• International journal of advanced smart convergence
• /
• 제4권2호
• /
• pp.84-93
• /
• 2015

This study is for the development of Cover Glass Grinding Processing System. This system is developed for manufacturing a mass product system grinding cover glasses with highly precise mechanism, and we improved resulted quality. In the development process, we developed a complete process technology through mechanical design, image processing technology, spindle control, mark identification algorithm etc. With this cover glass grinding development, we could developed process technology, image processing technology, organization mechanisms and control algorithms.

• 대한원격탐사학회지
• /
• 제28권4호
• /
• pp.369-392
• /
• 2012

현재까지 초분광영상을 위한 다양한 표적탐지 알고리즘이 개발 및 사용되고 있다. 그러나 표적탐지 알고리즘의 비교 및 검증 기준으로 1~2가지 영상에 적용한 탐지정확도 만을 사용하고 있어, 사용자 입장에서 그 적용성을 평가하는 데에는 한계가 있다. 본 연구의 목적은 초분광영상에 대한 표적탐지 알고리즘의 적용성을 체계적으로 분석하는 것이다. 이를 위하여 표적, 배경, 영상의 분광적 또는 복사적 특성에 관련된 5가지 기준 인자들을 정의하였고, 각 인자의 변이에 따른 6가지 기존 표적탐지 알고리즘의 탐지정확도 변화를 비교하였다. 이와 더불어 영상 크기에 따른 각 알고리즘의 처리시간을 비교하였다. 그 결과 탐지정확도 측면에서는 기준인자에 따라 적용성이 높은 알고리즘의 종류가 다르게 나타났다. 처리시간은 2차 통계값 기반 알고리즘이 다른 알고리즘에 비해 매우 크게 나타났다. 탐지정확도와 처리시간을 종합적으로 고려한 결과 사용하는 영상과 표적 그리고 배경의 특성에 따라 적용성이 높은 알고리즘의 종류가 다른 것으로 나타났다. 따라서 초분광영상에 대한 기존 표적탐지 알고리즘의 적용성은 자료의 특성 및 배경과 표적의 공간적 분광적 관계에 따라 다르게 나타나므로, 사용하는 자료의 특성과 목적에 따라 적용하는 표적탐지 알고리즘의 종류가 달라질 필요가 있다.

• 대한전기학회논문지
• /
• 제37권11호
• /
• pp.804-815
• /
• 1988

Real-time image processing algorithms to detect position and orientation of rectangular type electronic components are developed. The position detection algorithm is implemented with the use of projection method which is insensitive to noise. Also dynamic thresholding method of projection is employed in order to distinguish between the boundary of a component and any marking on the component. The orientation is determined by Hough transform of boundary candidates of a component, which is obtained a priori by a simple edge detection method. For real-time processing of both position and orientation for a component which is not aligned well, parallel processing method of image data is proposed and tested in real-time.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.427-430
• /
• 2019

Object detection is applied in various field. Autonomous driving, surveillance, OCR(optical character recognition) and aerial image etc. We will look at the algorithms that are using to object detect. These algorithms are divided into two methods. The one is R-CNN algorithms [2], [5], [6] which based on region proposal. The other is YOLO [7] and SSD [8] which are one stage object detector based on regression/classification.

• 반도체디스플레이기술학회지
• /
• 제10권1호
• /
• pp.113-118
• /
• 2011

This paper proposes computer visual inspection algorithms for PCB defects which are found in a manufacturing process. The proposed method can detect open circuit and short circuit on bare PCB without using any reference images. It performs adaptive threshold processing for the ROI (Region of Interest) of a target image, median filtering to remove noises, and then analyzes connected components of the binary image. In this paper, the connected components of circuit pattern are defined as 6 types. The proposed method classifies the connected components of the target image into 6 types, and determines an unclassified component as a defect of the circuit. The analysis of the original target image detects open circuits, while the analysis of the complement image finds short circuits. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.60-67
• /
• 2020

Recently, artificial intelligence related technologies including machine learning are being applied to various fields, and the demand is also increasing. In particular, with the development of AR, VR, and MR technologies related to image processing, the utilization of computer vision based on deep learning has increased. The algorithms for object recognition and detection based on deep learning required for image processing are diversified and advanced. Accordingly, problems that were difficult to solve with the existing methodology were solved more simply and easily by using deep learning. This paper introduces various deep learning-based object recognition and extraction algorithms used to detect and recognize various objects in an image and analyzes the technologies that attract attention.

• Journal of information and communication convergence engineering
• /
• 제8권4호
• /
• pp.405-410
• /
• 2010

Image processing operations like smoothing and edge detection, and many more are very widely used in areas like Computer Vision. We classify the image processing domain as seven branches-image acquirement and output, image coding and compression, image enhancement and restoration, image transformation, image segmentation, image description, and image recognition and description. We implemented algorithms of gaussian smoothing, laplace sharpening, image contrast effect, image black and white effect, image fog effect, image bright and dark effect, image median filter, and canny edge detection. Such experimental results show the figures respectively.

• 전기학회논문지
• /
• 제63권1호
• /
• pp.173-178
• /
• 2014

In this study, the new color image processing algorithms with an android-based mobile device are developed to detect the abnormal color densities in a skin image and interpret them as the vitiligo lesions. Our proposed method is firstly based on transforming RGB data into HSI domain and segmenting the imag into the vitiligo-skin candidates by applying Otsu's threshold algorithm. The structure elements for morphological image processing are suggested to delete the spurious regions in vitiligo regions and the image blob labeling algorithm is applied to compare RGB color densities of the abnormal skin region with them of a region of interest. Our suggested color image processing algorithms are implemented with an android-platform smartphone and thus a mobile device can be utilized to diagnose or monitor the patient's skin conditions under the environments of pervasive healthcare services.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1984년도 춘계학술발표회논문집
• /
• pp.13-17
• /
• 1984

A hybrid version of the Hadamard and center Line Symmetric Haar Transform called H-CLSH is defined and developed. Efficient algorithms for fast computation of the H-CLSH and its inverse are developed. The H-CLSH is applied to digital signal and image processing and its utility and image processing and its utility and effectiveness are compared with Hadamard-Haar discrete transforms on the basis of some standard performance criteria.

• 전기전자학회논문지
• /
• 제22권4호
• /
• pp.948-952
• /
• 2018

Haze removal is an object of scientific desire due to its various practical applications. Existing algorithms are founded upon histogram equalization, contrast maximization, or the growing trend of applying machine learning in image processing. Since machine learning-based algorithms solve problems based on the data, they usually perform better than those based on traditional image processing/computer vision techniques. However, to achieve such a high performance, one of the requisites is a large and reliable training database, which seems to be unattainable owing to the complexity of real hazy and haze-free images acquisition. As a result, researchers are currently using the synthetic database, obtained by introducing the synthetic haze drawn from the standard uniform distribution into the clear images. In this paper, we propose the enhanced equidistribution, improving upon our previous study on equidistribution, and use it to make a new database for training machine learning-based haze removal algorithms. A large number of experiments verify the effectiveness of our proposed methodology.