• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.1-14
• /
• 2023

Soybeans are one of the world's top five staple crops and a major source of plant-based protein. Due to their susceptibility to climate change, which can significantly impact grain production, the National Agricultural Science Institute is conducting research on crop phenotypes through growth analysis of various soybean varieties. While the process of capturing growth progression photos of soybeans is automated, the verification, recording, and analysis of growth stages are currently done manually. In this paper, we designed and trained a YOLOv5s model to detect soybean leaf objects from image data of soybean plants and a Convolution Neural Network (CNN) model to judgement the unfolding status of the detected soybean leaves. We combined these two models and implemented an algorithm that distinguishes layers based on the coordinates of detected soybean leaves. As a result, we developed a program that takes time-series data of soybeans as input and performs growth analysis. The program can accurately determine the growth stages of soybeans up to the second or third compound leaves.

• 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%.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.327-336
• /
• 2004

For visual inspection system in real industrial environment, it is one of most important tasks to design fast and stable pattern matching algorithm. This paper presents an edge-based point correlation algorithm avoiding full search in visual inspection system. Conventional algorithms based on NGC(normalized gray-level correlation) have to overcome some difficulties for applying to automated inspection system in factory environment. First of all, NGC algorithms need high time complexity and thus high performance hardware to satisfy real-time process. In addition, lighting condition in realistic factory environments if not stable and therefore intensity variation from uncontrolled lights gives many roubles for applying directly NGC as pattern matching algorithm in this paper, we propose an algorithm to solve these problems from using thinned and binarized edge data and skipping full point search with edge-map analysis. A point correlation algorithm with the thinned edges is introduced with image pyramid technique to reduce the time complexity. Matching edges instead of using original gray-level pixel data overcomes NGC problems and pyramid of edges also provides fast and stable processing. All proposed methods are preyed from experiments using real images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.41-43
• /
• 2022

In order to prevent and block infectious diseases caused by the recent COVID-19 pandemic, non-contact biometric information acquisition and analysis technology is attracting attention. The invasive and attached biometric information acquisition method accurately has the advantage of measuring biometric information, but has a risk of increasing contagious diseases due to the close contact. To solve these problems, the non-contact method of extracting biometric information such as human fingerprints, faces, iris, veins, voice, and signatures with automated devices is increasing in various industries as data processing speed increases and recognition accuracy increases. However, although the accuracy of the non-contact biometric data acquisition technology is improved, the non-contact method is greatly influenced by the surrounding environment of the object to be measured, which is resulting in distortion of measurement information and poor accuracy. In this paper, we propose a context-based bio-signal modeling technique for the interpretation of personalized information (image, signal, etc.) for bio-information analysis. Context-based biometric information modeling techniques present a model that considers contextual and user information in biometric information measurement in order to improve performance. The proposed model analyzes signal information based on the feature probability distribution through context-based signal analysis that can maximize the predicted value probability.

• Nuclear Medicine and Molecular Imaging
• /
• v.42 no.1
• /
• pp.8-16
• /
• 2008

Purpose: To assess the effect of extracranial-intracranial (EC-IC) bypass surgery on hemodynamic improvement, we evaluated serial regional cerebral hemodynamic change of the middle cerebral artery (MCA) in symptomatic patients with atherosclerotic occlusion of the internal carotid artery (ICA) or MCA using $^{99m}Tc$-ECD acetazolamide stress brain perfusion SPECT (Acetazolamide SPECT). Materials and Methods: The patients who had suffered a recent stroke with atherosclerotic ICA or MCA occlusion underwent EC-IC bypass surgery and Acetazolamide SPECT at 1 week before and three to six months after surgery. For image analysis, attenuation corrected images were spatially normalized to SPECT templates with SPM2. Anatomical automated labeling was applied to calculate mean counts of each Volume-Of-Interest (VOI). Seven VOIs of bilateral frontal, parietal, temporal regions of the MCA territory and the ipsilateral cerebellum were defined. Using mean counts of 7 VOIs, cerebral perfusion index and perfusion reserve index were calculated. Results: Seventeen patients (M:F =12:5, mean age $53{\pm}2yr$) were finally included in the analysis. The cerebral blood flow of the parietal region increased at 1 week (p = 0.003) and decreased to the preoperative level at 3-6 months (p = 0.003). The cerebrovascular reserve of the frontal and parietal regions increased significantly at 1 week after surgery (p<0.01) and improved further at 3-6 months. Conclusion: Cerebrovascular reserve of the MCA territory was significantly improved at early postoperative period after EC-IC bypass and kept improved state during long-term follow-up, although cerebral blood flow did not significantly improved. Therefore, cerebrovascular reserve may be a good indicator of postoperative hemodynamic improvement resulted from bypass effect.

• The Journal of the Korean bone and joint tumor society
• /
• v.10 no.2
• /
• pp.113-119
• /
• 2004

Purpose: To determine the utility of sonographically guided percutaneous core needle biopsy to diagnose musculoskeletal soft tissue masses. Methods: A prospective study was performed in 55 patients referred for image-guided needle biopsy of primary or recurrent soft tissue masses and bone lesion or suspected solitary metastasis with extraosseous masses. Tissue samples were obtained with a 14-gauge or 18-gauge cutting needle coupled to an automated biopsy device under local anesthesia and sonographic guidance. Statistical analysis was based on 49 biopsies confirmed by successful clinical treatment (11 cases) or surgical resection (38 cases). Results: An accurate diagnosis was obtained in 47 (97%) of 49 biopsies; sensitivity was 95%, and specificity was 100%. The method did not yield sufficient tissue to establish a diagnosis in 6 cases. Considering all 55 biopsies, high-quality specimens were obtained in 87%. There were no serious complications. Conclusions: Sonographically guided core needle biopsy is accurate and safe, in soft tissue masses and bone tumors with extraosseous masses in the appendicular skeleton. In such patients, the sonographically guided procedure is the most prompt and effective method for obtaining tissue samples.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.12
• /
• pp.163-173
• /
• 2014

When evaluating the spatial resolution images and evaluation of low contrast resolution using CT standard phantom, and might present a automated quantitative evaluation method for minimizing errors by subjective judgment of the evaluator be, and try to evaluate the usefulness. 120kVp and 250mAs, 10mm collimation, SFOV(scan field of view) of 25cm or more than, exposure conditions DFOV(display field of view) of 25cm, and were evaluated the 24 passing images and 20 failing images taken using a standard reconstruction algorithm by using the Nuclear Associates, Inc. AAPM CT Performance Phantom(Model 76-410). Quantitative evaluation of low contrast resolution and spatial resolution was using an evaluation program that was self-developed using the company Mathwork Matlab(Ver. 7.6. (R2008a)) software. In this study, the results were evaluated using the evaluation program that was self-developed in the evaluation of images using CT standard phantom, it was possible to evaluate an objective numerical qualitative evaluation item. First, if the contrast resolution, if EI is 0.50, 0.51, 0.52, 0.53, as a result of evaluating quantitatively the results were evaluated qualitatively match. Second, if CNR is -0.0018~-0.0010, as a result of evaluating quantitatively the results were evaluated qualitatively match. Third, if the spatial resolution, as a result of using a image segmentation technique, and automatically extract the contour boundary of the hole, as a result of evaluating quantitatively the results were evaluated qualitatively match.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.5
• /
• pp.71-77
• /
• 2016

Solar energy is a viable source to replace fossil fuels. However, challenges associated with site selection for solar panel installation inhibit the uptake of solar energy systems. Expressway slopes offer a potentially attractive alternative for solar panel installation for the following reasons: expressway slopes are vacant public sites, they are abundant (about 4,193km in South Korea), and they are linear in nature. Traditoinally when selecting sites for solar systems conventional surveying methods are employed. Unfortunately, these methods can be dangerous, time consuming, and labor intensive. To overcome these limitations of conventional site selection methodologies, we propose an automated approach using numerical maps. First, contour and expressway polylines are extracted separately from numeric maps. The extracted contour lines are then converted into a digital terrain model; this is used to calculate aspect and slope information. Next, the extracted expressway lines are projected onto a binary image and refined to recover the disconnections, and then applied to create a buffer zone to narrow the search space. Finally, all data sets are overlaid to identify candidate sites for solar panel systems and are visually verified through comparisons with aerial photos.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.2
• /
• pp.133-142
• /
• 2014

Landsat is one of the popular satellites for observing land surface that is used in various areas including monitoring, detecting and classifying changes in land surface. However, shades, which cloud itself and its shadow, interrupted often clear observation and analysis of ground surface. For this reason, the process of removing shades and restoring original ground surfaces are critical for geospatial users. This study is planned to recommend a methodology for more accurate and clear images of Landsat-8 sensor, which provided two additional bands of costal/aerosol and cirrus. In fact, those bands are known as functioned effectively in detecting and restoring shades. Otsu's thresholding technique to detect clouds, we replaced those detective shades by using experimental and reference images. In accurate assessment, the overall accuracy and kappa coefficients were about 85% and 0.7128, respectively. This indicates that the proposed technique is effective for recovering the original land surface.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.