DCT-based local motion blur detection

Kalalembang, Erik; Usman, Koredianto; Gunawan, Irwan Prasetya

doi:10.1109/icici-bme.2009.5417252

Cited by 24 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Golestaneh et al [33] proposed a spatially-varying blur detection method. Kalalembang et al [34] presented a method of detecting unwanted motion blur effects. Gast et al [35] proposed a parametric object motion model by combining with a segmentation mask to exploit localized, non-uniform motion blur.…”

Section: Related Workmentioning

confidence: 99%

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Pei

Huang

Zou

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

174

View full text Add to dashboard Cite

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional Neural Networks (CNN). Most of the existing works are focused on classifying very clear natural images, evidenced by the widely used image databases such as Caltech-256, PASCAL VOCs and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification. More specifically, we wonder whether image-classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image-classification performance. In this paper, we empirically study this problem for four kinds of degraded images -hazy images, underwater images, motion-blurred images and fish-eye images. For this study, we synthesize a large number of such degraded images by applying respective physical models to the clear natural images and collect a new hazy image dataset from the Internet. We expect this work can draw more interests from the community to study the classification of degraded images.

show abstract

Section: Related Workmentioning

confidence: 99%

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Pei

Huang

Zou

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

174

View full text Add to dashboard Cite

show abstract

“…Research on the subject of blur analysis generally consists of the topics of deblurring [14,15,16,17], blur simulation [9,10,11,18], blur detection [19,20,21] and blur identification [22,23,24]. The most common topic of blur analysis is image deblurring, while blur detection and blur identification are also mainly used for the purpose of deblurring.…”

Section: Blur Analysismentioning

confidence: 99%

Motion Estimation in Blurred Frames Using Phase Correlation

Firouzi

Joslin

2013

2013 International Conference on Signal-Image Technology &Amp; Internet-Based Systems

View full text Add to dashboard Cite

This paper presents a method to adopt phase correlation for blurred frames. Phase correlation is a strong motion estimation tool which is highly robust against noise; However, phase correlation is not robust against blur degradation in frames. In scenarios where only one of the frames is blurred or when the two frames have different blur extents, phase correlation does not achieve an accurate estimation of the motion vector. We also show that the number of motion vectors estimated by the block-matching technique is reduced in such scenarios; therefore, a technique to estimate the motion in such scenarios is strongly needed. We investigate the effects of blurring on motion estimation and show the effectiveness of our algorithm for motion estimation in blurred frames and compare it against existing methods.

show abstract

“…For example, when taking a picture, moving objects being taken at high speed or lens shake will blur the picture. In noiseless case, the convolution processes of motion blur with amplitude u and shifting angle α are given by the formula [21]…”

Section: Observed Data Generation and Kernelsmentioning

confidence: 99%

Image Deconvolution with Deep Image and Kernel Priors

Wang

Bilen

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Image deconvolution is the process of recovering convolutional degraded images, which is always a hard inverse problem because of its mathematically ill-posed property. On the success of the recently proposed deep image prior (DIP), we build an image deconvolution model with deep image and kernel priors (DIKP). DIP is a learning-free representation which uses neural net structures to express image prior information, and it showed great success in many energy-based models, e.g. denoising, super-resolution, inpainting. Instead, our DIKP model uses such priors in image deconvolution to model not only images but also kernels, combining the ideas of traditional learning-free deconvolution methods with neural nets. In this paper, we show that DIKP improve the performance of learning-free image deconvolution, and we experimentally demonstrate this on the standard benchmark of six standard test images in terms of PSNR and visual effects.

show abstract

DCT-based local motion blur detection

Cited by 24 publications

References 11 publications

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Motion Estimation in Blurred Frames Using Phase Correlation

Image Deconvolution with Deep Image and Kernel Priors

Contact Info

Product

Resources

About