• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.4060-4079
• /
• 2020

Blur is an important type of image distortion. How to evaluate the quality of blurred image accurately and efficiently is a research hotspot in the field of image processing in recent years. Inspired by the multi-scale perceptual characteristics of the human visual system (HVS), this paper presents a no-reference image blur/sharpness assessment method based on multi-scale local features in the spatial domain. First, considering various content has different sensitivity to blur distortion, the image is divided into smooth, edge, and texture regions in blocks. Then, the Gaussian scale space of the image is constructed, and the categorized contrast features between the original image and the Gaussian scale space images are calculated to express the blur degree of different image contents. To simulate the impact of viewing distance on blur distortion, the distribution characteristics of local maximum gradient of multi-resolution images were also calculated in the spatial domain. Finally, the image blur assessment model is obtained by fusing all features and learning the mapping from features to quality scores by support vector regression (SVR). Performance of the proposed method is evaluated on four synthetically blurred databases and one real blurred database. The experimental results demonstrate that our method can produce quality scores more consistent with subjective evaluations than other methods, especially for real burred images.

• Smart Structures and Systems
• /
• 제14권5호
• /
• pp.831-845
• /
• 2014

This paper proposed a discrete wavelet transform based method for time-varying physical parameter identification of shear type structures. The time-varying physical parameters are dispersed and expanded at multi-scale as profile and detail signal using discrete wavelet basis. To reduce the number of unknown quantity, the wavelet coefficients that reflect the detail signal are ignored by setting as zero value. Consequently, the time-varying parameter can be approximately estimated only using the scale coefficients that reflect the profile signal, and the identification task is transformed to an equivalent time-invariant scale coefficient estimation. The time-invariant scale coefficients can be simply estimated using regular least-squares methods, and then the original time-varying physical parameters can be reconstructed by using the identified time-invariant scale coefficients. To reduce the influence of the ill-posed problem of equation resolving caused by noise, the Tikhonov regularization method instead of regular least-squares method is used in the paper to estimate the scale coefficients. A two-story shear type frame structure with time-varying stiffness and damping are simulated to validate the effectiveness and accuracy of the proposed method. It is demonstrated that the identified time-varying stiffness is with a good accuracy, while the identified damping is sensitive to noise.

• 한국멀티미디어학회논문지
• /
• 제20권9호
• /
• pp.1481-1490
• /
• 2017

This paper presents an image quality enhancement algorithm for dark image acquired under poor lighting condition. Various retinex algorithms which are human perception-based image processing methods were proposed to solve this problem. Although MSR(Multi-Scale Retinex) among these algorithm works well under most lighting condition, it shows color degradation because their separate nonlinear processing of RGB color channels. To compensate for the loss of the color, MSRCR(Multi-Scale Retinex with Color Restoration) was proposed. However, it requires high computational load and has additional parameters that need to be adjusted according to input image. In order to overcome this problem, a new retinex algorithm based on MSR is proposed in this paper. The proposed method consists of V channel MSR, saturation correction, and separate contrast enhancement process. Experimental results show that the subjective and objective image quality of the proposed method better than those of the conventional methods.

• 한국지능시스템학회논문지
• /
• 제15권4호
• /
• pp.467-472
• /
• 2005

영상 향상기법들의 주요한 목적은 특정한 응용프로그램에서 결과영상이 원영상보다 보다 적절하게 하기 위해 처리하는 것이다. 야간에 촬영한 영상들은 열약한 주위환경에 기인하여 저대비 영상을 가질 수 있다. 본 논문에서는 클러스터링 알고리듬을 이용한 영상 대비 향상 기법(ICECA)과 히스토그램 평활화(HE), 양분 히스토램 평활화(BBHE), Multi-Scale Retinek(MSR)와 같은 영상 향상 기법들을 비교하였다. 성능 비교를 위해 다양한 영상에 영상 향상기법들을 적용하여 비교하였다.

• Journal of Information Processing Systems
• /
• 제13권6호
• /
• pp.1628-1639
• /
• 2017

The combination texture feature extraction approach for texture image retrieval is proposed in this paper. Two kinds of low level texture features were combined in the approach. One of them was extracted from singular value decomposition (SVD) based dual-tree complex wavelet transform (DTCWT) coefficients, and the other one was extracted from multi-scale local binary patterns (LBPs). The fusion features of SVD based multi-directional wavelet features and multi-scale LBP features have short dimensions of feature vector. The comparing experiments are conducted on Brodatz and Vistex datasets. According to the experimental results, the proposed method has a relatively better performance in aspect of retrieval accuracy and time complexity upon the existing methods.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.648-651
• /
• 2023

Video anomaly detection aims to detect abnormal events. Motivated by the power of transformers recently shown in vision tasks, we propose a novel transformer-based network for video anomaly detection. To capture long-range information in video, we employ a multi-scale transformer as an encoder. A convolutional decoder is utilized to predict the future frame from the extracted multi-scale feature maps. The proposed method is evaluated on three benchmark datasets: USCD Ped2, CUHK Avenue, and ShanghaiTech. The results show that the proposed method achieves better performance compared to recent methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1620-1634
• /
• 2023

This paper studies the task of embedding nodes with multiple graphs representing multiple information channels, which is useful in a large volume of network clustering tasks. By learning a node using multiple graphs, various characteristics of the node can be represented and embedded stably. Existing studies using multi-channel networks have been conducted by integrating heterogeneous graphs or limiting common nodes appearing in multiple graphs to have similar embeddings. Although these methods effectively represent nodes, it also has limitations by assuming that all networks provide the same amount of information. This paper proposes a method to overcome these limitations; The proposed method gives different weights according to the source graph when embedding nodes; the characteristics of the graph with more important information can be reflected more in the node. To this end, a novel method incorporating a multi-channel gate layer is proposed to weigh more important channels and ignore unnecessary data to embed a node with multiple graphs. Empirical experiments demonstrate the effectiveness of the proposed multi-channel-based embedding methods.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.439-448
• /
• 2012

TFT-LCD 패널을 저해상도로 획득한 영상은 불균일한 휘도 분포와 노이즈 신호, 그리고 결함 신호로 구성되어 있다. 불균일한 휘도 분포와 노이즈로 인해 결함 신호를 분할하기 어려우며 이를 위해 다양한 분할 방법이 개발되고 있다. 본 논문에서는 공간영역 상에서 Eikvil et al.'s에 의해 제안되어진 크기가 다른 두 개의 창을 두고 각 창의 평균을 계산하고 그 값의 차이를 이용하는 방법을 이용하여 TFT-LCD 패널 이미지 상에 존재하는 결함의 영역을 분할하는 방법을 제안한다. 하지만 이 방법은 창의 크기에 의해 검출 가능한 결함영역의 크기가 제한되어 큰 결함영역을 분할하기 위해서는 창을 키워야 하므로 효율적이지 못한 문제점을 가지고 있다. 이 문제를 해결하기위해 멀티스케일(Multi-scale)을 이용하고, 각 스케일에서 검출 가능한 결함 크기를 제한함으로써 다양한 크기의 결함 영역을 분할 할 수 있는 알고리즘을 제안한다. 알고리즘의 성능을 검증하기위해 다양한 크기의 결함 영역을 만들어 분할되어진 결과와 실제 결함이 존재하는 TFT-LCD 패널 이미지의 분할 결과들을 통해 실제 적용 가능한 알고리즘임을 보인다.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1268-1280
• /
• 2015

In video surveillance system, the exposure of a person's face is a serious threat to personal privacy. To protect the personal privacy in large amount of videos, an automatic face detection method is required to locate and mask the person's face. However, in real-world surveillance videos, the effectiveness of existing face detection methods could deteriorate due to large variations in facial appearance (e.g., facial pose, illumination etc.) or degraded face (e.g., occluded face, low-resolution face etc.). This paper proposes a new face detection method based on multi-level facial features. In a video frame, different kinds of spatial features are independently extracted, and analyzed, which could complement each other in the aforementioned challenges. Temporal domain analysis is also exploited to consolidate the proposed method. Experimental results show that, compared to competing methods, the proposed method is able to achieve very high recall rates while maintaining acceptable precision rates.

• 한국산학기술학회논문지
• /
• 제11권9호
• /
• pp.3176-3183
• /
• 2010

본 논문은 다축 하중을 받는 복합재 압력용기의 멀티 스케일 피로수명 예측 방법을 제시하였다. 멀티 스케일 접근법은 복합재료의 기본 구성재료인 섬유, 기지 및 섬유/기지 경계면의 거동으로부터 복합재 플라이, 적층판 및 구조물의 전체 거동을 예측한다. 멀티 스케일 피로수명은 거시적 응력 해석과 미시적 피로파손 해석을 통해 예측된다. 유한요소법을 이용하여 복합재 압력용기의 적층판에 가해지는 다축 피로하중을 구하며, 고전적층판이론을 이용하여 적층판의 플라이 응력을 계산하였다. 미소역학 모델을 이용하여 플라이 응력으로부터 각각 섬유, 기지 및 섬유/기지 경계면에 발생되는 응력을 계산하였다. 복합재 구성재료의 피로수명은 섬유에 대해서는 최대응력법을, 기지에 대해서는 등가응력법을, 섬유/기지 경계면에 대해서는 임계평면법을 사용하였다. 평균응력을 고려하기 위하여 수정된 Goodman 식을 적용하였다. 모든 피로하중에 의한 손상은 Miner 법칙을 이용하여 선형 누적이 되고, 이를 통해 최종 피로파손을 판단한다. 섬유와 기지의 물성값, 섬유체적비 및 와인딩 각도의 확률분포에 따른 복합재 압력용기의 피로수명 영향을 분석하기 위해 몬테카르로 시뮬레이션을 수행하였다.