• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.146-153
• /
• 2018

This paper presents a superresolution demosaicing technique that can restore high-resolution color image from differently blurred low resolution images in Bayer domain. The proposed superresolution demosaicing algorithm uses an aperture mask wheel to get differently blurred low resolution images, so we just need to estimate point spread function at each frame. In addition, it does not require image registration because there is no translational motion between low resolution images. By using a rotatable aperture mask wheel, consecutive captured images provide sufficiently exclusive information for superresolution. Therefore, the proposed method can reduce the registration error between the low-resolution image as well as the calculation amount for superresolution restoration. The existing lens system of the camera can be extended to obtain a superresolution image by only adding an rotatable aperture mask wheels. Finally, in order to verify the performance of the proposed system, experimental results are performed. The proposed method showed the significant improvements in the sense of spatial and color resolution.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1039-1045
• /
• 2021

In modern society, due to the influence of the 4th industrial revolution, camera sensors and image-based automation systems are being used in various fields, and interest in image and signal processing is increasing. In this paper, we propose a digital filter algorithm for image reconstruction in an impulse noise environment. The proposed algorithm divides the image into eight masks in vertical, horizontal, and diagonal directions based on the local mask set in the image, and compares the standard deviation of each segmentation mask to obtain a reference value. The final output is calculated by applying the weight according to the spatial distance and the weight using the reference value to the local mask. To evaluate the performance of the proposed algorithm, it was simulated with the existing algorithm, and the performance was compared using enlarged images and PSNR.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.385-388
• /
• 2011

Patients' privacy protection is a heated issue in medical business, as medical information in digital format transmit everywhere through networks without any limitation. A current protection method for brain images is to deface from the brain image for patient's privacy. However, the defacing process often removes important brain voxels so that the defaced brain image is damaged for medical analysis. An ad-hoc method is proposed to conceal patient's identification by adding cylindrical mask, while the brain keep all important brain voxels. The proposed lossless deformation of brain image is verified not to loose any important voxels. Futhermore, the masked brain image is proved not to be recognized by others.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.219-222
• /
• 2002

본 논문에서는 잘못된 인쇄로 인한 문서상의 잡영이 생기거나 문자 훼손이 있는 문서영상을 복원 하고자 한다. 제안하는 방법은 문서영상을 스캐너로 읽어들여 잡영을 제거 한 뒤 훼손된 숫자 영상에 대해서 프로젝션을 이용하여 숫자 열을 낱낱의 숫자로 분할한다. 각각의 숫자에 대해서 크기가 일정하도록 정규화를 시킨 다음, Backpropagation을 이용하여 훼손된 숫자를 학습하였다. 학습시킨 다음 원 영상과 훼손된 영상을 각 픽셀단위로 비교하여 4-방향 마스크를 이용하여 원래의 숫자 영상으로 복원하도록 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.434-436
• /
• 2022

For 4th industrial revolution and the development of various communication media, unmanned and automation are rapidly progressing in various fields. In particular, high-level image processing technology is required in fields such as smart factories, autonomous driving technology, and intelligent CCTV. Accordingly, the importance of preprocessing in a system operating based on an image is increasing, and an algorithm for effectively removing noise from an image is attracting attention. In this paper, we propose a filtering algorithm using noise judgment and a segmentation mask in a complex noise environment. The proposed algorithm calculates the final output by switching the segmentation mask suitable for filtering by performing noise judgment on the pixel values of the input image. Simulation was conducted to verify the performance of the proposed algorithm, and the result image was compared and evaluated with the existing filter algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.670-672
• /
• 2002

본 논문에서는 잘못된 인쇄로 인한 문서상의 잡영이나 문자 훼손이 있는 문서를 복원 하고자 만다. 제안하는 방법은 스캐너로 읽어들인 문서영상을 잡영 제거론 만 다음 훼손된 숫자 영상에 대해서 프로젝션을 이용하여 숫자 열을 낱낱의 숫자로 분할한다. 각각의 숫자에 대해서 크기가 일정하도록 정규화를 시킨 다음, Backpropagalion을 이용하여 훼손된 숫자를 학습하였다. 학습시킨 다음 원 영상과 훼손된 영상을 각 픽셀단위로 비교하여 4-방향 마스크를 이용하여 원래의 숫자 영상으로 복원하도록 만다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.413-414
• /
• 2024

영상 인식을 위한 학습 데이터 구성 단계에서 에지는 물체의 크기, 방향 등의 정보를 포함하고 있어 영상의 특징으로 사용한다. 본 논문에서는 얼굴 인식을 위하여 소벨 마스크를 사용하여 원영상과 압축영상 그리고 에지영상간의 학습에 따른 인식 정도를 파악하고자 한다. 실험결과, 원영상 그대로 인식하는 것보다 에지 영상에 의한 학습 속도에 차이가 있음을 알 수 있었다.

• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2014

This paper presents a superresolution restoration technique that can restore high-resolution images from differently blurred low resolution images rather than using the motion information between low-resolution images. In order to restore the super-resolution image the rotatable aperture mask lens system is proposed. The proposed technique does not need to estimate point spread function at each frame. In addition, it does not require image registration because there is no global translational motion between low resolution images. By using a rotatable rectangular aperture, two consecutive captured images provide sufficiently exclusive information for superresolution. Therefore, the proposed method can reduce the registration error between the low-resolution image as well as the calculation amount for superresolution restoration. The existing lens system of the camera can be extended to obtain a superresolution image by only adding an rotatable rectangular aperture mask. Finally, in order to verify the performance of the proposed system, experimental results are performed. By comparing with the existing superresolution methods, the proposed method showed the significant improvements in the sense of spatial resolution.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.542-551
• /
• 2000

In this paper, a novel technique is presented for automatic brain region segmentation in single channel MR image data sets for 3D visualization and analysis. The method detects brain contours in 2D and 3D processing of four steps. The first and the second make a head mask and an initial brain mask by automatic thresholding using a curve fitting technique. The stage 3 reconstructs 3D volume of the initial brain mask by cubic interpolation and generates an intermediate brain mask using morphological operation and labeling of connected components. In the final step, the brain mask is refined by automatic thresholding using curve fitting. This algorithm is useful for fully automatic brain region segmentation of T1-weighted, T2-weighted, PD-weighted, SPGR MRI data sets without considering slice direction and covering a whole volume of a brain. In the experiments, the algorithm was applied to 20 sets of MR images and showed over 0.97 in comparison with manual drawing in similarity index.