect these edge. Existing edge detection methods include Sobel, Prewitt, Roberts, Laplacian, LoG and etc. which apply fixed weight value. As these existing edge detection methods apply fixed weight mask to the image, edge detection characteristic appears slightly insufficient. Accordingly, in order to supplement these problems, this study used bottom-hat transformation from mathematical morphology and opening operation in improving the image and proposed an algorithm that detects for the edge after calculating mask-based gradient. And to evaluate the performance of the proposed algorithm, a comparison was made against the existing Sobel, Roberts, Prewitt, Laplacian, LoG edge detection methods, in illustrating visual images, and similarities were compared by calculating the MSE value based on the standard of each image.

• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.949-955
• /
• 2005

In this Paper, we propose fast block matching algorithm by dividing complex areas based on complexity order of reference block and square sub-block to reduce an amount of computation of full starch(FS) algorithm for fast motion estimation, while keeping the same prediction quality compared with the full search algorithm. By using the fact that matching error is proportional to the gradient of reference block, we reduced unnecessary computations with square sub-block adaptive matching scan based image complexity instead of conventional sequential matching scan and row/column based matching scan. Our algorithm reduces about $30\%$ of computations for block matching error compared with the conventional partial distortion elimination(PDE) algorithm without any prediction quality, and our algorithm will be useful in real-time video coding applications using MPEG-4 AVC or MPEG-2.