Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Osman Gokhan Sezer is active.

Publication


Featured researches published by Osman Gokhan Sezer.


international conference on image processing | 2008

Sparse orthonormal transforms for image compression

Osman Gokhan Sezer; Oztan Harmanci; Onur G. Guleryuz

We propose a block-based transform optimization and associated image compression technique that exploits regularity along directional image singularities. Unlike established work, directionality comes about as a byproduct of the proposed optimization rather than a built in constraint. Our work classifies image blocks and uses transforms that are optimal for each class, thereby decomposing image information into classification and transform coefficient information. The transforms are optimized using a set of training images. Our algebraic framework allows straightforward extension to non-block transforms, allowing us to also design sparse lapped transforms that exploit geometric regularity. We use an EZW/SPIHT like entropy coder to encode the transform coefficients to show that our block and lapped designs have competitive rate-distortion performance. Our work can be seen as nonlinear approximation optimized transform coding of images subject to structural constraints on transform basis functions.


data compression conference | 2011

Robust Learning of 2-D Separable Transforms for Next-Generation Video Coding

Osman Gokhan Sezer; Robert A. Cohen; Anthony Vetro

With the simplicity of its application together with compression efficiency, the Discrete Cosine Transform(DCT) plays a vital role in the development of video compression standards. For next-generation video coding, a new set of 2-D separable transforms has emerged as a candidate to replace the DCT. These separable transforms are learned from residuals of each intra prediction mode, hence termed as Mode dependent-directional transforms (MDDT). MDDT uses the Karhunen-Loeve Transform (KLT) to create sets of separable transforms from training data. Since the residuals after intra prediction have some structural similarities, transforms utilizing these correlations improve coding efficiency. However, the KLT is the optimal approach only if the data has a Gaussian distribution without outliers. Due to the nature of the least-square norm, outliers can arbitrarily affect the directions of the KLT components. In this paper, we will address robust learning of separable transforms by enforcing sparsity on the coefficients of the representations. With this new approach, it is possible to improve upon the video coding performance of H.264/AVC by up to 10.2% BD-rate for intra coding. At no additional cost, the proposed techniques can also provide up to 3.9% improvement in BD-rate for intra coding compared to existing MDDT schemes.


IEEE Transactions on Image Processing | 2015

Approximation and Compression With Sparse Orthonormal Transforms

Osman Gokhan Sezer; Onur G. Guleryuz; Yucel Altunbasak

We propose a new transform design method that targets the generation of compression-optimized transforms for next-generation multimedia applications. The fundamental idea behind transform compression is to exploit regularity within signals such that redundancy is minimized subject to a fidelity cost. Multimedia signals, in particular images and video, are well known to contain a diverse set of localized structures, leading to many different types of regularity and to nonstationary signal statistics. The proposed method designs sparse orthonormal transforms (SOTs) that automatically exploit regularity over different signal structures and provides an adaptation method that determines the best representation over localized regions. Unlike earlier work that is motivated by linear approximation constructs and model-based designs that are limited to specific types of signal regularity, our work uses general nonlinear approximation ideas and a data-driven setup to significantly broaden its reach. We show that our SOT designs provide a safe and principled extension of the Karhunen-Loeve transform (KLT) by reducing to the KLT on Gaussian processes and by automatically exploiting non-Gaussian statistics to significantly improve over the KLT on more general processes. We provide an algebraic optimization framework that generates optimized designs for any desired transform structure (multiresolution, block, lapped, and so on) with significantly better n-term approximation performance. For each structure, we propose a new prototype codec and test over a database of images. Simulation results show consistent increase in compression and approximation performance compared with conventional methods.


international conference on image processing | 2010

A sparsity-distortion-optimized multiscale representation of geometry

Osman Gokhan Sezer; Yucel Altunbasak; Onur G. Guleryuz

This paper describes the construction of a new multiresolutional decomposition with applications to image compression. The proposed method designs sparsity-distortion-optimized orthonormal transforms applied in wavelet domain to arrive at a multiresolutional representation which we term the Sparse Multiresolutional Transform (SMT). Our optimization operates over sub-bands of given orientation and exploits the inter-scale and intra-scale dependencies of wavelet co-efficients over image singularities. The resulting SMT is substantially sparser than the wavelet transform and leads to compaction that can be exploited by well-known coefficient coders. Our construction deviates from the literature, which mainly focuses on model-based methods, by offering a data-driven optimization of wavelet representations. Simulation experiments show that the proposed method consistently offers better performance compared to the original wavelet-representation and can reach up to 1dB improvements within state-of-the-art coefficient coders.


Proceedings of SPIE | 2010

Postprocessing and denoising of video using sparse multiresolutional transforms

Osman Gokhan Sezer; Onur G. Guleryuz

This paper describes the construction of a set of sparsity-distortion-optimized orthonormal transforms designed for wavelet-domain image denoising. The optimization operates over sub-bands of given orientation and exploits intra-scale dependencies of wavelet coefficients over image singularities. When applied on the top of standard wavelet transforms, the resulting new sparse representation provides compaction that can be exploited in transform domain denoising via cycle-spinning.1 Our construction deviates from the literature, which mainly focuses on model-based methods, by offering a data-driven optimization of wavelet representations. Compared with translational-invariant denoising, the proposed method consistently offers better performance compared to the original wavelet-representation and can reach up to 3dB improvements.


visual communications and image processing | 2009

Adaptive boxcar/wavelet transform

Osman Gokhan Sezer; Yucel Altunbasak

This paper presents a new adaptive Boxcar/Wavelet transform for image compression. Boxcar/Wavelet decomposition emphasizes the idea of average-interpolation representation which uses dyadic averages and their interpolation to explain a special case of biorthogonal wavelet transforms (BWT). This perspective for image compression together with lifting scheme offers the ability to train an optimum 2-D filter set for nonlinear prediction (interpolation) that will adapt to the context around the low-pass wavelet coefficients for reducing energy in the high-pass bands. Moreover, the filters obtained after training is observed to posses directional information with some textural clues that can provide better prediction performance. This work addresses a firrst step towards obtaining this new set of training-based fillters in the context of Boxcar/Wavelet transform. Initial experimental results show better subjective quality performance compared to popular 9/7-tap and 5/3-tap BWTs with comparable results in objective quality.


international conference on image processing | 2009

Weighted average denoising with Sparse Orthonormal Transforms

Osman Gokhan Sezer; Yucel Altunbasak

Sparse Orthonormal Transforms (SOT) has recently been proposed as a data compression method that can achieve sparser representations in transform domain. Given initial conditions, the optimization method utilized to generate the dictionary of SOT also achieves the optimal orthonormal transform for hard thresholding. In the context of translation-invariant denoising, one can use this dictionary to represent the local neighborhood around each pixel and obtain denoised estimates for that neighborhood with hard thresholding. Building upon this approach, here we propose a method to fuse the overlapping denoised estimates via weighted linear averaging to compute final denoised signal.


international conference on image processing | 2009

Better computer vision under video compression, an example using mean shift tracking

Salman Aslam; Aaron F. Bobick; Christopher F. Barnes; Osman Gokhan Sezer

In this paper, our goal is to understand what needs to be done to enable computer vision algorithms running on uncompressed image sequences to run as well on image sequences that have undergone compression and then decompression. The central conflict of context based computer vision algorithms versus the structured block based approach of todays codecs means that more has to be done than to simply create a divide between coding foreground preferentially and giving less importance to background. We take as example, a single computer vision algorithm, the mean shift tracker and see that its performance can be improved substantially in low bit rate scenarios, albeit some tradeoffs.


international conference on pattern recognition | 2008

NorMaL: Non-compact Markovian Likelihood for change detection

Osman Gokhan Sezer; Joseph L. Mundy; Yucel Altunbasak; David B. Cooper

This paper presents a new normalcy model of a scene for change detection using images taken from multiple views and varying illumination conditions. Each coregistered pixel site is statistically modeled by a probability distribution conditioned on a set of pixels in a non-local neighborhood that are less likely to be affected by a change that happens at the pixel of interest. These ldquonon-compact neighborsrdquo are located using information theoretic approaches. The associated change detection algorithm is called non-compact Markovian Likelihood (NorMaL), which predicts normalcy of a scene based on non-compact neighborhoods using non-parametric conditional density estimation.


Archive | 2008

Image and video compression using sparse orthonormal transforms

Oztan Harmanci; Onur G. Guleryuz; Osman Gokhan Sezer

Collaboration


Dive into the Osman Gokhan Sezer's collaboration.

Top Co-Authors

Avatar

Yucel Altunbasak

Georgia Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Aaron F. Bobick

Georgia Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Anthony Vetro

Georgia Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Christopher F. Barnes

Georgia Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Salman Aslam

Georgia Institute of Technology

View shared research outputs
Researchain Logo
Decentralizing Knowledge