• International Journal of Advanced Culture Technology
• /
• v.9 no.2
• /
• pp.100-105
• /
• 2021

Contactless service is rapidly emerging as a new growth strategy due to consumers who are reluctant to the face-to-face situation in the global pandemic of coronavirus disease 2019 (COVID-19), and various technologies are being developed to support the fast-growing contactless service market. In particular, the restaurant industry is one of the most desperate industrial fields requiring technologies for contactless service, and the representative technical case should be a kiosk, which has the advantage of reducing labor costs for the restaurant owners and provides psychological relaxation and satisfaction to the customer. In this paper, we propose a solution to the restaurant's store operation through the unmanned kiosk using a state-of-the-art artificial intelligence (AI) technology of image recognition. Especially, for the products that do not have barcodes in bakeries, fresh foods (fruits, vegetables, etc.), and autonomous restaurants on highways, which cause increased labor costs and many hassles, our proposed system should be very useful. The proposed system recognizes products without barcodes on the ground of image-based AI algorithm technology and makes automatic payments. To test the proposed system feasibility, we established an AI vision system using a commercial camera and conducted an image recognition test by training object detection AI models using donut images. The proposed system has a self-learning system with mismatched information in operation. The self-learning AI technology allows us to upgrade the recognition performance continuously. We proposed a fully automated payment system with AI vision technology and showed system feasibility by the performance test. The system realizes contactless service for self-checkout in the restaurant business area and improves the cost-saving in managing human resources.

• Progress in Medical Physics
• /
• v.31 no.3
• /
• pp.111-123
• /
• 2020

Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.171-181
• /
• 2011

Proposed in this paper is the intelligent video surveillance system to effectively detect multiple loitering objects even that disappear from the out of camera's field of view and later return to a target zone. After the background and foreground are segmented using Gaussian mixture model and shadows are removed, the objects returning to the target zone is recognized using the chromaticity histogram and the duration of loitering is preserved. For more accurate measurement of the loitering behavior, the camera calibration is also applied to map the image plane to the real-world ground. Hence, the loitering behavior can be detected by considering the time duration of the object's existence in the real-world space. The experiment was performed using loitering video and all of the loitering behaviors are accurately detected.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.187-192
• /
• 2021

This study proposes a system for take-off in a forest or similar complex environment using an object detector. In the simulator, a raspberry pi is mounted on a quadcopter with a length of 550mm between motors on a diagonal line, and the experiment is conducted based on edge computing. As for the images to be used for learning, about 150 images of 640⁎480 size were obtained by selecting three points inside Kunsan University, and then converting them to black and white, and pre-processing the binarization by placing a boundary value of 127. After that, we trained the SSD_Inception model. In the simulation, as a result of the experiment of taking off the drone through the model trained with the verification image as an input, a trajectory similar to the takeoff was drawn using the label.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Atmosphere
• /
• v.31 no.5
• /
• pp.489-510
• /
• 2021

In this paper, we propose an algorithm for detecting convective initiation (CI) using GEO-KOMPSAT-2A/advanced meteorological imager data. The algorithm identifies clouds that are likely to grow into convective clouds with radar reflectivity greater than 35 dBZ within the next two hours. This algorithm is developed using statistical and qualitative analysis of cloud characteristics, such as atmospheric instability, cloud top height, and phase, for convective clouds that occurred on the Korean Peninsula from June to September 2019. The CI algorithm consists of four steps: 1) convective cloud mask, 2) cloud object clustering and tracking, 3) interest field tests, and 4) post-processing tests to remove non-convective objects. Validation, performed using 14 CI events that occurred in the summer of 2020 in Korean Peninsula, shows a total probability of detection of 0.89, false-alarm ratio of 0.46, and mean lead-time of 39 minutes. This algorithm can be useful warnings of rapidly developing convective clouds in future by providing information about CI that is otherwise difficult to predict from radar or a numerical prediction model. This CI information will be provided in short-term forecasts to help predict severe weather events such as localized torrential rainfall and hail.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1949-1955
• /
• 2021

With the recent COVID-19 situation, countries are seriously feeling the need for medical personnel and their technologies. PDepending on the aging society, the number of medical staff is actually decreasing, and in order to solve this problem, research is needed to replace the part that does not require high expertise among actual medical practices performed by doctors. This paper describes and proposes actual research methods related to unmanned medical systems that use various deep learning image processing-based technologies to check the recovery status applicable to rehabilitation areas where medical staff should face patients directly. The proposed method replaces passive calculations such as a protractor or a method of drawing a line in a photograph, which is the method used for actual motion comparison. Since it is performed in real time, it helps to diagnose quickly, and it is easy for medical staff to provide necessary information because data on the degree of match of motion performance can be checked.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.19-26
• /
• 2022

With the recent development of intelligent transportation systems, car license plate recognition systems are being used in various fields. Such systems need to guarantee real-time performance to recognize the license plate of a driving car. Also, they should keep a high recognition rate even in problematic situations such as small license plates in low-resolution and unclear image due to distortion. In this paper, we propose a real-time car license plate recognition system that improved processing speed using object detection algorithm based on anchor-free method and text recognition algorithm based on Convolutional Neural Network(CNN). In addition, we used Spatial Transformer Network to increase the recognition rate on the low resolution or distorted images. We confirm that the proposed system is faster than previously existing car license plate recognition systems and maintains a high recognition rate in a variety of environment and quality images because the proposed system's recognition rate is 93.769% and the processing speed per image is about 0.006 seconds.