• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.2
• /
• pp.70-76
• /
• 2012

In this paper, an automatic extraction method of glomerulus region from human renal tissue image is presented. The important information reflecting the state of kidneys richly included in the glomeruli, so it should be the first step to extract the glomerulus region from the renal tissue image for the further quantitative analysis of the renal condition. Especially, there is no clear difference between the glomerulus and other tissues, so the glomerulus region can not be easily extracted from its background by the existing segmentation methods. The outer edge of a glomerulus region is regarded as a common property for the regions of this kind ; a two- dimensional Gaussian distribution is used to convolve with an original image first and then the image is thresholded at this blurred image ; a closed curve corresponding to the outer edge can be obtained by usual pattern processing skills like thinning, branch-cutting, hole-filling etc., Finally, the glomerulus region can be obtained by extracting the area in the original image surrounded by the closed curve. The glomerulus regions are correctly extracted by 85 percentages and experimental results show the proposed method is effective.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• Journal of the Korean earth science society
• /
• v.45 no.2
• /
• pp.111-120
• /
• 2024

Cloud coverage is a key factor in determining whether to proceed with observations. In the past, human judgment played an important role in weather evaluation for observations. However, the development of remote and robotic observation has diminished the role of human judgment. Moreover, it is not easy to evaluate weather conditions automatically because of the diverse cloud shapes and their rapid movement. In this paper, we present the development of a cloud monitoring program by applying a machine learning-based Python module "cloudynight" on all-sky camera images obtained at Miryang Arirang Astronomical Observatory (MAAO). The machine learning model was built by training 39,996 subregions divided from 1,212 images with altitude/azimuth angles and extracting 16 feature spaces. For our training model, the F1-score from the validation samples was 0.97, indicating good performance in identifying clouds in the all-sky image. As a result, this program calculates "Cloudiness" as the ratio of the number of total subregions to the number of subregions predicted to be covered by clouds. In the robotic observation, we set a policy that allows the telescope system to halt the observation when the "Cloudiness" exceeds 0.6 during the last 30 minutes. Following this policy, we found that there were no improper halts in the telescope system due to incorrect program decisions. We expect that robotic observation with the 0.7 m telescope at MAAO can be successfully operated using the cloud monitoring program.

• Journal of Animal Environmental Science
• /
• v.11 no.1
• /
• pp.35-44
• /
• 2005

The objectives of this study were to develop an image processing algorithm for finding the sick or the dead layers(SDL) rearing in the multi-tier layer battery, which is a core technology of remote monitoring systems for layers, and to test the performance of algorithm developed in the experimental poultry housing. Based on the literature study and experiment, the standing up of layer was set as a criterion for judging layers whether sick or dead. Then, by the criterion set, an algorithm was developed. The image processing algorithm developed was tested how well it could and SDL at the experimental poultry housing. Test results showed that its monitoring correctness of layers standing up in the cages having all healthy layers was $92\%$, and $96\%$ in the cages having SDL. Therefore, it would be concluded that the image processing algorithm developed in this study was well suited to the purpose of development.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.5
• /
• pp.1080-1088
• /
• 2004

In this paper, the interesting moving objects tracking algorithm using color information on Multi-Video camera against variance of intensity, shape and background is proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area, after converting RGB color coordination of image which is input from multi-video camera into HSI color coordination. Hue information of the detected moving area are segmented to 24 levels from $0^{\circ}$ to $360^{\circ}$. It is used to the feature parameter of the moving objects that are three segmented hue levels with the highest distribution and difference among three segmented hue levels. To examine propriety of the proposed method, human images with variance of intensity and shape and human images with variance of intensity, shape and background are targeted for moving objects. As surveillance results of the interesting human, hue distribution level variation of the detected interesting human at each camera is under 2 level, and it is confirmed that the interesting human is tracked and surveilled by using feature parameters at cameras, automatically.

• Journal of the Korea Computer Graphics Society
• /
• v.3 no.2
• /
• pp.27-34
• /
• 1997

3-D image modeling is in high demand for automated visual inspection and non-destructive testing. It also can be useful in biomedical research, medical therapy, surgery planning, and simulation of critical surgery (i.e. cranio-facial). Image processing and image analysis are used to enhance and classify medical volumetric data. Analyzing medical volumetric data is very difficult In this paper, we propose a new image modeling method based on tetrahedrization to improve the visualization of three-dimensional medical volumetric data. In this method, the trivariate piecewise linear interpolation is applied through the constructed tetrahedral domain. Also, visualization methods including iso-surface, color contouring, and slicing are discussed. This method can be useful to the correct and speedy analysis of medical volumetric data, because it doesn't have the ambiguity problem of Marching Cubes algorithm and achieves the data reduction. We expect to compensate the degradation of an accuracy by using an adaptive sub-division of tetrahedrization based on least squares fitting.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.1 s.6
• /
• pp.93-102
• /
• 1996

For an atomatic generation of DEM(Digital Elevation Model) by computer, it is a time-consumed work to determine adquate matches from stereo images. Correlation and evenly distributed area-based method is generally used for matching operation. In this paper, we propose a new approach that computes matches efficiantly by changing the size of mask window and search area according to the given terrain information. For image segmentation, at first edge-preserving smoothing filter is used for preprocessing, and then region growing algorithm is applied for the filterd images. The segmented regions are classifed into mountain, plain and water area by using MRF(Markov Random Filed) model. Maching is composed of predicting parallex and fine matching. Predicted parallex determines the location of search area in fine matching stage. The size of search area and mask window is determined by terrain information for each pixel. The execution time of matching is reduced by lessening the size of search area in the case of plain and water. For the experiments, four images which are covered $10km{\times}10km(1024{\times}1024\;pixel)$ of Taejeon-Kumsan in each are studied. The result of this study shows that the computing time of the proposed method using terrain information for matching operation can be reduced from 25% to 35%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.634-638
• /
• 2018

Haze is a factor that degrades the performance of various image processing algorithms, such as those for detection, tracking, and recognition using an electro-optical sensor. For robust operation of an electro-optical sensor-based unmanned system used outdoors, an algorithm capable of effectively removing haze is needed. As a haze removal method using a single electro-optical sensor, the dark channel prior using statistical properties of the electro-optical sensor is most widely known. Previous methods used a square filter in the process of obtaining a transmission using the dark channel prior. When a square filter is used, the effect of removing haze becomes smaller as the size of the filter becomes larger. When the size of the filter becomes excessively small, over-saturation occurs, and color information in the image is lost. Since the size of the filter greatly affects the performance of the algorithm, a relatively large filter is generally used, or a small filter is used so that no over-saturation occurs, depending on the image. In this paper, we propose an improved haze removal method using color image segmentation. The parameters of the color image segmentation are automatically set according to the information complexity of the image, and the over-saturation phenomenon does not occur by estimating the amount of transmission based on the parameters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.6
• /
• pp.1209-1214
• /
• 2016

LPR(License plate recognition) is a kind of the most popular surveillance technology based on accompanied by a video and video within the optical character recognition. LPR need a many process. One is a localization of car license plates, license plate of size, space, contrast, normalized to adjust the brightness, another is character division for recognize the character optical character recognition to win the individual characters, character recognition, the other is phrase analysis of the shape, size, position by year, the procedure for the analysis by comparing the database of license plate having a difference by region. In this paper, describing the results of performance of license plate recognition S/W, which was implemented using EmguCV, find the location, using the tesseract OCR, which are well known to an optical character recognition engine of open source, the characters of the license plate image capturing angle of the plate, image size, brightness.