Blurred image regions detection using wavelet-based histograms and SVM

Kanchev, Vladimir; Tonchev, Krasimir; Boumbarov, Ognian

doi:10.1109/idaacs.2011.6072795

Cited by 10 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main idea of algorithm of wavelet-based histogram and support vector machine is on discrimination of the gradient distributions between blurred and non-blurred image regions [26]. The proposed algorithm does not need the prior knowledge about the input image and is oriented to out-of-focus blur, unlike motion blur detection as described in section 2.6.…”

Section: G Out-of-focus Blur Detection Using Wavelet-based Histogrammentioning

confidence: 99%

See 1 more Smart Citation

A Literature Survey on Blur Detection Algorithms for Digital Imaging

Koik

Ibrahim

2013

2013 1st International Conference on Artificial Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

Development of blur detection algorithms has attracted many attentions in recent years. The blur detection algorithms are found very helpful in real life applications and therefore have been developed in various multimedia related research areas including image restoration, image enhancement, and image segmentation. These researches have helped us in compensating some unintentionally blurred images, resulted from out-of-focus objects, extreme light intensity, physical imperfection of camera lenses and motion blur distortion. Overview on a few blur detection methods will be presented in this paper. The methods covered in this manuscript are based on edge sharpness analysis, low depth of field (DOF) image segmentation, blind image de-convolution, Bayes discriminant function method, non-reference (NR) block, lowest directional high frequency energy (for motion blur detection) and wavelet-based histogram with Support Vector Machine (SVM). It is found that there are still a lot of future works need to be done in developing an efficient blur detection algorithm.

show abstract

Section: G Out-of-focus Blur Detection Using Wavelet-based Histogrammentioning

confidence: 99%

“…The thick red lines are the areas where high probablility of gradient distribution of the blurred images being located, while thin and scaterred blue lines indicate the areas where high probability of gradient distribution for sharp images. (Modified from[26]. )…”

mentioning

confidence: 97%

A Literature Survey on Blur Detection Algorithms for Digital Imaging

Koik

Ibrahim

2013

2013 1st International Conference on Artificial Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

show abstract

“…This project involves the lighting and shading of the images with the use of illuminating inter image. Zivkovic et al [9] taken the eco-friendly region as the source for the analyzation. In the year of 2009 the rules and the factors indicate the performance of both physical and chemical index of water including pH, DO etc.…”

Section: Related Workmentioning

confidence: 99%

Multi-Scale Fish Segmentation Refinement Using Contour Based Segmentation

Archana

et al. 2021

Advances in Parallel Computing Technologies and Applications

View full text Add to dashboard Cite

Image processing and the analysis techniques are the increasing attention when they have enabled the non-extractive and the non-lethal approach for the collection of fisheries data. The data collection includes the following requirements such as fish size, catch estimation, regulatory compliance, species recognition and population counting. The main process that is used to measure the size of fish accurately is image segmentation. The challenges that can affect the segmentation of images include the blurring of the image areas due to the water droplets on the camera lens and the fish bodies which are out of the camera view. This project describes the automatic segmentation of fish for underwater images This segmentation algorithm implemented for identify the shape of the fish contour-based segmentation is implemented in this project. The project describes about the issues with an effective contour-based segmentation from an initial segmentation. The refinement is processed from coarse level to fine level. At the coarse level, the entire fish is aligned for the contour of the initial segmentation with trained representative contours by using iteratively reweighted least squares (IRLS). At finer levels, the refinement of contour segments is done to represent poorly segmented or missing shape parts. This method addresses the problems listed above and generates promising results with highly robust segmentation performance and length measurement.

show abstract

“…For example, Alippi et al [8] propose a method which detects external disturbances on camera lenses by comparing the blur measures of a series of frames which contain the same scene acquired from a static camera. Kanchev et al [9] propose an algorithm for detecting blurred regions in images by using wavelet-based histograms and SVM. Blur measure is defined on the fish contour to locate the water drop region by Huang et al [10].…”

Section: Related Workmentioning

confidence: 99%

Multi-Scale Fish Segmentation Refinement and Missing Shape Recovery

et al. 2019

View full text Add to dashboard Cite

Image processing and analysis techniques have drawn increasing attention since they enable a non-extractive and non-lethal approach to collecting fisheries data, such as fish size measurement, catch estimation, regulatory compliance, species recognition, and population counting. Measuring fish size accurately requires reliable image segmentation. Major challenges that can easily affect the segmentation include blurring of image areas due to water drops on the camera lens and parts of a fish body being out of the camera view. In this paper, we address each of these issues with an innovative and effective contour-based segmentation and a missing shape recovery method from an arbitrary initial segmentation. The refinement is processed from the coarse level to the fine level. At the coarse level, we align the entire fish contour of the initial segmentation with trained representative contours by using iteratively reweighted least squares (IRLS). At finer levels, we iteratively refine contour segments to represent poorly segmented or missing shape parts. This method addresses the problems listed above and generates promising results with highly robust segmentation performance and length measurement.

show abstract

Blurred image regions detection using wavelet-based histograms and SVM

Cited by 10 publications

References 12 publications

A Literature Survey on Blur Detection Algorithms for Digital Imaging

A Literature Survey on Blur Detection Algorithms for Digital Imaging

Multi-Scale Fish Segmentation Refinement Using Contour Based Segmentation

Multi-Scale Fish Segmentation Refinement and Missing Shape Recovery

Contact Info

Product

Resources

About