• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.683-693
• /
• 2023

In this study, we used satellite images to analyze the green algae phenomenon that first occurred in Soyang-ho, which was completed in 1973. The research data used 13 optical images over a period of about 2 months from July 2023, and the area of green algae that occurred in Soyang-ho was calculated. To calculate the exact area where green algae occurred, image classification was performed based on the support vector machine algorithm. As a result, green algae in Soyang-ho occurred around the point where the impurities that caused the green algae were introduced. It seemed to temporarily decrease due to the effects of Typhoon Khanun in August 2023, but green algae increased again due to the continued heat. Soyang-ho is one of the major water sources in the metropolitan area, suggesting that we must prepare for repeated green algae outbreaks.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2003

In this paper, I proposed a classifier of liver cirrhotic step using T1-weighted MRI(magnetic resonance imaging) and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were obtained in Pusan National University Hospital from June 2001 to december 2001. And the number of data was 46. We extracted liver region and nodule region from T1-weighted MR liver image. Then objective interpretation classifier of liver cirrhotic steps in T1-weighted MR liver images. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier teamed through error back-propagation algorithm. A classifying result shows that recognition rate of normal is 100%, 1type is 82.3%, 2type is 86.7%, 3type is 83.7%. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered, this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.2
• /
• pp.123-130
• /
• 2016

Purpose : The aim of this study was to compare the differences between the volumes acquired with four-dimensional computed tomography (4DCT)images with a reconstruction image-filtering algorithm and cone-beam computed tomography (CBCT) images with dynamic phantom. Materials and Methods : The 4DCT images were obtained from the computerized imaging reference systems (CIRS) phantom using a computed tomography (CT) simulator. We analyzed the volumes for maximum intensity projection (MIP), minimum intensity projection (MinIP) and average intensity projection (AVG) of the images obtained with the 4DCT scanner against those acquired from CBCT images with CT ranger tools. Results : Difference in volume for node of 1, 2 and 3 cm between CBCT and 4DCT was 0.54~2.33, 5.16~8.06, 9.03~20.11 ml in MIP, respectively, 0.00~1.48, 0.00~8.47, 1.42~24.85 ml in MinIP, respectively and 0.00~1.17, 0.00~2.19, 0.04~3.35 ml in AVG, respectively. Conclusion : After a comparative analysis of the volumes for each nodal size, it was apparent that the CBCT images were similar to the AVG images acquired using 4DCT.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.101-109
• /
• 2014

It is an essential element for the establishment of image processing related systems to find the exact contour from the image of an arbitrary object. In particular, if a vision system is established to inspect the products in the automated production process, it is very important to detect the contours for standardized shapes such lines and curves. In this paper, we propose a prototype adaptive dynamic contour model, p-Snake with improved contour extraction algorithms by adding the prototype energy. The proposed method is to find the initial contour by applying the existing Snake algorithm after Sobel operation is performed for prototype analysis. Next, the final contour of the object is detected by analyzing prototypes such as lines and circles, defining prototype energy and using it as an additional energy item in the existing Snake function on the basis of information on initial contour. We performed experiments on 340 images obtained by using an environment that duplicated the background of an industrial site. It was found that even if objects are not clearly distinguished from the background due to noise and lighting or the edges being insufficiently visible in the images, the contour can be extracted. In addition, in the case of similarity which is the measure representing how much it matches the prototype, the prototype similarity of contour extracted from the proposed p-ACM is superior to that of ACM by 9.85%.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.339-349
• /
• 2018

The massive green tide occurred every summer in the Yellow Sea since 2008, and many studies are being actively conducted to estimate the coverage of green tide through analysis of satellite imagery. However, there is no satellite images selection criterion for accurate coverage calculation of green tide. Therefore, this study aimed to find a suitable satellite image from for the comparison of the green tide coverage according to the spatial resolution of satellite image. In this study, Landsat ETM+, MODIS and GOCI images were used to coverage estimation and its spatial resolution is 30, 250 and 500 m, respectively. Green tide pixels were classified based on the NDVI algorithm, the difference of the green tide coverage was compared with threshold value. In addition, we estimate the proportion of the green tide in one pixel through the Linear Spectral Unmixing (LSU) method, and the effect of the difference of green tide ratio on the coverage calculation were evaluated. The result of green tide coverage from the calculation of the NDVI value, coverage of green tide usually overestimate with decreasing spatial resolution, maximum difference shows 1.5 times. In addition, most of the pixels were included in the group with less than 0.1 (10%) LSU value, and above 0.5 (50%) LSU value accounted for about 2% in all of three images. Even though classified as green tide from the NDVI result, it is considered to be overestimated because it is regarded as the same coverage even if green tide is not 100% filled in one pixel. Mixed-pixel problem seems to be more severe with spatial resolution decreases.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.117-125
• /
• 2008

The Object tracking by real-time image analysis is one of the major concerns in computer vision and its application fields. The Object detection process of real-time images must be preceded before the object tracking process. To achieve the stable object detection performance in the exterior environment, adaptive background model generation methods are needed. The adaptive background model can accept the nature's phenomena changes and adapt the system to the changes such as light or shadow movements that are caused by changes of meridian altitudes of the sun. In this paper, we propose a robust background model generation method effective in an illegal parking auto-detection application area. We also provide a evaluation method that judges whether a moving vehicle stops or not. As the first step, an initial background model is generated. Then the differences between the initial model and the input image frame is used to trace the movement of object. The moving vehicle can be easily recognized from the object tracking process. After that, the model is updated by the background information except the moving object. These steps are repeated. The experiment results show that our background model is effective and adaptable in the variable exterior environment. The results also show our model can detect objects moving slowly. This paper includes the performance evaluation results of the proposed method on the real roads.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.6
• /
• pp.117-129
• /
• 2021

The movement of animals is one of the primary factors that influence the variation of livestock emissions. This study evaluated the relationship between animal activity and three major emissions, PM₁₀, PM_2.5, and ammonia gas, in weaning, growing, and fattening pig houses through continuous monitoring of the animal activity. The movement score of animals was quantified by the developed image analysis algorithm using 10-second video clips taken in the pig houses. The calculated movement scores were validated by comparison with six activity levels graded by an expert group. A comparison between PMs measurement and the movement scores demonstrated that an increase of the PMs concentrations was obviously followed by increased movement scores, for example, when feeding started. The PM₁₀ concentrations were more affected by the animal activity compared to the PM_2.5 concentrations, which were related to the inflow of external PM_2.5 due to ventilation. The PM₁₀ concentrations in the fattening house were 1.3 times higher than those in the weaning house because of the size of pigs while weaning pigs were more active and moved frequently compared to fattening pigs showing 2.45 times higher movement scores. The results also indicated that indoor ammonia concentration was not significantly influenced by animal activity. This study is significant in the sense that it could provide realistic emission factors of pig farms considering animal's daily activity levels if further monitoring is carried out continuously.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.155-166
• /
• 2021

Most object detection algorithms are studied based on RGB images. Because the RGB cameras are capturing images based on light, however, the object detection performance is poor when the light condition is not good, e.g., at night or foggy days. On the other hand, high-quality infrared(IR) images regardless of weather condition and light can be acquired because IR images are captured by an IR sensor that makes images with heat information. In this paper, we performed the object detection algorithm based on the compression ratio in RGB and IR images to show the detection capabilities. We selected RGB and IR images that were taken at night from the Free FLIR Thermal dataset for the ADAS(Advanced Driver Assistance Systems) research. We used the pre-trained object detection network for RGB images and a fine-tuned network that is tuned based on night RGB and IR images. Experimental results show that higher object detection performance can be acquired using IR images than using RGB images in both networks.

• Journal of radiological science and technology
• /
• v.44 no.2
• /
• pp.91-100
• /
• 2021

High-Resolution thoracic CT (HRCT) is a scanning protocol in which thin slice thickness and sharpness algorithm are utilized to enhance image resolution for diagnosis and assessment of interstitial lung disease (ILD). This examination is sometimes performed in both supine and prone position to improve sensitivity to early changes of these conditions. Anatomical structures (the size of lung field and heart and descending aorta) of 150 patients who underwent HRCT were retrospectively compared. HRCT had been conducted in two positions (supine and prone). Data were divided into five groups according to patient body weights (from 40 to more than 80kg, 10kg intervals, 60 patients/each group). Quantitative analysis was utilized in Image J program. In the supine position defined as the control group, the average values of lung fields and heart size and aorta were compared with the prone position defined as the experimental group. The size of the lungs was found to be higher in the supine position, and it was confirmed that there was a statistically significant difference in patients over 70 kg (p<0.05). In addition, both sizes of the heart and descending aorta were larger in prone position, but in the case of the heart, there was no correlation with the presence or absence of ILD disease (p>0.05). Also, the area of prone in the descending aorta was higher than supine position, but there was no statistically significant difference between supine and prone position (p>0.05). In conclusion, when the severity of ILD disease was severe, there was no statistically significant difference in the area difference between supine and prone position, so it is considered that it will be helpful in diagnostic decision.