• Journal of The Korean Association of Information Education
• /
• v.8 no.3
• /
• pp.365-372
• /
• 2004

The purpose of this study is to develop FVU, which enables teachers effectively to construct self-page on the screen, to reduce the size of file for teaching, and to correct many different kinds of event which was already made in the previous. The instrument used in the development of this Editor is UML(Unified Modeling Language), which is object-oriented methodology. The Authoring tool developed in this study is named FVU. The first page which is needed in class can be constructed by using VUEditor in FVU. Using VUEditor can get Instructional Syllabus exported into VUAuthor through Vector-transformation. Through this procedure, the size of image file comes to be reduced into forming low band width, which results in solving the problem of network traffic. Also, Instructor can create image, shape and text, and delete and correct errors or mistakes which make in the course of constructing materials for teaching. In conclusion, this VUEditor enables program designer to construct the first page, even without using such applied program as Image Tool and Power Point. This VUEditor makes instructor to make some contents for teaching easily.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1480-1489
• /
• 1999

In this paper, we propose a new post-processing method which can solve a problem of MSDS(Mean Squared Difference of Slope) method. Using that method the blocking artifacts can significantly be reduced without any restriction, which is a major drawback of block-based DCT compression method. In this approach, the OSLD(Overlapped Sub-Laplacian Distribution) of dequantized block boundary pixel difference values is defined and used to categorize each block of an image into one of four types. Those types are also classified into one of two classes: an edge and a non-edge classes. A slope across the block boundary is used to quantify discontinuity of the image. If an absolute estimated quantization error value of a DCT coefficient is greater than the corresponding quantization step size, it is saturated to the step size in the edge class. The proposed post-processing method can improve not only the PSNR value up to 0.1~O.3 dB but visual quality without any constraints determined by ad-hoc manner.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.375-382
• /
• 2010

In this paper, we propose the simplified and improved system of One Color Detector to protect color distortion of simple color images in the processed of Auto White Balance (AWB). The proposed One Color Detector is based on Grayworld algorithm which controls color compensation except one color in simple image and widely applies for mobile phone camera because of high efficiency. This system can be suitable for diverse image size, and let user control the threshold in diverse size and environments compared with conventional system. Also the hardware size of the proposed system is reduced by 80% over that of the conventional one.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2127-2134
• /
• 2007

The electronic learning helped a learner to overcome the time restriction by providing mobility, instantly and flexibility but the restriction in connection with space on cable computer remained unsolved. Accordingly, the electronic learning has tendency to change into mobile learning environment which allows a learner to overcome time and spatial restriction. However, these mobile devices have a limitation to awareness of learning contents provided over the realtime video movie due to its small display size. Therefore, this paper suggests a technique according to the following priority: for a real time learning image, extract region of study for region of interest, rescale the real time image to its proper size suitable for the display device, and then make it displayed on a wireless PDA. As a result of the experiment, we reduced the calculating time by sampling the field centering on learning contents adaptively and computing the field best suited for device size of the user effectively.

• Fashion & Textile Research Journal
• /
• v.18 no.5
• /
• pp.637-646
• /
• 2016

The goal of this study is to provide basic data on developing circular knit basic pattern for women in their 20's. Production conditions of circular knit product pattern making among domestic women's apparel industry was researched, and collected data on sizes and ease amounts from woven and circular knit pattern were compared and analyzed. According to the result of the survey, product measurements adjusted to the actual body size fit for the brand's image were used, and the common problem among manufacturers and consumers regarding circular knit products turned out to be change in size and form due to stretching. For the basic pattern of circular knit, stretching quality was reflected in the woven basic pattern based on plain stitch(single knit) and then dart was removed and ease amount was reduced. The result of looking into size and ease amount about woven and circular knit torso & sleeve block shows that there is a significant difference among chest circumference, hip circumference, bi-shoulder length, interscye back, interscye front, scye depth, upper arm circumference and wrist circumference, and it was clear that circumference and width on the areas around the wrist tended to fit around the body more when circular knit was used instead of woven fabric.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.724-732
• /
• 2001

In this paper, a new method of feature extraction of major objects to represent an image using Vector Quantization(VQ) is proposed. The principal features of the image, which are used in a content-based image retrieval system, are color, texture, shape and spatial positions of objects. The representative color and texture features are extracted from the given image using VQ(Vector Quantization) clustering algorithm with a general feature extraction method of color and texture. Since these are used for content-based image retrieval and searched by objects, it is possible to search and retrieve some desirable images regardless of the position, rotation and size of objects. The experimental results show that the representative feature extraction time is much reduced by using VQ, and the highest retrieval rate is given as the weighted values of color and texture are set to 0.5 and 0.5, respectively, and the proposed method provides up to 90% precision and recall rate for 'person'query images.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.8
• /
• pp.31-39
• /
• 2010

The paper proposes the median filter based Retinex algorithm to detect the lanes in a foggy image. Whether an input image is foggy or not is determined by analyzing the histogram in the pre-defined ROI(Region of Interest). If the image is determined as a foggy one, then it is improved by the median filter based Retinex algorithm. By replacing the Gaussian filter by the median filter in the Retinex algorithm, the processing time can be reduced and the lane features can be detected more robustly. Once the enhanced image is acquired, the binarization based on multi-threshold and the labeling operations are applied. Finally, it detects the lane information using the size and direction parameters of the detected lane features. The proposed algorithm has been evaluated by using various foggy images collected on different road conditions to prove that it detects lanes more robustly in most cases than the conventional methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.2
• /
• pp.82-89
• /
• 2013

A detection method of high precision digital line within image is proposed in this paper. If we set the size of image to $N{\times}N$, in fact it is difficult to use the resulting values that the amount of computation is $O(N^4)$. Multiple algorithms are examined to reduced the amount of computation to $O(N^3)$, while suppressing the degradation of precision. How to detect line from the image processing, after stretching treatment of line segments extracted by Hough transform in the local area of an image is a great way to be able to detect several long or short line at high speed, but this method is slightly less precision in the detection of tilted line segments. In this paper, a line detection method improving the precision detection of tilted line segment is applied to the local area, thereby this method does not reduce the processing speed, while it is high precision method for detecting line segments. The experimental results confirm that the proposed method can detect a high precision line in a shorter period of time, compared with the existing methods.