Corpus ID: 235458621

A Multi-task convolutional neural network for blind stereoscopic image quality assessment using naturalness analysis

  title={A Multi-task convolutional neural network for blind stereoscopic image quality assessment using naturalness analysis},
  author={Salima Bourbia and Ayoub Karine and A. Chetouani and Mohammed El Hassouni Lrit and Mohammed V Rabat and Rabat and Morocco. and Isen Yncrea Ouest and 33 Quater Chemin du Champ de Manoeuvre and 44470 Carquefou and France and Laboratoire Prisme and Universit'e d'Orl'eans and Flsh},
This paper addresses the problem of blind stereoscopic image quality assessment (NR-SIQA) using a new multi-task deep learning based-method. In the field of stereoscopic vision, the information is fairly distributed between the left and right views as well as the binocular phenomenon. In this work, we propose to integrate these characteristics to estimate the quality of stereoscopic images without reference through a convolutional neural network. Our method is based on two main tasks: the first… Expand

Figures and Tables from this paper


Blind Stereoscopic Image Quality Assessment Using Convolutional Neural Networks and Support Vector Regression
A framework for blind stereoscopic image quality metric based on Convolutional Neural Network and Support Vector Regression and the obtained results through two common datasets show the relevance of the proposed approach. Expand
Learning structure of stereoscopic image for no-reference quality assessment with convolutional neural network
The proposed no-reference metric achieves the state-of-the-art performance for quality assessment of stereoscopic images, and is even competitive to existing full-reference quality metrics. Expand
On the use of a scanpath predictor and convolutional neural network for blind image quality assessment
This paper proposes an efficient method that estimates the quality of 2D images without access to the pristine image based on the relevant patches selected by saliency information and a convolution neural network. Expand
No-Reference Stereoscopic Image Quality Assessment Using Natural Scene Statistics
  • Yanqing Li, Xinping Hu
  • Computer Science
  • 2017 2nd International Conference on Multimedia and Image Processing (ICMIP)
  • 2017
Experimental results show that the proposed objective method achieves consistent stereoscopic image quality evaluation results with subjective assessment for various types of distortion, especially show its effectiveness for assessing stereoscopic imagewithcross-distortion. Expand
Dual-Stream Interactive Networks for No-Reference Stereoscopic Image Quality Assessment
The experimental results show that the proposed StereoQA-Net outperforms state-of-the-art algorithms on both symmetrically and asymmetrically distorted stereoscopic image pairs of various distortion types and can effectively predict the perceptual quality of local regions. Expand
Full reference image quality metric for stereo images based on Cyclopean image computation and neural fusion
  • A. Chetouani
  • Computer Science
  • 2014 IEEE Visual Communications and Image Processing Conference
  • 2014
A New Stereo Full-Reference Image Quality Metric (SFR-IQM) based on Cyclopean Image computation and 2D IQM fusion and combined using an Artificial Neural Networks in order to derive a single index is presented. Expand
No-reference stereoscopic image quality assessment
A no-reference perceptual quality assessment is developed for JPEG coded stereoscopic images based on segmented local features of artifacts and disparity based on inspired by the human visual system. Expand
Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment
Experimental results demonstrated that the statistical properties of the difference image can well represent the perceptual quality of the stereoscope image, which outperforms the representative RR quality metrics for stereoscopic image and even some full reference (FR) quality metrics. Expand
Oriented Correlation Models of Distorted Natural Images With Application to Natural Stereopair Quality Evaluation
A new no-reference stereoscopic/3D IQA framework is developed, dubbed stereoscopic-3D blind image naturalness quality index, which utilizes both univariate and generalized bivariate natural scene statistics (NSS) models. Expand
Blind Image Quality Assessment for Stereoscopic Images Using Binocular Guided Quality Lookup and Visual Codebook
Experimental results on three 3-D image quality assessment databases demonstrate that in comparison with the most related existing methods, the devised algorithm achieves high consistency alignment with subjective assessment and low-complexity pooling. Expand