• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.26-35
• /
• 2009

In this paper, we present morphology-based step region extraction and regularized iterative point-spread-function (PSF) estimation methods. The proposed PSF estimation method uses canny edge detector to extract the edge of the input image. We extract feasible vertical and horizontal edges using morphology analysis, such as the hit-or-miss transform. Given extracted edges we estimate the optimal step-response using flattening and normalization processes. The PSF is finally characterized by solving the equation which relates the optimal step response and the 2D isotropic PSF. We shows the restored image by the estimated PSF. The proposed algorithm can be applied a fully digital auto-focusing system without using mechanical focusing parts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2949-2955
• /
• 2015

Recently, with the sharp increase of digital visual media such as photographs, animations, and digital videos, it has been necessary to generate mosaic blocks in a static or dynamic image intentionally or unintentionally. In this paper, we suggest a new method for detecting mosaic blocks contained in a color image using boundary features. The suggested method first extracts Canny edges in the image and finds candidate mosaic blocks with the boundary features of mosaic blocks. The method then determines real mosaic blocks after filtering out non-mosaic blocks using geometric features like size and elongatedness features. Experimental results show that the proposed method can detect mosaic blocks robustly rather than other methods in various types of input images.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.67-76
• /
• 2012

This paper proposes an efficient method that helps a visually impaired person to detect a pavement borderline. A pedestrian is equipped with a camera so that the front view of a natural scene is captured. Our approach analyzes the captured image and detects the borderline of a pavement in a very robust manner. Our approach performs the task in two steps. In a first step, our approach detects a vanishing point and vanishing lines by applying an edge operator. The edge operator is designed to take a threshold value adaptively so that it can handle a dynamic environment robustly. The second step is to determine the borderlines of a pavement based on vanishing lines detected in the first step. It analyzes the vanishing lines to form VRays that confines the pavement only. The VRays segments out the pavement region in a radial manner. We compared our approach against Canny edge detector. Experimental results show that our approach detects borderlines of a pavement very accurately in various situations.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.51-58
• /
• 2012

Recently, 3D technology based on depth image is widely used in various fields including 3D space recognition, image acquisition, interaction, and games. Depth camera is used in order to produce depth image, various types of effort are made to improve quality of the depth image. In this paper, we suggests using area-based Canny edge detector to improve depth image in applying 3D technology based on depth camera. The suggested method provides improved depth image with pre-processing and post-processing by fixing image quality deterioration, which may take place in acquiring depth image in a limited environment. For objective image quality evaluation, we have confirmed that the image is improved by 0.42dB at maximum, by applying and comparing improved depth image to virtual view reference software. In addition, with DSCQS(Double Stimulus Continuous Quality Scale) evaluation method, we are reassured of the effectiveness of improved depth image through objective evaluation of subjective quality.

• Journal of Digital Contents Society
• /
• v.17 no.5
• /
• pp.441-448
• /
• 2016

In this paper, we propose a method that segments the image, extracts its slope and compensate it in the image that text and background are mixed. The proposed method uses morphology based preprocessing and extracts the edges using canny operator. And after segmenting the image which the edges are extracted, it excludes the areas which the edges are included, only uses the area which the edges are included and creates the projection histograms according to their various direction slopes. Using them, it takes a slope having the greatest edge concentrativeness of each area and compensates the slope of the scene. On extracting the slope of the mixed scene of the text and background, the method can get better results as 0.7% than the existing methods as it excludes the useless areas that the edges do not exist.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.18-25
• /
• 2016

As more people have cars, the threat of traffic accidents is posed on men and women of all ages. The main culprit of traffic accidents is driving while intoxicated or drowsy. The method to recognize and prevent the cause of traffic accidents is to use lane detection. In this study, a total of 4,000 frames (day image: 2,900 frames, night image: 1,100 frames) were used to test lane detection. According to the test, in the case of day image, when the threshold of Sobel edge detection technique was detected with second-order differential equation, there was the highest candidate lane detection rate which was 86.1%. In the threshold of Canny edge detection technique, the highest detection rate of 88.0% was found at Low=50, and High=300. In the case of night image, the threshold of Sobel edge detection technique, when horizontal calculation and vertical calculation had second-order differential equation, and when horizontal-vertical calculation had 1.5th-order differential equation, there was the highest detection rate which was 83.1%. In the threshold of Canny edge detection technique, the highest detection rate of 89.9% was found at Low=50, and High=300.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.721-740
• /
• 2019

Noise reduction is an important field in image processing and requires a statistical approach. However, it is difficult to assume a specific distribution of noise, and a spatial filter that reflects regional characteristics is a small sample and cannot be accessed in a parametric manner. The first order image differential and the second order image differential show a clear difference according to the noise level included in the image and can be more clearly understood using the canyon edge detector. The Fligner-Killeen test was performed and the bootstrap method was used to statistically check the noise level. The estimated noise level was set between 0 and 1 using the cumulative distribution function of the beta distribution. In this paper, we propose a nonparametric noise reduction algorithm that accounts for the noise level included in the image.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.217-222
• /
• 2017

Recent studies for working robot in dangerous places have been carried out on large unmanned ground vehicles or 4-legged robots with the advantage of long working time, but it is difficult to apply in practical dangerous fields which require the real-time system with high locomotion and capability of delicate working. This research shows the collaborated docking system of drone and ground vehicles which combines image processing algorithm and laser sensors for effective detection of docking markers, and is finally capable of moving a long distance and doing very delicate works. We proposed the docking system of drone and ground vehicles with sensor fusion which also suggests two template matching methods appropriate for this application. The system showed 95% docking success rate in 50 docking attempts.