Block-based manipulations on transform-compressed images and videos

1998 ◽  
Vol 6 (2) ◽  
pp. 113-124 ◽  
Author(s):  
Bo Shen ◽  
Ishwar K. Sethi
Keyword(s):  
Compressed Images ◽  
Block Based

Blocking artefact detection in block-based DCT compressed images

2011 ◽  
Vol 4 (3) ◽  
pp. 181
Author(s):  
Jagroop Singh ◽  
Sukhwinder Singh ◽  
Dilbag Singh ◽  
Moin Uddin
Keyword(s):  
Compressed Images ◽  
Artefact Detection ◽  
Block Based

scholarly journals SCENet: Secondary Domain Intercorrelation Enhanced Network for Alleviating Compressed Poisson Noises

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1939 ◽  
Author(s):  
Seok Bong Yoo ◽  
Mikyong Han
Keyword(s):  
Noise Reduction ◽  
Image Coding ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Poisson Noise ◽  
Art Restoration ◽  
Compressed Images ◽  
Coding Systems ◽  
Satisfactory Performance ◽  
Block Based

In real image coding systems, block-based coding is often applied on images contaminated by camera sensor noises such as Poisson noises, which cause complicated types of noises called compressed Poisson noises. Although many restoration methods have recently been proposed for compressed images, they do not provide satisfactory performance on the challenging compressed Poisson noises. This is mainly due to (i) inaccurate modeling regarding the image degradation, (ii) the signal-dependent noise property, and (iii) the lack of analysis on intercorrelation distortion. In this paper, we focused on the challenging issues in practical image coding systems and propose a compressed Poisson noise reduction scheme based on a secondary domain intercorrelation enhanced network. Specifically, we introduced a compressed Poisson noise corruption model and combined the secondary domain intercorrelation prior with a deep neural network especially designed for signal-dependent compression noise reduction. Experimental results showed that the proposed network is superior to the existing state-of-the-art restoration alternatives on classical images, the LIVE1 dataset, and the SIDD dataset.

scholarly journals Evolutionary Algorithm Based Residual Block Search for Compression Artifact Removal

2020 ◽  
Author(s):  
Rishil Shah
Keyword(s):  
Image Compression ◽  
Evolutionary Algorithm ◽  
Evolutionary Search ◽  
Residual Network ◽  
Deep Convolutional Neural Networks ◽  
Artifact Removal ◽  
Compressed Images ◽  
Block Based ◽  
Residual Block ◽  
Computational Resources

<div>Lossy image compression is ubiquitously used for</div><div>storage and transmission at lower rates. Among the existing</div><div>lossy image compression methods, the JPEG standard is the most widely used technique in the multimedia world. Over the years, numerous methods have been proposed to suppress the compression artifacts introduced in JPEG-compressed images. However, all current learning-based methods include deep convolutional neural networks (CNNs) that are manually-designed by researchers. The network design process requires extensive computational resources and expertise. Focusing on this issue, we investigate evolutionary search for finding the optimal residual block based architecture for artifact removal. We first define a residual network structure and its corresponding genotype representation used in the search. Then, we provide details</div><div>of the evolutionary algorithm and the multi-objective function</div><div>used to find the optimal residual block architecture. Finally, we present experimental results to indicate the effectiveness of our approach and compare performance with existing artifact removal networks. The proposed approach is scalable and portable to numerous low-level vision tasks.</div>

scholarly journals Evolutionary Algorithm Based Residual Block Search for Compression Artifact Removal

2020 ◽  
Author(s):  
Rishil Shah
Keyword(s):  
Image Compression ◽  
Evolutionary Algorithm ◽  
Evolutionary Search ◽  
Residual Network ◽  
Deep Convolutional Neural Networks ◽  
Artifact Removal ◽  
Compressed Images ◽  
Block Based ◽  
Residual Block ◽  
Computational Resources

<div>Lossy image compression is ubiquitously used for</div><div>storage and transmission at lower rates. Among the existing</div><div>lossy image compression methods, the JPEG standard is the most widely used technique in the multimedia world. Over the years, numerous methods have been proposed to suppress the compression artifacts introduced in JPEG-compressed images. However, all current learning-based methods include deep convolutional neural networks (CNNs) that are manually-designed by researchers. The network design process requires extensive computational resources and expertise. Focusing on this issue, we investigate evolutionary search for finding the optimal residual block based architecture for artifact removal. We first define a residual network structure and its corresponding genotype representation used in the search. Then, we provide details</div><div>of the evolutionary algorithm and the multi-objective function</div><div>used to find the optimal residual block architecture. Finally, we present experimental results to indicate the effectiveness of our approach and compare performance with existing artifact removal networks. The proposed approach is scalable and portable to numerous low-level vision tasks.</div>

scholarly journals A Post-Processing Algorithm for Spatial Domain Detection & Removal of Alocking Artifacts

2019 ◽  
Vol 8 (10) ◽  
pp. 2968-2977
Keyword(s):  
Spatial Domain ◽  
Processing Algorithm ◽  
Blocking Artifacts ◽  
Post Processing ◽  
Compressed Images ◽  
Ringing Artifacts ◽  
Initial Stage ◽  
Pixel Value ◽  
Block Based ◽  
Processing Techniques

Block based Discrete Cosine Transform (BDCT) is commonly used to detect and remove blocking artifacts in the compressed images. We proposed spatial domain post processing algorithm with four fold model. In the initial stage, pixel vector (PV) is calculated for horizontal as well as vertical block boundaries, after defining PV calculation of different threshold values is made for extracting blocking artifacts. These thresholds are basically adaptive to the image quality due to strong correlation with the PV. To avoid ringing artifacts across block edges directional filter is proposed. Our research further worked on region classification based upon activity of PV within the blocks. Based upon different PV activity regions separate filters are used to achieve best filtering and finally Symmetrical Pixel Normalization filter (SPN Filter) is used to normalize the values of symmetrical pixel value for better visual performance . Proposed technique various indices like PSNR, MSSIM, GBIM are calculated and compare with different post processing techniques used in literature

Sign in / Sign up

Export Citation Format

Share Document