pavancm/stitched-image-quality-evaluator

Official implementation of Stitched Image Quality evaluator (SIQE)

Stitched-Image-Quality-Evaluator

This is the MATLAB implementation of Stiched Image Quality Evaluator (SIQE) presented in the paper:

P. C. Madhusudana and R. Soundararajan, "Subjective and Objective Quality Assessment of Stitched Images for Virtual Reality," IEEE Transactions on Image Processing, vol. 28, no. 11, pp. 5620-5635, Nov 2019

Running on MATLAB

example.m file contains an example implementation of SIQE for the images present in the 'images' folder.

Dependencies

• MATLAB Pyramid toolbox (can be downloaded from HERE)
• LIBSVM Package (can be downloaded from HERE)

Note on training - This release version of SIQE was trained on the entire ISIQA database.

Kindly contact Pavan ([email protected]) if you have any questions, suggestions or corrections to the above implementation.

You can change this program as you like and use it anywhere, but please refer to its original source (cite our paper mentioned above).

Citation

@article{madhusudana2019subjective,
  author={Madhusudana, Pavan Chennagiri and Soundararajan, Rajiv},
  journal={IEEE Transactions on Image Processing}, 
  title={Subjective and Objective Quality Assessment of Stitched Images for Virtual Reality}, 
  year={2019},
  volume={28},
  number={11},
  pages={5620-5635}}

stitched-image-quality-evaluator's Issues

Very long runtime

I followed all the guidelines in the README to install the necessary toolboxes, changed the paths accordingly, and launched the example.m script using the 5 sample images provided in the images folder, but I've been waiting for a quality score for more than 45 minutes now while it is still halfway through it. I've seen the comment about the inclusion of VLFeat to remove overlapping regions possibly being quite time consuming, but is it really 45-minute-long time consuming?

Feature extraction seems indeed to be quite the bottleneck. Could this warning be the key?

You should compile the MEX version of "pointOp.c", found in the MEX subdirectory of matlabPyrTools,
and put it in your MATLAB path. It is MUCH faster.

MATLAB version: R2020b