• Journal of Korea Multimedia Society
• /
• v.23 no.11
• /
• pp.1361-1371
• /
• 2020

Fonts have developed as a visual element, and their influence has rapidly increased around the world. Research on font automation is actively being conducted mainly in English because Hangul is a combination character and the structure is complicated. In the previous study to solve this problem, the stroke element of the character was automatically extracted by applying the object detection by component. However, the previous research was only for similarity, so it was tested on various print style fonts, but it has not been tested on other characters. In order to extract the stroke elements of all characters and fonts, we performed a performance analysis experiment according to the expansion character in the Hangul stroke element extraction training. The results were all high overall. In particular, in the font expansion type, the extraction success rate was high regardless of having done the training or not. In the character expansion type, the extraction success rate of trained characters was slightly higher than that of untrained characters. In conclusion, for the perfect Hangul stroke element extraction model, we will introduce Semi-Supervised Learning to increase the number of data and strengthen it.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.34.1-34
• /
• 2002

1. Introduction 2. Focus of Expansion 3. Log-Polar Mapping 4. Egomotion and Optical Flow 5. Experimental Results 6. Conclusion. References.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.630-632
• /
• 2012

Contemporary society has evolved in the digital information age. Because of this, use of various digital images has been increased. To process these images, various digital image processing methods are used. Edge detection methods, one of those, are utilized to various areas of application such as object recognition, line detection. To detect edge, there are many methods such as Sobel, Prewitt, Laplacian. Because images which are dealt with existing methods are processed in same methods regardless the distribution of gray-level in image, edge detection property is insufficient. Therefore, In this study, to improve shortcomings of existing methods an algorithm using modified expansion mask is proposed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.167-175
• /
• 2022

With the recent expansion of electric kickboards and bicycle sharing services, more and more people use them. In addition, the rapid growth of the delivery business due to the COVID-19 has significantly increased the use of two-wheeled vehicles and personal mobility. As the accident rate increases, the rule related to the two-wheeled vehicles is changed to 'mandatory helmets for kickboards and single-person transportation' and was revised to prevent boarding itself without driver's license. In this paper, we propose a wearable smart safety equipment, called SafetyHelmet, that can keep helmet-wearing duty and lower the accident rate with the communication between helmets and mobile devices. To make this function available, we propose a safe driving assistance function by notifying the driver when an object that interferes with driving such as persons or other vehicles are detected by applying the YOLO v5 object detection algorithm. Therefore it is intended to provide a safer driving assistance by reducing the failure rate to identify dangers while driving single-person transportation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.770-772
• /
• 2013

Edges on the images are widely used in preprocessing in various areas including recognition and detection of the object. As generally known edge detection methods, there is a method using mask and these methods are Sobel, Prewitt, Roberts, Laplacian operator and etc. Implementation of these existing edge detection methods is simple. However, when processing the impulse noise added images, the properties of edge detection is not sufficient. Accordingly, in order to compensate for the weakness of existing edge detection methods and to detect strong edges on the images which were damaged by impulse noise, the edge detection algorithm using transformed mask was proposed in this paper.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.1
• /
• pp.77-85
• /
• 2018

This paper proposes a robust digital video stabilization algorithm to extract and track an object, which uses a phase correlation-based motion correction. The proposed video stabilization algorithm consists of background stabilization based on motion estimation and extraction of a moving object. The motion vectors can be estimated by calculating the phase correlation of a series of frames in the eight sub-images, which are located in the corner of the video. The global motion vector can be estimated and the image can be compensated by using the multiple local motions of sub-images. Through the calculations of the phase correlation, the motion of the background can be subtracted from the former frame and the compensated frame, which share the same background. The moving objects in the video can also be extracted. In this paper, calculating the phase correlation to track the robust motion vectors results in the compensation of vibrations, such as movement, rotation, expansion and the downsize of videos from all directions of the sub-images. Experimental results show that the proposed digital image stabilization algorithm can provide continuously stabilized videos and tracking object movements.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.104-112
• /
• 2016

The Adaboost chooses a good set of features in rounds. On each round, it chooses the optimal feature and its threshold value by minimizing the weighted error of classification. The involved process of classification performs a hard decision. In this paper, we expand the process of classification to a soft fuzzy decision. We believe this expansion could allow some flexibility to the Adaboost algorithm as well as a good performance especially when the size of a training data set is not large enough. The typical Adaboost algorithm assigns a same weight to each training datum on the first round of a training process. We propose a new algorithm to assign different initial weights based on some statistical properties of involved features. In experimental results, we assess that the proposed method shows higher performance than the traditional one.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.687-690
• /
• 2017

Edge detection is an important step in determining the performance of lane recognition, object and pattern detection, and so on. And much research has been done until now. Sobel, Prewitt, Roberts, and Canny edge detection algorithms are widely known. However, these algorithms are often judged to be a non-edge region when processing a smooth change in brightness value. Therefore, in this paper, edge detection algorithm using gray-level morphology using erosion, expansion, open and close in the mask area. is proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1026-1031
• /
• 2021

With the development of global automotive technology and the expansion of market size, demand for vehicles is increasing, which is leading to a decrease in the number of passengers on the road and an increase in the number of vehicles on the road. This causes traffic jams, and in order to solve these problems, the number of illegal vehicles continues to increase. Various technologies are being studied to crack down on these illegal activities. Previously developed systems use trigger equipment to recognize vehicles and photograph vehicles using infrared cameras to detect the number of passengers on board. In this paper, we propose a vehicle occupant detection system with deep learning model techniques without exploiting existing system-applied trigger equipment. The proposed technique proposes a system to detect vehicles by establishing triggers within images and to apply deep learning object recognition models to detect real-time boarding personnel.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.1
• /
• pp.55-62
• /
• 2004

The computer security is considered important due to the side effect generated from the expansion of computer network and rapid increase of the use of internet. Therefore, Intrusion detection system has been an active research area to reduce the risk from intruders. A number of advantages of using mobile agent computing paradigms have been Proposed. These advantages include : overcoming network latency, reducing network load, executing asynchronously and autonomously, adapting dynamically, and operating in heterogeneous environments. Many information security models have been proposed to mitigate agent-to-agent. agent-to-platform, and platform-to-agent element risks . In these paper, We have an object which is that through intrusion detection system development, the mobile agent is managed and through the analysis of performance data. the best environment is served.