• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.428-435
• /
• 2017

In this paper, we propose a novel motion field estimation algorithm for which a U-disparity map and forward-and-backward error removal are applied in a vehicular environment. Generally, a motion exists in an image obtained by a camera attached to a vehicle by vehicle movement; however, the obtained motion vector is inaccurate because of the surrounding environmental factors such as the illumination changes and vehicles shaking. It is, therefore, difficult to extract an accurate motion vector, especially on the road surface, due to the similarity of the adjacent-pixel values; therefore, the proposed algorithm first removes the road surface region in the obtained image by using a U-disparity map, and uses then the optical flow that represents the motion vector of the object in the remaining part of the image. The algorithm also uses a forward-backward error-removal technique to improve the motion-vector accuracy and a vehicle's movement is predicted through the application of the RANSAC (RANdom SAmple Consensus) to the previously obtained motion vectors, resulting in the generation of a motion field. Through experiment results, we show that the performance of the proposed algorithm is superior to that of an existing algorithm.

• The Korea Journal of Herbology
• /
• v.22 no.3
• /
• pp.39-45
• /
• 2007

Objectives : The purpose of this study is to investigate the delayed luminescence-biophoton emission from root of Angelica sinensis D., Angelica acutiloba K., and Angelica pubescens M. These three species of Genus Angelica are now imported from other nations into Republic of Korea. Methods : Randomly selected samples from roots of Angelica sinensis D., Angelica acutiloba K., and Angelica pubescens M. were radiated with 150 W metal halide lamp for 1 minute. After radiation. biophoton emissions of each sample were detected by electron multiplication(EM)-charge coupled device camera. The detected biophoton image was calculated with unit of counts per pixel. Results: The average biophoton emissions of delayed luminescence with EM ratio of $\times$150 and $\times$250 were distinguished significantly. The maximum biophoton emissions of delayed luminescence with EM ratio of $\times$250 were distinguished significantly. Conclusions : These results suggest that biophoton imaging of roots of Angelica sinensis D., Angelica acutiloba K., and Angelica pubescens M. could become the meaningful method for the study of differentiation for these three species of Genus Angelica.

• The Korea Journal of Herbology
• /
• v.21 no.2
• /
• pp.175-180
• /
• 2006

Objectives : The difference of delayed luminescence-biophoton emission was investigated in Cervi Pantotrichum Cornu selected randomly. Cervi Pantotrichum Cornu was used as a tonic in Korean medicine. Methods : Randomly selected samples of Cervi Pantotrichum Cornu were radiated with 150 W metal halide lamp for 1 minute. After radiation, biophoton emissions of each sample were detected by electron multiplication(EM)-charge coupled device camera. The detected biophoton image was calculated with unit of counts per pixel. Results : The average biophoton emissions of delayed luminescence with EM ratio of ${\times}l50\;and\;{\times}250$ were distinguished significantly. The maximum biophoton emissions of delayed luminescence with EM ratio of ${\times}250$ were distinguished significantly. Conclusion : These results suggest that biophoton imaging of Cervi Pantotrichum Cornu could become the meaningful method for the study of differentiation and classification of Cervi Pantotrichum Cornu.

• Proceedings of the Korean Vacuum Society Conference
• /
• 1999.07a
• /
• pp.244-244
• /
• 1999

Liquid Crystal Displays(LCDs) 투명성 전도막으로 사용하는 Indium Tin Oxide (ITO)의 고밀도 식각특성을 조사하였다. 특히 ITO식각의 경우, pixel electrode 전극에서 사용되는 underlayer인 SiO2, Si3N4와의 최적의 선택비를 얻는데 중점을 두고 있다. 따라서 본 실험에서는 Inductively Coupled Plasma(ICP)를 이용하여 source power, gas combination, bias voltage, pressure 및 기판온도에 따른 ITO의 식각 특성과 이의 underlayer인 SiO2, Si3N4와의 선택비를 조사하였다. Ar과 CH4를 주된 식각가스로서 사용하였으며 첨가가스로는 O2와 HBr를 사용하였다. ITO의 식각특성을 이해하기 위하여 Quadruple Mass Spectrometry(QMS), Optical emission spectroscopy(OES) 이용하였으며, 식각된 sample의 잔류물을 조사하기 위하여 X-ray photoelectron spectroscopy(XPS)를 이용하여 분석하였다. Ar gas에 적정량의 CH4 혼합이 순수한 Ar 가스로 식각한 경우에 비하여 ITO와 SiO2, Si3N4의 선택비가 높았으며, 더 높은 식각 선택비를 얻기 위하여 Ar/CH 분위기에서 첨가가스 O2, HBr을 사용하였다. Source power 및 bias 증가에 따라 ITO의 식각률은 증가하나, underlayer와의 선택비는 감소함을 보였다. 본 실험에서 측정된 ITO의 high 식각률은 약 1500$\AA$/min이며, SiO2, Si3N4와의 high selectivity는 각각 7:1, 12:1로 나타났다. ITO의 etchrate 및 선택비는 source power, bias, pressure, CH 가스첨가에 의존하였지만 기판온도에는 큰 변화가 없음을 관찰하였다. 또한 적정량의 가스조합으로 식각된 시편의 잔류물을 줄일 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.71-77
• /
• 2008

This paper presents a methodology for recovering the industrial radiographic images from the effects of nonlinear distortion. Analytical approach based on the inverse square law and Beer's law is developed in order to improve a mathematic model of nonlinear type. The geometric effect due to dimensions of the radioactive source appeals on the digitized images. The relation that expresses parameters values(angle, position, absorption coefficient, length, width and pixel account) is defined in this model, matching with the sample image. To perform the search for image recovery most similar to the model, a correction procedure is designed. The application of this method on the radiographic images of steel tubes is shown and recovered results are discussed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.67-70
• /
• 2015

최근 깊이 영상 기반 렌더링 방법을 이용하여 제작된 3차원 컨텐츠가 우리의 눈을 즐겁게 해주고 있다. 이러한 깊이 영상 기반 렌더링에서는 필연적으로 색상 카메라와 깊이 카메라 간의 시점 차이가 발생한다. 따라서 두 시점을 일치시키는 전처리 과정으로서 카메라 파라미터가 중요한 역할을 수행한다. 카메라 파라미터를 획득하는 과정으로 카메라 캘리브레이션이 수행된다. 널리 사용되는 기존의 카메라 캘리브레이션 방법은 평면의 체스보드 패턴을 여러 자세로 촬영한 다음 패턴 특징점을 손으로 직접 선택해야하는 불편함이 따른다. 따라서 본 논문에서는 이 문제를 해결하기 위해 원형 샘플 화소 검사와 호모그래피 예측을 이용한 반자동 카메라 캘리브레이션을 제안한다. 제안하는 방법은 먼저 FAST 코너 검출 알고리즘을 이용하여 패턴 특징점의 후보를 영상으로부터 추출한다. 다음으로 원형 샘플 화소를 검사하여 후보군의 크기를 줄인다. 그리고 호모그래피 예측을 통해 손실된 패턴 특징점을 보완하는 완전한 패턴 특징점군을 획득한다. 마지막으로 화소 정확성 향상을 통해 실수 단위의 정확성을 가지는 패턴 특징점의 위치를 획득한다. 실험을 통해 제안하는 방법이 기존의 방법과 비교하여 카메라 파라미터의 정확성은 유지하고 수작업의 불편함을 해소할 수 있음을 확인했다.

• Journal of IKEEE
• /
• v.7 no.2 s.13
• /
• pp.271-280
• /
• 2003

This paper presents an effective method to segment objects from the ultrasound medical image which is inherently corrupted by speckle noise. In order to reduce the speckle noise morphological opening was used as preprocessing. For the preprocessed image, sample variance of neighborhood pixels is to be computed to classify where the pixel is located on the edge region or homogeneous region. Then pseudomedian filtering with different window size is taken according to the region classified, named adaptive pseudomedian filter. Various experimental results were presented to prove superiority of the proposed filter.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.7
• /
• pp.333-338
• /
• 2016

This study is to estimate proximity without direct measurement of the weight of fresh ginseng. For this work, we developed a ginseng image acquiring instrument and obtained 126 ginseng images using the instrument. Image analysis and parameter extraction process was used C language based Labwindows/CVI development tools and open source library OpenCV. Estimation formula is made by weighing the sample with image analysis of fresh ginseng. We analyzed the correlation between the pixel number and the weight of ginseng using a linear regression approach. It was obtained a strong positive correlation coefficient of 0.9162 with a linearity value.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.