• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.67-75
• /
• 2023

Recently, many studies have been conducted on ways to utilize AI technology in NIDS (Network Intrusion Detection System). In particular, CNN-based NIDS generally shows excellent performance. CNN is basically a method of using correlation between pixels existing in an image. Therefore, the method of generating an image is very important in CNN. In this paper, the performance comparison of CNN-based NIDS according to the image generation method was performed. The image generation methods used in the experiment are a direct conversion method and a one-hot encoding based method. As a result of the experiment, the performance of NIDS was different depending on the image generation method. In particular, it was confirmed that the method combining the direct conversion method and the one-hot encoding based method proposed in this paper showed the best performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11C
• /
• pp.1116-1124
• /
• 2005

We investigated the mean and variance of the MSE and the MI-based image registration methods that have been widely applied for image registration. By using the first order Taylor series expansion, we have approximated the mean and the variance for one-dimensional image registration. The asymptotic results show that the MSE based method is unbiased and efficient for the same image registration problem while the MI-based method shows larger variance. However, for the different modality image registration problem, the MSE based method is largely biased while the MI based method still achieves registration. The results imply that the MI based method achieves robustness to the different image modalities at the cost of inefficiency. The analytical results are supported by simulation results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.7
• /
• pp.664-670
• /
• 2007

This study deals with image-based visual servoing for automatic recharging of mobile robot. Because mobile robot must be recharged periodically, it is necessary to detect and move to docking station. Generally, laser scanner is used for detect of position of docking station. CCD Camera is also used for this purpose. In case of using cameras, the position-based visual servoing method is widely used. But position-based visual servoing method requires the accurate calibration and it is hard and complex work. Another method using cameras is image-based visual servoing. Recently, image based visual servoing is widely used for robotic application. But it has a problem that cannot have linear trajectory in the 3-dimensional space. Because of this weak point, image-based visual servoing has a limit for real application. In case of 2-dimensional movement on the plane, it has also similar problem. In order to solve this problem, we point out the main reason of the problem of the resolved rate control method that has been generally used in the image-based visual servoing and we propose an image-based visual servoing method that can reduce the curved trajectory of mobile robot in the cartesian space.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.2
• /
• pp.165-172
• /
• 2020

There is growing interest in Vision-based video image matching owing to the constantly developing technology of unmanned-based systems. The purpose of this paper is the development of a fast and effective matching technique for the UAV oblique video image. We first extracted initial matching points using NCC (Normalized Cross-Correlation) algorithm and improved the computational efficiency of NCC algorithm using integral image. Furthermore, we developed a triangulation-based outlier removal algorithm to extract more robust matching points among the initial matching points. In order to evaluate the performance of the propose method, our method was quantitatively compared with existing image matching approaches. Experimental results demonstrated that the proposed method can process 2.57 frames per second for video image matching and is up to 4 times faster than existing methods. The proposed method therefore has a good potential for the various video-based applications that requires image matching as a pre-processing.

• Journal of information and communication convergence engineering
• /
• v.8 no.2
• /
• pp.185-190
• /
• 2010

In this paper we propose the CBIR algorithm which is based on a novel image block method that combined both color and edge feature. The main drawback of global histogram representation is dependent of the color without spatial or shape information, a new image block method that divided the image to 8 related blocks which contained more information of the image is utilized to extract image feature. Based on these 8 blocks, histogram equalization and edge detection techniques are also used for image retrieval. The experimental results show that the proposed image block method has better ability of characterizing the image contents than traditional block method and can perform the retrieval system efficiently.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.275-288
• /
• 2023

Many image edge details are easily lost in the image denoising process, and the smooth image regions are prone to produce jagged. In this paper, we propose a wavelet-based image global k- singular value decomposition variational method to remove image noise. A layer of wavelet decomposition is applied to the noisy image first. Then, the image global k-singular value decomposition (IGK-SVD) method is used to remove the random noise of low-frequency components. Furthermore, a constructed variational denoising method (VDM) removes the random noise in the high-frequency component. Finally, the denoised image is obtained by wavelet reconstruction. The experimental results show that the proposed method's peak signal-to-noise ratio (PSNR) value is higher than other methods, and its structural similarity (SSIM) value is closer to one, indicating that the proposed method can effectively suppress image noise while retaining more image edge details. The denoised image has better denoising effects.

• Journal of the Korean Society of Industry Convergence
• /
• v.18 no.2
• /
• pp.90-98
• /
• 2015

This research propose with image-based visual a new approach to design a feedback control of mobile robot. because mobile robot must be recharged periodically, it is necessary to detect and move to docking station. Generally, laser scanner is used for detect of position of docking station. CCD Camera is also used for this purpose. In case of using camera, the position-based visual servoing method is widely used. But position-based visual servoing method requires the accurate calibration and it is hard and complex work. Another method using cameras is inmage-based visual feedback. Recently, image based visual feedback is widely used for robotic application. But it has a problem that cannot have linear trajectory in the 3-dimensional space. Because of this weak point, image-based visual servoing has a limit for real application. in case of 2-dimensional movement on the plane, it has also similar problem. In order to solve this problem, we point out the main reason of the problem of the resolved rate control method that has been generally used in the image-based visual servoing and we propose an image-based visual feedback method that can reduce the curved trajectory of mobile robot in th cartesian space.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.862-864
• /
• 2003

Thresholding is a popular image segmentation method that converts a gray-level image into a binary image. The selection of optimum threshold has remained a challenge over decades. Many image segmentation techniques are developed using information about image in other space rather than the image space itself. Most of the technique based on histogram analysis information-theoretic approaches. In this paper, the criterion function for finding optimal threshold is developed using an intensity-based classuncertainty (a histogram-based property of an image) and region-homogeneity (an image morphology-based property). The theory of the optimum thresholding method is based on postulates that objects manifest themselves with fuzzy boundaries in any digital image acquired by an imaging device. The performance of the proposed method is illustrated on experimental data obtained by W-band millimeter-wave radiometer image under different noise level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1760-1778
• /
• 2018

For image segmentation with intensity inhomogeneity, many region-based level set methods have been proposed. Some of them however can't get the relatively ideal segmentation results under the severe intensity inhomogeneity and weak edges, and without use of the image gradient information. To improve that, we propose a new level set method combined with local direction gradient in this paper. Firstly, based on two assumptions on intensity inhomogeneity to images, the relationships between segmentation objects and image gradients to local minimum and maximum around a pixel are presented, from which a new pixel classification method based on weight of Euclidian distance is introduced. Secondly, to implement the model, variational level set method combined with image spatial neighborhood information is used, which enhances the anti-noise capacity of the proposed gradient information based model. Thirdly, a new diffusion process with an edge indicator function is incorporated into the level set function to classify the pixels in homogeneous regions of the same segmentation object, and also to make the proposed method more insensitive to initial contours and stable numerical implementation. To verify our proposed method, different testing images including synthetic images, magnetic resonance imaging (MRI) and real-world images are introduced. The image segmentation results demonstrate that our method can deal with the relatively severe intensity inhomogeneity and obtain the comparatively ideal segmentation results efficiently.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.2057-2062
• /
• 2024

Among photon counting detector (PCD)-based technologies, the K-edge subtraction (KES) method has a very high material decomposition efficiency. Yet, since the increase in noise in the X-ray image to which the KES method is applied is inevitable, research on image quality improvement is essential. Here, we modeled a block-matching and 3D filtering (BM3D) algorithm and applied it to PCD-based X-ray images with the improved KES (IKES) method. For PCD modeling, Monte Carlo simulation was used, and a phantom composed of iodine substances with different concentrations was designed. The IKES method was modeled by adding a log term to KES, and the X-ray image used for subtraction was obtained by applying the 3.0 keV range based on the K-edge region of iodine. As a result, the IKES image using the BM3D algorithm showed the lowest normalized noise power spectrum value. In addition, we confirmed that the contrast-to-noise ratio and no-reference-based evaluation results when the BM3D algorithm was applied to the IKES image were improved by 29.36 % and 20.56 %, respectively, compared to the noisy image. In conclusion, we demonstrated that the IKES imaging technique using a PCD-based detector and the BM3D algorithm fusion technique were very efficient for X-ray imaging.