A phase congruency based patch evaluator for complexity reduction in multi-dictionary based single-image super-resolution

A flexible single-image super-resolution (SISR) framework based on multi-dictionary based SISR (MDSISR) is proposed.A phase congruency (PC) based patch evaluator is proposed to classify the low resolution patches into three categories in this framework.Different types of images are scaled up adaptively by different methods.Compared with conventional MDSISR, our method reduces conisderable computational complexity without much deterioration in both visual and numberical results. Single-image based super-resolution (SISR) aims to recover a high-resolution (HR) image from one of its degraded low-resolution (LR) images. To improve the quality of reconstructed HR image, many researchers attempt to adopt multiple pairs of dictionaries to sparsely represent the image patches. Conventionally, all the patches with different contents are treated equally, and each patch is coded by multiple pairs of dictionaries, which results in tremendous computational burden in the reconstruction process. In this paper, a phase congruency (PC) based patch evaluator (PCPE) is proposed to divide the LR patches into three categories: significant, less-significant and smooth based on the complexity of the contents. Thus, a flexible multi-dictionary based SISR (MDSISR) framework is proposed, which reconstructs different patches by different approaches. In this framework, multiple dictionaries are only applied to scale up the significant patches to maintain high reconstruction accuracy. Also, two simpler baseline approaches are used to reconstruct the less-significant and smooth patches, respectively. Experimental studies on benchmark database demonstrate that the proposed method can achieve competitive PSNR, SSIM, and FSIM with some state-of-the-art SISR approaches. Besides, it can reduce the computational cost in conventional MDSISR significantly without much degradation in visual and numerical results.

• Publication year

  2016

• Venue

  Information Sciences

• Publication date

  2016-11-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1016/j.ins.2016.05.024
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A fast deconvolution-based approach for single-image super-resolution with GPU acceleration

  2018cited by this paper
• Bilevel optimization of block compressive sensing with perceptually nonlocal similarity

  2016cited by this paper
• Video super-resolution using an adaptive superpixel-guided auto-regressive model

  2016cited by this paper
• Breast cancer discriminant feature analysis for diagnosis via jointly sparse learning

  2016cited by this paper
• Dual-sparsity regularized sparse representation for single image super-resolution

  2015cited by this paper
• Learning Multiple Linear Mappings for Efficient Single Image Super-Resolution

  2015cited by this paper
• SAR Image Registration Using Phase Congruency and Nonlinear Diffusion-Based SIFT

  2015cited by this paper
• Sparse Support Regression for Image Super-Resolution

  2015cited by this paper
• Nonrigid Structure From Motion via Sparse Representation

  2015cited by this paper
• Single image super-resolution via 2D sparse representation

  2015cited by this paper
• Complexity reduction in multi-dictionary based single-image superresolution reconstruction via pahse congtuency

  2015cited by this paper
• Phase congruency analysis of down-sampled and blurring images for foreground extraction

  2015cited by this paper
• Combining sparse representation and local rank constraint for single image super resolution

  2015cited by this paper
• Robust sparse signal reconstructions against basis mismatch and their applications

  2015cited by this paper
• A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution

  2014cited by this paper
• Learning a Deep Convolutional Network for Image Super-Resolution

  2014cited by this paper
• A Unified Learning Framework for Single Image Super-Resolution

  2014cited by this paper
• Unsupervised images segmentation via incremental dictionary learning based sparse representation

  2014cited by this paper
• Semantic preserving distance metric learning and applications

  2014cited by this paper
• Video super-resolution based on automatic key-frame selection and feature-guided variational optical flow

  2014cited by this paper
• Superresolution Mapping Using Multiple Dictionaries by Sparse Representation

  2014cited by this paper
• No-training, no-reference image quality index using perceptual features

  2013cited by this paper
• Rank Preserving Sparse Learning for Kinect Based Scene Classification

  2013cited by this paper
• A Sparse-Group Lasso

  2013cited by this paper
• Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution

  2013cited by this paper
• Depth image super-resolution using multi-dictionary sparse representation

  2013cited by this paper
• Person Re-Identification by Regularized Smoothing KISS Metric Learning

  2013cited by this paper
• Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

  2013cited by this paper
• Fast Direct Super-Resolution by Simple Functions

  2013cited by this paper
• Multiple Learned Dictionaries Based Clustered Sparse Coding for the Super-Resolution of Single Text Image

  2013cited by this paper
• Image super-resolution by extreme learning machine

  2012cited by this paper
• Coupled Dictionary Training for Image Super-Resolution

  2012cited by this paper
• Single-Image Super-Resolution Reconstruction via Learned Geometric Dictionaries and Clustered Sparse Coding

  2012cited by this paper
• Multitask dictionary learning and sparse representation based single-image super-resolution reconstruction

  2011cited by this paper
• Blind Image Quality Assessment Using a General Regression Neural Network

  2011cited by this paper
• Image Super-Resolution Via Sparse Representation

  2010cited by this paper
• Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

  2010cited by this paper
• On Single Image Scale-Up Using Sparse-Representations

  2010cited by this paper
• Behavioral / Systems / Cognitive Representation of Cross-Frequency Spatial Phase Relationships in Human Visual Cortex

  2009cited by this paper
• Phase congruency features for palm-print verification

  2009cited by this paper
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit

  2007cited by this paper
• Real-Time Image Restoration for Iris Recognition Systems

  2007cited by this paper
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

  2006cited by this paper
• Image quality assessment: from error visibility to structural similarity

  2004cited by this paper
• Phase Congruency Detects Corners and Edges

  2003cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• Iterative Methods for Total Variation Denoising

  1996cited by this paper
• Image Features from Phase Congruency

  1995cited by this paper
• Adaptive Thresholding for the DigitalDesk

  1993cited by this paper
• A k-means clustering algorithm

  1979cited by this paper

• Biological Basis and Computer Vision Applications of Image Phase Congruency: A Comprehensive Survey

  2024cites this paper
• SPCM: Image quality assessment based on symmetry phase congruency

  2020cites this paper
• Face hallucination through differential evolution parameter map learning with facial structure prior

  2019cites this paper
• Progressive Perception-Oriented Network for Single Image Super-Resolution

  2019cites this paper
• Collaborative block compressed sensing reconstruction with dual-domain sparse representation

  2019cites this paper
• Novel Quantum Video Steganography and Authentication Protocol with Large Payload

  2018cites this paper
• Gradient boosting for single image super-resolution

  2018cites this paper
• Piecewise linear regression-based single image super-resolution via Hadamard transform

  2018cites this paper
• Fractional-Grey Wolf optimizer-based kernel weighted regression model for multi-view face video super resolution

  2017cites this paper
• PET and MRI image fusion based on combination of 2-D Hilbert transform and IHS method

  2017cites this paper
• Super resolution reconstruction of medical image based on adaptive quad-tree decomposition

  2017cites this paper
• Single image superresolution by multiple geometrical regressors

  2017cites this paper
• Local patch encoding-based method for single image super-resolution

  2017cites this paper
• A Novel Quantum Video Steganography Protocol with Large Payload Based on MCQI Quantum Video

  2017cites this paper