• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.227-234
• /
• 2018

Recently, stitching techniques are used for obtaining wide FOV, e.g., panorama contents, from normal cameras. Despite many proposed algorithms, the no objective quality evaluation method is developed, so the comparison of algorithms are performed only in subjective way. The paper proposes a 'Delaunay-triangulation based objective assessment method' for evaluating the geometric and photometric distortions of stitched or warped images. The reference and target images are segmented by Delaunay-triangulation based on matched points between two images, the average Euclidian distance is used for geometric distortion measure, and the average or histogram of PSNR for photometric measure. We shows preliminary results with several test images and stitching methods for demonstrate the benefits and application.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.4
• /
• pp.265-272
• /
• 2019

In this paper, a vision-based deep learning algorithm and image processing method are proposed to detect bolt-loosening in steel connections. To achieve this objective, the following approaches are implemented. First, a bolt-loosening detection method that includes regional convolutional neural network(RCNN)-based deep learning algorithm and Hough line transform(HLT)-based image processing algorithm are designed. The RCNN-based deep learning algorithm is developed to identify and crop bolts in a connection image. The HLT-based image processing algorithm is designed to estimate the bolt angles from the cropped bolt images. Then, the proposed vision-based method is evaluated for verifying bolt-loosening detection in a lab-scale girder connection. The accuracy of the RCNN-based bolt detector and HLT-based bolt angle estimator are examined with respect to various perspective distortions.

• 대한치과교정학회:학술대회논문집
• /
• 2005.11a
• /
• pp.151.1-151.1
• /
• 2005

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.274-279
• /
• 2007

본 논문은 MPEG2 다중화 방식을 이용한 고화질 이미지를 실시간으로 송수신하는 시스템을 제안한다. 송신 시스템은 카메라로부터 획득한 고화질 이미지와 GPS 장비로부터 획득한 위치정보를 MPEG2 TS 방식으로 변환하여 전송한다. 수신 시스템은 송신되는 MPEG2 TS data를 실시간으로 고화질 이미지와 위치정보로 추출한 후에 화면에 display한다. 본 논문에서는 오류 발생에 대한 회피 방법으로 고화질 이미지를 포함한 패킷을 단순히 중복적으로 전송하는 방법을 사용하였다. 이러한 방법은 신호의 왜곡 혹은 패킷 손실에 의해 발생되었던 오류들을 현저하게 줄여주었으나 한 장의 고화질 이미지에 대한 평균 처리시간을 증가하였다. 평균 처리 시간을 줄이기 위해 송신 시스템은 스레드를 이용한 전송 방법을 사용하였으며 이러한 방법의 사용은 스레드 기법을 사용하지 않았을 때보다 빠른 평균 처리시간을 측정할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.5 no.1
• /
• pp.69-72
• /
• 2004

Compared to the barcode which is being widely employed to store information on products, the color code may find more various applications because of its favorable appearance and larger possible number of combinations. However, the color values read in practice may suffer from distortions from environments and devices. In this paper, we propose efficient ways to reduce the effect of such distortions and to detect color codes. for which we apply the Right Hand on Wall (RHOW) algorithm originated from the area of the maze search. The color codes used in this paper have high values of Hue and Saturation components and have a circular shape. We first preprocessed the images to detect candidate areas of color codes, and then applied the RHOW algorithm to determine optimal coordinates of rectangles enclosing the areas. As a result, we could obtain accurate coordinates of color codes by using the RHOW algorithm.

• Korean Journal of Optics and Photonics
• /
• v.30 no.6
• /
• pp.237-242
• /
• 2019

A compact virtual-reality (VR) device with wider field of view provides users with a more realistic experience and comfortable fit, but VR lens distortion is inevitable, and the amount of distortion must be measured for correction. In this paper, we propose two different full-field distortion-measurement methods, considering the characteristics of the VR device. The first is the distortion-measurement method using multiple images based on camera calibration, which is a well-known technique for the correction of camera-lens distortion. The other is the distortion-measurement method by measuring lens distortion at multiple measurement points by rotating a camera. Our proposed methods are verified by measuring the lens distortion of Google Cardboard, as a representative sample of a commercial VR device, and comparing our measurement results to a simulation using the nominal values.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.97-100
• /
• 2012

본 논문은 변환영역 기반의 방법 중 DCT 변환영역 워터마크를 이용한 이미지 무결성 검증 시스템을 제안하였다. DCT 변환영역에 워터마크를 삽입하는 것이 공간영역에 삽입하는 것보다 잡음과 일반적인 신호처리나 영상편집, 선형/비선형 필터링, 압축 등의 영상처리에 강하다. 추출된 워터마크가 원본 워터마크와의 유사도 평가에서 임계값보다 크면 이미지에 변형이 없었다고 판단한다. 만약 이미지에 변형이 있을 경우 워터마크가 훼손되어 정확한 정보를 추출하기 어려울 수 있다. 이때 추출기에서 이미지 왜곡을 역변환 시켜 워터마크를 온전하거나 최소화된 훼손으로 추출한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.703-705
• /
• 2004

의학적 진단이나 치료를 하는 과정에선 실험이나 촬영을 통한 사진이나 영상이 많이 생성된다 의학용 이미지들은 각각 생성된 환경에 따른 특성을 가지고 있기 때문에. 효율적으로 이미지를 관리하기 위해서는 이미지의 특징이나 증상과 같은 정보들을 함께 표현해야한다. 본 논문에서는 의료 영상이 나타내는 정보를 표기하고, 카메라로부터 입력받는 영상을 출력 및 분석할 수 있는 컴포넌트웨어에 대해서 살펴본다. 본 논문에서 개발한 컴포넌트웨어는 다른 프로그램에서도 쉽게 영상관련 처리를 할 수 있도록 COM 기반의 Activex 컨트롤로 개발하였으며 이미지의 주석기능과 더불어 각각의 이미지나 카메라로부터 입력받는 동영상의 색 공간변환 및 왜곡보정 등의 기능을 가지고 있어, 보다 정교한 작업을 요하는 의료 영상처리 프로그램에 손쉽게 추가하여 사용할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.67-68
• /
• 2021

기존 객체탐지는 경계 상자 회귀방식을 적용하였지만, 문자는 왜곡과 변형이 심한 특성을 가진 객체로 U-net 구조의 이미지 분할 방식을 사용하는 경우가 많다. 따라서 최근 문자 탐지는 통계적 모델에 비해 높은 정확도를 보이는 심층 신경망 기반의 모델 연구가 많이 진행되고 있다. 본 연구에서는 이미지 분할을 통한 양방향 특징 결합 기법을 사용한 문자 탐지 모델을 제안한다. 이미지 분할 방식은 메모리의 효율이 떨어지기 때문에 이를 극복하고자 특징 추출 단계에서 경량화된 네트워크를 적용하였다. 또한, 객체 탐지에서 큰 성과를 보인 양방향 특징 결합 모듈을 U-net 구조에 추가하여 추출된 특징이 효과적으로 결합 되는 결과를 얻었다. 제안하는 모델의 문자 탐지 성능은 합성 문자 데이터셋을 이용한 실험을 통해 기존의 U-net 구조의 이미지 분할 방식보다 향상되었음을 확인하였다.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.464-471
• /
• 2023

In this paper, we propose a method to reduce age distortion in facial expression image generation using StyleGAN Encoder. The facial expression image generation process first creates a face image using StyleGAN Encoder, and changes the expression by applying the learned boundary to the latent vector using SVM. However, when learning the boundary of a smiling expression, age distortion occurs due to changes in facial expression. The smile boundary created in SVM learning for smiling expressions includes wrinkles caused by changes in facial expressions as learning elements, and it is determined that age characteristics were also learned. To solve this problem, the proposed method calculates the correlation coefficient between the smile boundary and the age boundary and uses this to introduce a method of adjusting the age boundary at the smile boundary in proportion to the correlation coefficient. To confirm the effectiveness of the proposed method, the results of an experiment using the FFHQ dataset, a publicly available standard face dataset, and measuring the FID score are as follows. In the smile image, compared to the existing method, the FID score of the smile image generated by the ground truth and the proposed method was improved by about 0.46. In addition, compared to the existing method in the smile image, the FID score of the image generated by StyleGAN Encoder and the smile image generated by the proposed method improved by about 1.031. In non-smile images, compared to the existing method, the FID score of the non-smile image generated by the ground truth and the method proposed in this paper was improved by about 2.25. In addition, compared to the existing method in non-smile images, it was confirmed that the FID score of the image generated by StyleGAN Encoder and the non-smile image generated by the proposed method improved by about 1.908. Meanwhile, as a result of estimating the age of each generated facial expression image and measuring the estimated age and MSE of the image generated with StyleGAN Encoder, compared to the existing method, the proposed method has an average age of about 1.5 in smile images and about 1.63 in non-smile images. Performance was improved, proving the effectiveness of the proposed method.