• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.411-421
• /
• 2001

The generalized symmetry transform evaluates symmetry without segmentation and extracts regions of interest in an image by combining locality and reflectional symmetry The demand that the symmetry transform be local is reflected by the distance weight function. When calculating large regions-of-interest, we should select a large standard deviation of distance weight function. But such a large standard deviation makes the execution time increase in the second power of r, which is a radius of search area. In this paper we propose modified scan line based GST with selectively directional attention to improve time complexity The symmetry map of our proposed GST is found to be very similar to that of the existing GST. However the computation time of the proposed GST increases linearly with respect to r because our proposed GST evaluates symmetry between a pair of edge pixels along the scan lines. The GST computation decreases considerably when the proposed GST is peformed with selectively directional attention in case of large r. Several experiments in this paper demonstrate the time efficiency and the usefulness of our proposed GST.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.49-57
• /
• 2011

Extraction of regions of interest (ROIs) is the first and important step for the applications in computer vision and affects the rest of the application process. However, ROI extraction can be easily affected by the environment such as illumination, camera, etc. Many applications adopt problem-specific knowledge and/or post-processing to correct the error occurred in ROI extraction. In this paper, proposed is a robust framework that could overcome the environmental change and is independent from the rest of the process. The proposed framework uses a differential image and a color distribution to extract ROIs. The color distribution can be learned on-line, which make the framework to be robust to environmental change. Even more, the components of the framework are independent each other, which makes the framework flexible and extensible. The usefulness of the proposed framework is demonstrated with the application of hand region extraction in an image sequence.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.115-122
• /
• 2017

This paper proposes a deep learning algorithm based sign detection and recognition system for the blind. The proposed system is composed of sign detection stage and sign recognition stage. In the sign detection stage, aggregated channel features are extracted and AdaBoost classifier is applied to detect regions of interest of the sign. In the sign recognition stage, convolutional neural network is applied to recognize the regions of interest of the sign. In this paper, the AdaBoost classifier is designed to decrease the number of undetected signs, and deep learning algorithm is used to increase recognition accuracy and which leads to removing false positives which occur in the sign detection stage. Based on our experiments, proposed method efficiently decreases the number of false positives compared with other methods.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.1-10
• /
• 2018

This paper presents an autonomous detection and aiming point computation of a battle tank by using RGB images. Maximally stable extremal regions algorithm was implemented to find features of the tank, which are matched with images extracted from streaming video to figure out the region of interest where the tank is present. The median filter was applied to remove noises in the region of interest and decrease camouflage effects of the tank. For the tank segmentation, k-mean clustering was used to autonomously distinguish the tank from its background. Also, both erosion and dilation algorithms of morphology techniques were applied to extract the tank shape without noises and generate the binary image with 1 for the tank and 0 for the background. After that, Sobel's edge detection was used to measure the outline of the tank by which the aiming point at the center of the tank was calculated. For performance measurement, accuracy, precision, recall, and F-measure were analyzed by confusion matrix, resulting in 91.6%, 90.4%, 85.8%, and 88.1%, respectively.

• Nuclear Engineering and Technology
• /
• v.16 no.4
• /
• pp.181-194
• /
• 1984

The in-core fuel management problem was studied by use of the calculus of variations. Two functions of interest to a public power utility, the profit function and the cost function, were subjected to the constraints of criticality, the reactor turnup equations and an inequality constraint on the maximum allowable power density. The variational solution of the initial profit rate demonstrated that there are two distinct regions of the reactor, a constant power region and a minimum inventory or flat thermal flux region. The transition point between these regions is dependent on the relative importance of the profit for generating power and the interest charges for the fuel. The fuel cycle cost function was then used to optimize a three equal volume region reactor with a constant fuel enrichment. The inequality constraint on the maximum allowable power density requires that the inequality become an equality constraint at some points in the reactor. and at all times throughout the core cycle. The finite difference equations for reactor criticality and fuel burnup in conjunction with the equality constraint on power density were solved, and the method of gradients was used to locate an optimum enrichment. The results of this calculation showed that standard non-linear optimization techniques can be used to optimize a reactor when the inequality constraints are properly applied.

• The Korean Journal of Nuclear Medicine
• /
• v.26 no.2
• /
• pp.251-256
• /
• 1992

Regional cerebral blood flow were measured in 10 patients with Parkinson's disease and 12 normal persons using $^{99m}Tc-HMPAO$ SPECT. Reconstructed images were interpreted qualitatively and were compared with those findings of CT. For the quantitative analysis, six pairs of region of interest matched with the perfusion territories of large cerebral arteries and cerebellar hemisphere were determined. From the count values, indices showing the degree of asymmetry between right and left cerebral or cerebellar hemisphere, cerebral asymmetry index (ASI) and percent index of cerebellar asymmetry (PIA), and an index showing change of each region, region to cerebellum ratio (RCR) were obtained. ASI of normal persons and patients were $0.082{\pm}0.033$ and $0.108{\pm}0.062$, respectively and PIA were $-0.4{\pm}0.7%$ and $-0.7{\pm}1.0%$, respectively, which showed no statistically significant difference between normal persons and patients. Among 10 RCR's, those of both regions of basal ganglia and both regions of anterior cerebral artery were significantly reduced. We concluded that the most significant reduction of regional cerebral blood flow in patients with Parkinson's disease was observed in the regions of basal ganglia and in the regions of anterior cerebral artery, and the degree of change in hemispheric blood flow was similar in both hemisphere.

• Imaging Science in Dentistry
• /
• v.50 no.1
• /
• pp.23-30
• /
• 2020

Purpose: This study was conducted to assess the effectiveness of a metal artifact reduction (MAR) algorithm activated at different times during cone-beam computed tomography (CBCT) acquisition on the magnitude of artifacts generated by a zirconium implant. Materials and Methods: Volumes were obtained with and without a zirconium implant in a human mandible, using the OP300 Maxio unit. Three modes were tested: without MAR, with MAR activated after acquisition, and with MAR activated before acquisition. Artifacts were assessed in terms of the standard deviation (SD) of gray values and the contrast-to-noise ratio (CNR) in 6 regions of interest with different distances (10 to 35 mm, from the nearest to the farthest) and angulations(70° to 135°) from the implant region. Results: In the acquisitions without MAR, the regions closer to the implant(10 and 15mm) had a higher SD and lower CNR than the farther regions. When MAR was activated (before or after), SD values did not differ among the regions (P>0.05). The region closest to the implant presented a significantly lower CNR in the acquisitions without MAR than when MAR was activated after the acquisition; however, activating MAR before the acquisition did not yield significant differences from either of the other conditions. Conclusion: Both modes of MAR activation were effective in decreasing the magnitude of CBCT artifacts, especially when the effects of the artifacts were more noticeable.

• Journal of Korea Multimedia Society
• /
• v.9 no.12
• /
• pp.1588-1595
• /
• 2006

In this paper, we proposed a liver extracting procedure for computer aided liver diagnosis system. Extraction of liver region in an abdominal CT image is difficult due to interferences of other organs. For this reason, liver region is extracted in a region of interest(ROI). ROI is selected by the window which can measure the distribution of Hounsfield Unit(HU) value of liver region in an abdominal CT image. The distribution is measured by an existential probability of HU value of lever region in the window. If the probability of any window is over 50%, the center point of the window would be assigned to ROI. Actually, liver region is not clearly discerned from the adjacent organs like muscle, spleen, and pancreas in an abdominal CT image. Liver region is extracted by the watershed segmentation algorithm which is effective in this situation. Because it is very sensitive to the slight valiance of contrast, it generally produces over segmentation regions. Therefore these regions are required to merge into the significant regions for optimal segmentation. Finally, a liver region can be selected and extracted by prier information based on anatomic information.

• Anxiety and mood
• /
• v.16 no.2
• /
• pp.106-112
• /
• 2020

Objective : Social anxiety disorder (SAD) is characterized by fear of social threat and exhibits limbic hyper-reactivity toward social stimuli such as emotional faces. A previous study identified the uncinate fasciculus (UF) sub-tract as particularly related to facial memory. To explore the white matter tract relating to face-specific brain regions, we investigated the UF sub-tract in SAD. Methods : The diffusion tensor images of 22 patients with SAD and 20 healthy controls were analyzed with tractography. The UF sub-tract was delineated using the regions of interest of face patches in the anterior temporal lobe and the orbitofrontal cortex, and fractional anisotrophy (FA) and total number of streamlines (ST) were analyzed. We examined the group comparison of FA and ST of the UF sub-tract and correlations of FA and ST with the social anxiety symptoms such as the Liebowitz Social Anxiety Scale (LSAS), the Social Interaction Anxiety Scale (SIAS), the Social Phobia Scale (SPS) and the Fear of Negative Evaluation scale (FNE) in SAD. Results : There were no group differences in FA and ST of the UF sub-tract. However, negative correlations were observed between ST of the right UF sub-tract and severity of social anxiety symptoms (LSAS, r_s=-0.480, p=0.024; SIAS, r_s=-0.580, p=0.005; SPS, r_s=-0.590, p=0.004; FNE, r_s=-0.675, p=0.001) in patients with SAD. Conclusion : Although patients with SAD did not show quantitative abnormalities in the UF sub-tact connecting face-specific brain regions, this structure seems to play a role in the symptom severity of SAD.

• Clinics in Shoulder and Elbow
• /
• v.18 no.2
• /
• pp.86-90
• /
• 2015

Background: Although there are several methods for evaluating bone quality, Hounsfield units (HU), a standardized computed tomography (CT) attenuation coefficient, provide a useful tool for estimating focal bone mineral density (BMD). The aim of this study is to investigate the HU for evaluating the degree of osteoporosis in greater tuberosity with regard to anchor positioning. Methods: Forty patients diagnosed as normal on shoulder CT were included and categorized according to age and gender. Axially sectioned CT images were processed to 3-dimensional models containing information about bone quality using Mimics (14.11 platform v14.1.1.1 Materialise). Three-dimensional anchors were simulated and positioned according to 6 regions of interest (ROI) in the greater tuberosity classified using Tingart's system. Mean HU of intra-anchor volumes in the 6 regions was measured. Results: A significant decrease in HU was observed with increasing age (p=0.0001) and menopause (p<0.001). A significant difference in HU was found between male and female groups with males showing the higher values (p=0.0001). HU of proximal areas of ROI was higher than those of distal areas (p<0.005). However, although mean HU of distal posterior ROI showed the lowest values, no statistically significant difference was found between anterior, middle, and posterior regions (p=0.087). Conclusions: Mean HU of ROIs provides a tool for preoperative assessment of focal BMD, which is a factor of suture anchor stability and can be used to aid decision-making regarding secure anchor positioning for rotator cuff repair. Our data support that the most secure point is the proximal regions of ROI.