Papers by Azeddine Beghdadi
A new approach for analyzing the blur effect on real images is proposed. This approach is based o... more A new approach for analyzing the blur effect on real images is proposed. This approach is based on the Multiplicative Multi-resolution Decomposition MMD. From MMD image-content analysis, a blind image quality measure dedicated to blur is then derived. The proposed measure has been applied on Gaussianblurred and JPEG2000-compressed images from the LIVE, TID and IVC databases. The performance of the proposed measure is evaluated and compared with some referenced image quality metrics. The experimental results measured in terms of correlation with the subjective assessment of the images, demonstrate the efficiency of the proposed image quality measure in predicting the amount of blur.
2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006
In this paper we address a denoising technique based on calculation of non local means through ne... more In this paper we address a denoising technique based on calculation of non local means through neighborhoods. Non local neighborhoods are computed in a transformed domain, namely the wavelet domain. A noisy image is transformed using a lifting scheme. The wavelet coefficients in each subband image are modelized by a Generalized Gaussian Distribution (GGD) whose parameters (scale and shape parameters) are estimated using an appropriate technique. The estimated parameters are used to define a generalized non local mean which allows us to restore the original image. Processing in the wavelet domain is suitable since image are often available in a compressed domain, beside, processing smaller images allows us to reduce the computational cost.
This paper presents a new approach to trajectorybased
Abnormal Behavior Detection (ABD). While ex... more This paper presents a new approach to trajectorybased
Abnormal Behavior Detection (ABD). While existing
techniques include position in the feature vector, we propose
to estimate the probability distribution locally at each position,
hence reducing the dimensionality of the feature vector.
Local information derived from accumulated knowledge for a
particular position is integrated in the distribution enabling
context-based decision for ABD. A stochastic competitive learning
algorithm is employed to estimate the local distributions of the
feature vector and the location of the distribution modes. The
proposed algorithm is tested on the detection of driving under
the influence of alcohol. The performance of the new algorithm
is evaluated on synthetic data. First the local stochastic learning
algorithm is compared to its global variant. Then it is compared
to the Kohonen self organizing feature maps. In both cases, the
proposed algorithm achieves higher detection rates (at the same
false alarm rate) with fewer clusters.
Robust vehicle tracking is essential in traffic
monitoring because it is the groundwork to higher... more Robust vehicle tracking is essential in traffic
monitoring because it is the groundwork to higher level tasks
such as traffic control and event detection. This paper describes
a new technique for tracking vehicles with mean-shift using
a projective Kalman filter. The shortcomings of the meanshift
tracker, namely the selection of the bandwidth and
the initialization of the tracker, are addressed with a fine
estimation of the vehicle scale and kinematic model. Indeed, the
projective Kalman filter integrates the non-linear projection of
the vehicle trajectory in its observation function resulting in an
accurate localization of the vehicle in the image. The proposed
technique is compared to the standard Extended Kalman filter
implementation on traffic video sequences. Results show that
the performance of the standard technique decreases with the
number of frames per second whilst the performance of the
projective Kalman filter remains constant.
In this paper, a new perceptually adaptive method for
reducing the blocking and ringing artifacts... more In this paper, a new perceptually adaptive method for
reducing the blocking and ringing artifacts encountered
in image compression is proposed. The method consists
of three steps: (i) blocking-ringing artifacts detection, (ii)
perceptual distortion measure and (iii) blocking-ringing
artifacts reduction. The performance of the proposed
method is evaluated objectively and subjectively in terms
of image fidelity and blocking, ringing and blur effects
reduction. The obtained results are very promising and
confirm once more the efficiency of perceptual
approaches in image processing.
In this paper we propose a denoising technique based on nonlocal
means using an image similarity ... more In this paper we propose a denoising technique based on nonlocal
means using an image similarity measure. The idea is
to use the SVD-based image quality metric as a measure of
neighborhood similarity. This measure is then used in the
computation of the spatial Gaussian weighting kernel. We
also develop an optimization computation scheme using a parallel
architecture in order to accelerate the filtering process
on different machines or different cores on the same machine.
The obtained results are very promising.
Recently, digital image inpainting has attracted
strong research interest because of its extensiv... more Recently, digital image inpainting has attracted
strong research interest because of its extensive applications
in real life. The terminology ”inpainting” refers to automatic
restoration of image defects such as scratches or blotches as well
as removal of unwanted objects as, for instance, subtitles, logos,
etc, such that it is undetectable by viewers without the reference
to the original image. Many works on this subject have been published
in recent years. This paper introduces a novel unsupervised
image completion framework using a modified exemplar-based
method in conjunction with a pyramidal representation of an
image. A top-down iterative completion is performed gradually
with multi-resolution patches and a window-based priority. The
proposed approach is verified on different natural images. Also,
a comparison with some existing methods coming from literature
is carried out and the results show improvement in favor of our
approach.
The recent developments in 3D display technology have
opened new horizons and have raised a numbe... more The recent developments in 3D display technology have
opened new horizons and have raised a number of challenges
related to the processing and coding of 3D media. Today,
stereoscopic image technology is becoming widely used in
many fields. The physical limitations of image acquisition
systems, however, make stereoscopic technology far from
being the most widely accepted solution. Furthermore, the
depth/disparity extreme ranges may subject the viewers’ eyes
to additional strain, causing more discomfort. To address
this issue, we propose in this paper to improve stereoscopic
image quality by a novel contrast enhancement method that
combines local edges and depth information. The contrast
is increased locally, at specific depth levels for left and right
views. The increase of contrast is controlled based on the
depth information, and aims at promoting the nearest objects
in the 3D scene. The results obtained from a psychophysical
experiment are encouraging and show that the proposed
method produces stereo images that are less stressful on the
eyes, thus providing more pleasant viewing experience.
A novel objective measure for assessing the quality of image inpainting
is proposed. In contrast ... more A novel objective measure for assessing the quality of image inpainting
is proposed. In contrast to standard image quality metrics,
the proposed one takes into account some constraints and
characteristics related to the specific goals of inpainting techniques.
The idea is to combine spatial low-level features and
perceptual criteria in the design of the objective Image Inpainting
Quality Metric (IIQM). The used characteristics are the visual
coherence of the recovered regions and the visual saliency
describing the visual importance of an area. Experimental results
demonstrate the good performance of the proposed IIQM and its
well adaptation to the evaluation of image inpainting results.
Image quality assessment is still an active field of research.
The main objective of the develope... more Image quality assessment is still an active field of research.
The main objective of the developed image quality metric is
to offer an index of quality that is consistent with the human
subjective judgment of image quality. Despite the great
number of developed metrics, there is still a need for image
analysis tools that is able to extract the most perceptual
relevant characteristics of an image. The goal of this work is
then to propose a more advanced analysis and representation
tools to extract more effective features that could be
incorporated in the design of the image quality metric. In
this paper, we propose a novel objective metric based on
wave atoms transform. This new transform is half multiscale
and half multi-directional. It offers a better
representation of images containing oscillatory patterns and
textures than the others known transforms [10]. In this work,
we propose a new full reference image quality metric based
on wave atom transform and exploiting some properties of
the human visual system. The consistency of the proposed
metric with subjective evaluation is performed on LIVE
database. The obtained correlation of this metric with the
MOS provided by the database is better than other known
metrics confirming thus the efficiency of this new image
quality measure in predicting image quality.
Image quality assessment is still an active field of research.
The main objective of the develope... more Image quality assessment is still an active field of research.
The main objective of the developed image quality metric is
to offer an index of quality that is consistent with the human
subjective judgment of image quality. Despite the great
number of developed metrics, there is still a need for image
analysis tools that is able to extract the most perceptual
relevant characteristics of an image. The goal of this work is
then to propose a more advanced analysis and representation
tools to extract more effective features that could be
incorporated in the design of the image quality metric. In
this paper, we propose a novel objective metric based on
wave atoms transform. This new transform is half multiscale
and half multi-directional. It offers a better
representation of images containing oscillatory patterns and
textures than the others known transforms [10]. In this work,
we propose a new full reference image quality metric based
on wave atom transform and exploiting some properties of
the human visual system. The consistency of the proposed
metric with subjective evaluation is performed on LIVE
database. The obtained correlation of this metric with the
MOS provided by the database is better than other known
metrics confirming thus the efficiency of this new image
quality measure in predicting image quality.
A new free reference image quality index based on the perceptual
blur estimation is proposed. Her... more A new free reference image quality index based on the perceptual
blur estimation is proposed. Here, we limit the study to isotropic blurring degradation
although the principle could be extended to other distortions. The main
idea developed here is to exploit the limitation of the blurring discriminability
of the Human Visual System (HVS). The proposed method consists of adding a
small amount of blur to the image and measuring its impact on the image quality
level. From the two images, a perceptual map is then obtained using some
HVS characteristics. A quality index is finally derived by extracting some geometrical
features from the blurring map visibility. The obtained results are
compared with some known methods.
Block based transform coding is the most popular
technique for image and video compression. Howev... more Block based transform coding is the most popular
technique for image and video compression. However, images
compressed using block based algorithms exhibit highly visible
blocking artifacts. We propose an iterative algorithm to reduce
these artifacts using a map computed by summation of the
horizontal and vertical profiles of the gradient vector
magnitude. This map is then used as an input to a recursive filter
to reduce the blocking effect. The results of the proposed method
have been compared to some recent and efficient deblocking
algorithms. Experimental results show that the proposed method
is simple and yields a subjective quality that is nearly free of
blocking artifacts.
This article introduces a new particle filtering approach for object tracking in video sequences.... more This article introduces a new particle filtering approach for object tracking in video sequences. The projective
particle filter uses a linear fractional transformation, which projects the trajectory of an object from the real
world onto the camera plane, thus providing a better estimate of the object position. In the proposed particle
filter, samples are drawn from an importance density integrating the linear fractional transformation. This
provides a better coverage of the feature space and yields a finer estimate of the posterior density. Experiments
conducted on traffic video surveillance sequences show that the variance of the estimated trajectory is
reduced, resulting in more robust tracking.
2011 IEEE Symposium On Computational Intelligence For Multimedia, Signal And Vision Processing, 2011
Computer Vision, Graphics, and Image Processing, 1989
2011 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2011
Block based transform coding is the most popular technique for image and video compression. Howev... more Block based transform coding is the most popular technique for image and video compression. However, images compressed using block based algorithms exhibit highly visible blocking artifacts. We propose an iterative algorithm to reduce these artifacts using a map computed by summation of the horizontal and vertical profiles of the gradient vector magnitude. This map is then used as an input to a recursive filter to reduce the blocking effect. The results of the proposed method have been compared to some recent and efficient deblocking algorithms. Experimental results show that the proposed method is simple and yields a subjective quality that is nearly free of blocking artifacts.
2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2009
A new reference-free image quality index based on spectral analysis is proposed. The main idea is... more A new reference-free image quality index based on spectral analysis is proposed. The main idea is based on exploiting the limitations of the Human Visual System (HVS) in blur detection,. The proposed method consists of adding blur to the test image and measuring its impact. The impact is measured using radial analysis in the frequency domain. The efficiency of the proposed method is tested objectively by comparing it to some well known algorithms and in terms of correlation with subjective scores.
10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), 2010
Measurement of visual signal quality is of fundamental importance in a broad range of application... more Measurement of visual signal quality is of fundamental importance in a broad range of applications. The ultimate goal of quality assessment algorithms is to assess automatically the quality of images or videos in agreement with subjective human quality judgments. We discuss in this paper a new approach for ranking quality measures across different types of degradation that affect a given image. To rank the different image quality indices, we propose to use the concept of mutual information or information content. The experimental results show that the proposed ranking of quality indices is superior to the ranking based on second order correlation coefficients.
10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), 2010
Paris 13 , 2 LT1R, faculte d'electronique et d'informatique, USTHB, Alger.
Uploads
Papers by Azeddine Beghdadi
Abnormal Behavior Detection (ABD). While existing
techniques include position in the feature vector, we propose
to estimate the probability distribution locally at each position,
hence reducing the dimensionality of the feature vector.
Local information derived from accumulated knowledge for a
particular position is integrated in the distribution enabling
context-based decision for ABD. A stochastic competitive learning
algorithm is employed to estimate the local distributions of the
feature vector and the location of the distribution modes. The
proposed algorithm is tested on the detection of driving under
the influence of alcohol. The performance of the new algorithm
is evaluated on synthetic data. First the local stochastic learning
algorithm is compared to its global variant. Then it is compared
to the Kohonen self organizing feature maps. In both cases, the
proposed algorithm achieves higher detection rates (at the same
false alarm rate) with fewer clusters.
monitoring because it is the groundwork to higher level tasks
such as traffic control and event detection. This paper describes
a new technique for tracking vehicles with mean-shift using
a projective Kalman filter. The shortcomings of the meanshift
tracker, namely the selection of the bandwidth and
the initialization of the tracker, are addressed with a fine
estimation of the vehicle scale and kinematic model. Indeed, the
projective Kalman filter integrates the non-linear projection of
the vehicle trajectory in its observation function resulting in an
accurate localization of the vehicle in the image. The proposed
technique is compared to the standard Extended Kalman filter
implementation on traffic video sequences. Results show that
the performance of the standard technique decreases with the
number of frames per second whilst the performance of the
projective Kalman filter remains constant.
reducing the blocking and ringing artifacts encountered
in image compression is proposed. The method consists
of three steps: (i) blocking-ringing artifacts detection, (ii)
perceptual distortion measure and (iii) blocking-ringing
artifacts reduction. The performance of the proposed
method is evaluated objectively and subjectively in terms
of image fidelity and blocking, ringing and blur effects
reduction. The obtained results are very promising and
confirm once more the efficiency of perceptual
approaches in image processing.
means using an image similarity measure. The idea is
to use the SVD-based image quality metric as a measure of
neighborhood similarity. This measure is then used in the
computation of the spatial Gaussian weighting kernel. We
also develop an optimization computation scheme using a parallel
architecture in order to accelerate the filtering process
on different machines or different cores on the same machine.
The obtained results are very promising.
strong research interest because of its extensive applications
in real life. The terminology ”inpainting” refers to automatic
restoration of image defects such as scratches or blotches as well
as removal of unwanted objects as, for instance, subtitles, logos,
etc, such that it is undetectable by viewers without the reference
to the original image. Many works on this subject have been published
in recent years. This paper introduces a novel unsupervised
image completion framework using a modified exemplar-based
method in conjunction with a pyramidal representation of an
image. A top-down iterative completion is performed gradually
with multi-resolution patches and a window-based priority. The
proposed approach is verified on different natural images. Also,
a comparison with some existing methods coming from literature
is carried out and the results show improvement in favor of our
approach.
opened new horizons and have raised a number of challenges
related to the processing and coding of 3D media. Today,
stereoscopic image technology is becoming widely used in
many fields. The physical limitations of image acquisition
systems, however, make stereoscopic technology far from
being the most widely accepted solution. Furthermore, the
depth/disparity extreme ranges may subject the viewers’ eyes
to additional strain, causing more discomfort. To address
this issue, we propose in this paper to improve stereoscopic
image quality by a novel contrast enhancement method that
combines local edges and depth information. The contrast
is increased locally, at specific depth levels for left and right
views. The increase of contrast is controlled based on the
depth information, and aims at promoting the nearest objects
in the 3D scene. The results obtained from a psychophysical
experiment are encouraging and show that the proposed
method produces stereo images that are less stressful on the
eyes, thus providing more pleasant viewing experience.
is proposed. In contrast to standard image quality metrics,
the proposed one takes into account some constraints and
characteristics related to the specific goals of inpainting techniques.
The idea is to combine spatial low-level features and
perceptual criteria in the design of the objective Image Inpainting
Quality Metric (IIQM). The used characteristics are the visual
coherence of the recovered regions and the visual saliency
describing the visual importance of an area. Experimental results
demonstrate the good performance of the proposed IIQM and its
well adaptation to the evaluation of image inpainting results.
The main objective of the developed image quality metric is
to offer an index of quality that is consistent with the human
subjective judgment of image quality. Despite the great
number of developed metrics, there is still a need for image
analysis tools that is able to extract the most perceptual
relevant characteristics of an image. The goal of this work is
then to propose a more advanced analysis and representation
tools to extract more effective features that could be
incorporated in the design of the image quality metric. In
this paper, we propose a novel objective metric based on
wave atoms transform. This new transform is half multiscale
and half multi-directional. It offers a better
representation of images containing oscillatory patterns and
textures than the others known transforms [10]. In this work,
we propose a new full reference image quality metric based
on wave atom transform and exploiting some properties of
the human visual system. The consistency of the proposed
metric with subjective evaluation is performed on LIVE
database. The obtained correlation of this metric with the
MOS provided by the database is better than other known
metrics confirming thus the efficiency of this new image
quality measure in predicting image quality.
The main objective of the developed image quality metric is
to offer an index of quality that is consistent with the human
subjective judgment of image quality. Despite the great
number of developed metrics, there is still a need for image
analysis tools that is able to extract the most perceptual
relevant characteristics of an image. The goal of this work is
then to propose a more advanced analysis and representation
tools to extract more effective features that could be
incorporated in the design of the image quality metric. In
this paper, we propose a novel objective metric based on
wave atoms transform. This new transform is half multiscale
and half multi-directional. It offers a better
representation of images containing oscillatory patterns and
textures than the others known transforms [10]. In this work,
we propose a new full reference image quality metric based
on wave atom transform and exploiting some properties of
the human visual system. The consistency of the proposed
metric with subjective evaluation is performed on LIVE
database. The obtained correlation of this metric with the
MOS provided by the database is better than other known
metrics confirming thus the efficiency of this new image
quality measure in predicting image quality.
blur estimation is proposed. Here, we limit the study to isotropic blurring degradation
although the principle could be extended to other distortions. The main
idea developed here is to exploit the limitation of the blurring discriminability
of the Human Visual System (HVS). The proposed method consists of adding a
small amount of blur to the image and measuring its impact on the image quality
level. From the two images, a perceptual map is then obtained using some
HVS characteristics. A quality index is finally derived by extracting some geometrical
features from the blurring map visibility. The obtained results are
compared with some known methods.
technique for image and video compression. However, images
compressed using block based algorithms exhibit highly visible
blocking artifacts. We propose an iterative algorithm to reduce
these artifacts using a map computed by summation of the
horizontal and vertical profiles of the gradient vector
magnitude. This map is then used as an input to a recursive filter
to reduce the blocking effect. The results of the proposed method
have been compared to some recent and efficient deblocking
algorithms. Experimental results show that the proposed method
is simple and yields a subjective quality that is nearly free of
blocking artifacts.
particle filter uses a linear fractional transformation, which projects the trajectory of an object from the real
world onto the camera plane, thus providing a better estimate of the object position. In the proposed particle
filter, samples are drawn from an importance density integrating the linear fractional transformation. This
provides a better coverage of the feature space and yields a finer estimate of the posterior density. Experiments
conducted on traffic video surveillance sequences show that the variance of the estimated trajectory is
reduced, resulting in more robust tracking.