• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1649-1657
• /
• 2008

In this paper, to overcome the failure of binarization for the characters suffered from low contrast and non-uniform illumination in license plate character recognition system, we improved the binarization method by combining local thresholding with global thresholding and edge detection. Firstly, apply the local thresholding method to locate the characters in the license plate image and then get the threshold value for the character based on edge detector. This method solves the problem of local low contrast and non-uniform illumination. Finally, back-propagation Neural Network is selected as a powerful tool to perform the recognition process. The results of the experiments i1lustrate that the proposed binarization method works well and the selected classifier saves the processing time. Besides, the character recognition system performed better recognition accuracy 95.7%, and the recognition speed is controlled within 0.3 seconds.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.992-999
• /
• 2019

In this paper, I lay the foundation for creating a multiscale atlas that characterizes cerebrovasculature structural changes across the entire brain of a mouse in the Knife-Edge Scanning Microscopy dataset. The geometric reconstruction of the vascular filaments embedded in the volume imaging dataset provides the ability to distinguish cerebral vessels by diameter and other morphological properties across the whole mouse brain. This paper presents a means for studying local variations in the small vascular morphology that have a significant impact on the peripheral nervous system in other cerebral areas, as well as the robust and vulnerable side of the cerebrovasculature system across the large blood vessels. I expect that this foundation will prove invaluable towards data-driven, quantitative investigations into the system-level architectural layout of the cerebrovasculature and surrounding cerebral microstructures.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.488-489
• /
• 2019

We propose a method to identify vehicle type by the formula of distance between feature points of vehicle and proportional rate of size. Car images are converted from the basic RGB model to the gray color model. Perform Canny Edge Direction to remove the background image of the car. The desired feature points are obtained through contour extraction.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.124-127
• /
• 2018

넓은 동적 영역 (High Dynamic Range: HDR) 이미지는 주관적 화질 측면에서 우수하지만 대부분의 디스플레이는 좁은 동적 영역 (Low Dynamic Rang e: LDR) 만 지원이 가능하다. 본 논문에서는 이를 해결하기 위해서 톤 매핑 기법 (Tone Mapping Operator: TMO) 을 사용하여 넓은 동적 영역을 압축하여 수행한다. 기존의 지역 에지 보존 (Local Edge Preserving: LEP) 필터를 적용한 이미지결과는 에지를 보존하지만, 스케일의 분해 과정 중 디테일의 손실이 발생되었다. 본 논문에서는 이미지 변화도를 기반으로 디테일을 보존하는 알고리듬을 제안한다. LEP 필터가 적용되기 전에 이미지의 변화도와 동적 영역이 압축된 후의 이미지에 대한 변화도의 차이만큼 가중하여 디테일을 보존함으로써 주관적 화질을 향상시켰다.

• Journal of applied mathematics & informatics
• /
• v.41 no.3
• /
• pp.633-645
• /
• 2023

In this paper, Completely V-Regular on semiring is defined and used to derive new theorems with some of its properties. This paper also illustrates V-Regular algebra and Completely V-Regular Algebra with examples and properties. By extending completely V-Regular to fuzzy, a new concept, fuzzy V-Regular is brought out and fuzzy completely V-Regular algebra is introduced too. It is also developed by defining the ideals of Completely V -Regular Algebra and fuzzy completely V-Regular algebra. Finally, this fuzzy algebra concept is applied in image processing to detect edges. This V-Regular Algebra is novel in the research area.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.695-696
• /
• 2020

CNN(CNN: Convolutional Neural Network)은 컴퓨터 비전의 많은 분야에서 뛰어난 성능을 보이고 있으며, 단일 영상으로부터 깊이(depth) 추정에서도 기존 기법보다 향상된 성능을 보이고 있다. 그러나, 단일 영상으로부터 신경망이 얻을 수 있는 정보는 제한적이기 때문에 스테레오 카메라로부터 얻은 좌/우 영상으로부터의 깊이 추정보다 성능 향상에 한계가 있다. 따라서 본 논문에서는 에지 맵(edge map)을 이용한 CNN 기반의 단일 영상에서의 깊이 추정의 개선 기법을 제안한다. 제안 방법은 먼저 단일 영상에 대한 전처리를 통해서 에지 맵과 양방향 필터링된(bilateral filtered) 영상을 생성하고, 이를 CNN 입력으로 하여 기존 단일 영상 깊이 추정 기법 대비 개선된 성능을 보임을 확인하였다.

• Applied Microscopy
• /
• v.50
• /
• pp.27.1-27.6
• /
• 2020

Transition metal dichalcogenides (TMD), which is composed of a transition metal atom and chalcogen ion atoms, usually form vacancies based on the knock-on threshold of each atom. In particular, when electron beam is irradiated on a monolayer TMD such as MoS₂ and WS₂, S vacancies are formed preferentially, and they are aligned linearly to constitute line defects. And then, a hole is formed at the point where the successively formed line defects collide, and metal clusters are also formed at the edge of the hole. This study reports a process in which the line defects formed in a monolayer WS₂ sheet expends into holes. Here, the process in which the W cluster, which always occurs at the edge of the formed hole, goes through a uniform intermediate phase is explained based on the line defects and the formation behavior of the hole. Further investigation confirms the atomic structure of the intermediate phase using annular dark field scanning transition electron microscopy (ADF-STEM) and image simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4060-4079
• /
• 2020

Blur is an important type of image distortion. How to evaluate the quality of blurred image accurately and efficiently is a research hotspot in the field of image processing in recent years. Inspired by the multi-scale perceptual characteristics of the human visual system (HVS), this paper presents a no-reference image blur/sharpness assessment method based on multi-scale local features in the spatial domain. First, considering various content has different sensitivity to blur distortion, the image is divided into smooth, edge, and texture regions in blocks. Then, the Gaussian scale space of the image is constructed, and the categorized contrast features between the original image and the Gaussian scale space images are calculated to express the blur degree of different image contents. To simulate the impact of viewing distance on blur distortion, the distribution characteristics of local maximum gradient of multi-resolution images were also calculated in the spatial domain. Finally, the image blur assessment model is obtained by fusing all features and learning the mapping from features to quality scores by support vector regression (SVR). Performance of the proposed method is evaluated on four synthetically blurred databases and one real blurred database. The experimental results demonstrate that our method can produce quality scores more consistent with subjective evaluations than other methods, especially for real burred images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1507-1514
• /
• 2016

Full-image guided filter reflects all pixels of image in filtering by using weight propagation and two-pass model, whereas the existing guide filter is processed based on the kernel window. Therefore the computational complexity can be improved while maintaining characteristics of guide filter, such as edge-preserving, smoothing, and so on. In this paper, we propose an efficient VLSI architecture for the full-image guided filter by analyzing the data dependency, the data frequency and the PSNR analysis of the image in order to achieve enough speed for various applications such as stereo vision, real-time systems, etc. In addition, the proposed efficient scheduling enables the realtime process by minimizing the idle period in weight computation. The proposed VLSI architecture shows 214MHz of maximum operating frequency (image size: 384*288, 965 fps) and 76K of gates (internal memory excluded).

• Journal of Korea Multimedia Society
• /
• v.9 no.10
• /
• pp.1282-1295
• /
• 2006

This paper proposes a method of image tile mosaics to preserve detailed depiction of the source image. This method enhance the shortcoming of the previous mosaic methods that cannot express the detailed depiction because of the gap between tiles. Our method is implemented by the usage of image tiles to preserve detailed depiction of the source image, as well as the usage of 2-layered tiles to.eliminate the gap between tiles. The method suggested in this paper are composed of following process. First of all, the position of the upper layer tile is located through a centroidal voronoi diagram to which an edge avoidance technique is applied, and the position of the lower layer tile is calculated using Delaunay triangulation. Secondly, discover the size and direction field of the tile considering the relation between tiles. Thirdly, adopt a photomosaic technique to use the image tiles. At this time, the technique of multi-level indexing is used to accelerate the speed of image searching. Through above process, the gap between tiles is minimized against other methods and a mosaic image with a maximized detailed description is achieved.