• The Korean Journal of Applied Statistics
• /
• v.20 no.1
• /
• pp.147-157
• /
• 2007

Edge detection has been widely used in computer vision and image processing. We describe a new edge detector based on the robust rank-order test which is a useful alternative to Wilcoxon test. Our method is based on detecting pixel intensity changes between two neighborhoods with a $r{\times}r$ window using an edge-height model to perform effectively on noisy images. Some experiments of our robust rank-order detector with several existing edge detectors are carried out on both synthetic images and real images with and without noise.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.218-223
• /
• 2013

The performances of previous edge detection methods such as Sobel, Prewitt, and LoG(Laplacian of Gaussian) are insufficient for images degraded in AWGN(additive white Gaussian noise). Therefore, in this paper, we proposed an edge detection algorithm using a modified coefficient masks with gradient masks and distance weight mask. In order to confirm and verify the performance of the proposed algorithm, we simulated and compared proposed algorithm to conventional methods on various standard images added AWGN with a standard deviation ${\sigma}$=15, 30 and proposed algorithm shows superior edge detection characteristics in processed images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2259-2264
• /
• 2014

For edge detection methods, there are Sobel, Prewitt, Roberts and Canny edge detector, and these methods have insufficient detection characteristics in the image corrupted by the impulse noise. Therefore in this paper, in order to improve these disadvantages of the previous methods and to effectively detect the edge in the impulse noise environment, using the $5{\times}5$ mask, the noise factors within the $3{\times}3$ mask based on the central pixel is determined, and depending on its status, for noise-free it is processed as is, and if noise is found, by obtaining the estimated mask using the adjacent pixels of each factor, an algorithm that detects the edge is proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.735-741
• /
• 2014

Edge in images appears when a great difference shows up in light and shade between pixels and includes data of the subject's size, location direction and etc. The edge is generally detected by the methods such as Sobel, Roberts, Laplacian, LoG(Laplacian of Gaussian) and etc. However, in AWGN(additive white Gaussian noise) added images, quality of the edge becomes slightly uncertain. Therefore, this paper proposed edge detection algorithm using modified mask of weighting to improve the quality of the existing methods. And in order to verify the performance efficiency of the proposed method, processed image and PFOM(Pratt's figure of merit) has been used as valuation standard for a comparison with the existing methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.5
• /
• pp.1135-1140
• /
• 2007

This paper proposes an edge-based text region detection algorithm using the adaptive character-edge maps which are independent of the size of characters and the orientation of character string in natural images. First, labeled images are obtained from edge images and in order to search for characters, adaptive character-edge maps by way grammar are applied to labeled images. Next, selected label images are clustered as for distance of its neighbors. And then, text region candidates are obtained. Finally, text region candidates are verified by using the empirical rules and horizontal/vertical projection profiles based on the orientation of text region. As the results of experiments, a text region detection algorithm turned out to be robust in the matter of various character size, orientation, and the complexity of the background.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.9-15
• /
• 2006

In this paper we propose Wilcoxon test, Median test and Van der Waerden test such as linear rank tests in two-sample location problem for detecting edges effectively in noisy images. These methods are based on detecting image intensity changes between two pixel neighborhoods using an edge-height model to perform effectively on noisy images. The neighborhood size used here is small and its shape is varied adaptively according to edge orientations. We compare and analysis the performance of these statistical edge detectors on both natural images and synthetic images with and without noise.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.103-110
• /
• 2015

In this paper, we propose a deblurring method using 1/4 selective filter. Deblurring methods require a lot of processing time for deblurring. In order to enhance execution speed, we propose a novel 1/4 selective filter. The proposed 1/4 selective filter restores major edge, but it distorts minor edge and texture. To solve this problem, we apply 1/4 selective filter to restore major edge and DOG(Difference of Gaussian) filter to restore minor edge and texture. Experimental results show that the proposed method removes the blur effectively.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.3
• /
• pp.266-270
• /
• 2004

The image interpolation is one of an image preprocessing process to heighten a resolution. The conventional image interpolation used much to concept that it put in other pixel to select the nearest value in a pixel simply, and use much the temporal object interpolation techniques to do the image interpolation by detecting motion in a moving picture presently. In this paper, it is proposed the image interpolation techniques using the fuzzy wavelet base function. This is applied to embody a correct edge image and a natural image when expand part of the still image by applying the fuzzy wavelet base function coefficient to the conventional B-spline function. And the proposal algorithm in this paper is confirmed to improve about 1.2831 than the image applying the conventional B-spline function through the computer simulation.