Skip to content
/ SFA Public

[official] No reference image quality assessment based Semantic Feature Aggregation, published in ACM MM 2017, TMM 2019

License

Notifications You must be signed in to change notification settings

lidq92/SFA

Repository files navigation

Exploiting High-Level Semantics for No-Reference Image Quality Assessment of Realistic Blur Images

Description

SFA-PLSR (Test code) for the following paper: Li, Dingquan, Tingting Jiang, and Ming Jiang. "Exploiting High-Level Semantics for No-Reference Image Quality Assessment of Realistic Blur Images." Proceedings of the 2017 ACM on Multimedia Conference. ACM, 2017.

Requirement

Framework: Caffe 1.0 + MATLAB 2016b Interface

The PLSR model uesd in the test code is trained on LIVE gblur images.

Download the ResNet-50-model.caffemodel from https://github.com/KaimingHe/deep-residual-networks and paste it into the directory "models/" before using the code!

Note for training

All we need to train is a PLSR model, where the training function is plsregress.m in MATLAB. The features are extracted from the DCNN models pre-trained on the image classification task.

Citation

Please cite our paper if it helps your research:

@inproceedings{li2017exploiting,
  title={Exploiting High-Level Semantics for No-Reference Image Quality Assessment of Realistic Blur Images},
  author={Li, Dingquan and Jiang, Tingting and Jiang, Ming},
  booktitle={Proceedings of the 2017 ACM on Multimedia Conference},
  pages={378--386},
  year={2017},
  organization={ACM}
}

[Paper] [Poster]

Contact

Dingquan Li, [email protected].

License

MIT License