• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.18-23
• /
• 2016

QFN (Quad Flat No-leads Package) is one of the SMD (Surface Mount Device). Since there is no lead in QFN, there are many defects on solder. Therefore, we propose an efficient mechanism for QFN solder defect detection at this paper. For this, we employ Convolutional Neural Network (CNN) of the Machine Learning algorithm. QFN solder's color multi-layer images are used to train CNN. Since these images are 3-channel color images, they have a problem with applying to CNN. To solve this problem, we used each 1-channel grayscale image (Red, Green, Blue) that was separated from 3-channel color images. We were able to detect QFN solder defects by using this CNN. In this paper, it is shown that the CNN is superior to the conventional multi-layer neural networks in detecting QFN solder defects. Later, further research is needed to detect other QFN.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1391-1406
• /
• 2020

A zero-watermarking algorithm in transform domain based on RGB channel and voting strategy is proposed. The registration and identification of ownership have achieved copyright protection for color images. In the ownership registration, discrete wavelet transform (DWT), discrete cosine transform (DCT), and singular value decomposition (SVD) are used comprehensively because they have the characteristics of multi-resolution, energy concentration and stability, which is conducive to improving the robustness of the proposed algorithm. In order to take full advantage of the characteristics of the image, we use three channels of R, G, and B of a color image to construct three master shares, instead of using data from only one channel. Then, in order to improve security, the master share is superimposed with the copyright watermark encrypted by the owner's key to generate an ownership share. When the ownership is authenticated, copyright watermarks are extracted from the three channels of the disputed image. Then using voting decisions, the final copyright information is determined by comparing the extracted three watermarks bit by bit. Experimental results show that the proposed zero watermarking scheme is robust to conventional attacks such as JPEG compression, noise addition, filtering and tampering, and has higher stability in various common color images.

• 한국해양공학회지
• /
• 제34권6호
• /
• pp.442-453
• /
• 2020

Underwater color images suffer from low visibility and color cast effects caused by light attenuation by water and floating particles. This study applied single image enhancement techniques to enhance the quality of underwater images and compared their performance with real underwater images taken in Korean waters. Dark channel prior (DCP), gradient transform, image fusion, and generative adversarial networks (GAN), such as cycleGAN and underwater GAN (UGAN), were considered for single image enhancement. Their performance was evaluated in terms of underwater image quality measure, underwater color image quality evaluation, gray-world assumption, and blur metric. The DCP saturated the underwater images to a specific greenish or bluish color tone and reduced the brightness of the background signal. The gradient transform method with two transmission maps were sensitive to the light source and highlighted the region exposed to light. Although image fusion enabled reasonable color correction, the object details were lost due to the last fusion step. CycleGAN corrected overall color tone relatively well but generated artifacts in the background. UGAN showed good visual quality and obtained the highest scores against all figures of merit (FOMs) by compensating for the colors and visibility compared to the other single enhancement methods.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2004년도 춘계학술발표대회 논문집 제23권 1호
• /
• pp.81-84
• /
• 2004

In this paper, we propose a virtual sound localization algorithm which improves the sound localization accuracy and sound color preservation for two channel and multi-channel surround speaker layouts. In conventional CPP laws, the sound direction is different from the panning angle and the sound color is different from real sound source especially when the speakers are spread out widely. To overcome this drawback, we design a virtual sound localization algorithm using directional psychoacoustic criteria (DPC) and sound color compensator (SCC). The analysis results show that in the case of the proposed system, the sound direction is the same as the panning angle in the audible frequency range and the sound color is less deviated from a real sound source than the conventional CPP law. In addition, its performance is verified by means of subjective tests using a real sound source.

• 한국광학회지
• /
• 제10권5호
• /
• pp.379-385
• /
• 1999

칼라 CRT(cathode ray tube) 모니터의 화면밝기와 명암대비 레벨에 따른 화질 특성을 연구하였다. 화면밝기와 명암대비 레벨을 변화시키면서 SQRI(square root integrals)를 측정하여 시감효과를 고려한 분해능을 조사하였다. 또한 이들 레벨에서 삼색 채녈의 색도 좌표와 휘도를 측정하여 채널의 색도 좌표 일정, 색재현 영역, 그리고 채널의 독립을 만족하는 흰색의 최대 휘도를 분석하였다. 결과를 바탕으로 최적의 분해능과 색재현 특성을 가지는 화면 밝기와 명암대비 레벨을 제시하였다.

• 한국인쇄학회:학술대회논문집
• /
• 한국인쇄학회 1998년도 추계 논문 발표회 논문집
• /
• pp.16-21
• /
• 1998

Spectral reflrectance of the object should be mesured to predict the color of object under various illuminants. The spectral reflectance can be represented in a multidemensional space; Generally we can obtain only three-channel data from input device such as CCD camera, color scanner etc. The estimation from three dimernsional to multidimension can be achieved using principal components of spectral reflectance. In this paper, A method to predict the spectral reflectance of skin color taken by 3-channel input device is discribed. To confirm this method, we simulate color represent under various illuminants about yellow, white and colored women face.

• Current Optics and Photonics
• /
• 제6권6호
• /
• pp.608-618
• /
• 2022

By analyzing the signal-to-noise ratio (SNR) theory of the conventional true color night vision system, we found that the output image SNR is limited by the wavelength range of the system response λ₁ and λ₂. Therefore, we built a double-channel four-band true color night vision system to expand the system response to improve the output image SNR. In the meantime, we proposed an image fusion method based on principal component analysis (PCA) and nonsubsampled shearlet transform (NSST) to obtain the true color night vision images. Through experiments, a method based on edge extraction of the targets and spatial dimension decorrelation was proposed to calculate the SNR of the obtained images and we calculated the correlation coefficient (CC) between the edge graphs of obtained and reference images. The results showed that the SNR of the images of four scenes obtained by our system were 125.0%, 145.8%, 86.0% and 51.8% higher, respectively, than that of the conventional tri-band system and CC was also higher, which demonstrated that our system can get true color images with better quality.

• 대한전자공학회논문지SP
• /
• 제49권1호
• /
• pp.67-72
• /
• 2012

본 논문에서는 대기 열황 영상의 색상 분석을 통해 대기값과 전달률을 추정하여 대기 열화 요인을 제거함으로써 영상의 가시성을 향상시키는 알고리듬을 제안한다. 제안하는 알고리듬은 RGB채널의 최대값을 이용하여 영상을 정규화 시키고, 반사율을 이용하여 RGB 채널 각각의 적응적 대기값을 추정한다. 또한 영상의 Y채널의 감마보정을 통해 전달률을 생성한다. 결과적으로 대기값과 전달률을 이용하여 대기 열화 요인을 제거함으로써 가시성이 향상된 영상을 얻는다. 제안된 방법은 영상의 색상을 분석하기 때문에 기존의 기술의 문제점인 색상왜곡을 억제하고, 효과적으로 영상을 복원함으로써 가시성 향상에 있어서 뛰어난 성능을 보인다. 그 결과 제안된 알고리듬은 안개, 연기, 먼지 등과 같은 다양한 대기중의 불순물에 의한 화질 열화를 효과적으로 제거하여 가시성 향상에 기여할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제9권4호
• /
• pp.434-442
• /
• 2006

본 논문에서는 모니터와 모바일 디스플레이간의 복잡한 색 정합 과정을 단순화시키는 3차원의 색 정합 look-up table(LUT)을 설계하였다. 여기에서 영상의 색은 CIEXYZ 혹은 CIELAB 등의 장치 독립적인 색 공간에서 처리되며, 색역의 차이를 보상하기 위해 색역 사상이 수행된다. 장치 의존적인 RGB 색 공간에서 장치 독립적인 색 공간으로의 변환은 디스플레이 특성화 과정을 수행함으로써 이루어진다. 기존의 S-curve 모텔을 이용하여 모바일 LCD 를 특성화 하면 모바일 LCD의 채널 색도 변화와 채널 의존 특성으로 인해 특성화 오차가 허용 오차보다 커지게 된다. 본 논문에서는 R, G, B, C, M, Y, K 성분의 X, Y, Z의 전기-빛 입출력 곡선을 모두 이용하여 특성화 오차를 줄였다. 제안한 색 정합 LUT 와 복잡하고 단계적인 색 정합 절차 사이의 색 정합 결과 영상 비교 실험을 통해 허용오차 내의 영상을 재현할 수 있는 색 정합 LUT의 최소 크기가 64($4{\times}4{\times}4$)라는 것을 확인하였다.

• 한국측량학회지
• /
• 제15권1호
• /
• pp.41-50
• /
• 1997

본 연구에서는 실시간에 걸쳐서, 자동적으로 공액점들을 매칭시킬 수 있는 색상분리기법을 제시하는데 목적을 두고 있다 CCD카메라에의해 취득된 영상으로부터 계산된 상좌표는 취득된 상좌표의 정확도 와 소트를 통한 매칭의 정확도 측면에서 점검되었다. 점검결과, 연구에의하여 취득된 상좌표를 이용하여 사진측량 프로그램에 의해 계산된 대상물좌표의 RMSE는 근거리사진측량의 기대RMSE내에 분포하고 있었으며, 소트에의한 공액표정점들의 매칭 또한 정확하게 수행되었다. 따라서 본 연구에서 제시하는 색상분리기법이 정확한 상좌표의 취득과 공액점의 매칭에 적절함을 알 수 있었으며, 이 방법은 실시간에 걸쳐서 취득정보를 빠르고 정확하게 처리해야하는 산업분야에 유용할 것으로 생각된다.