Residual Networks Based Distortion Classification and Ranking for Laparoscopic Image Quality Assessment

@article{Khan2020ResidualNB,
  title={Residual Networks Based Distortion Classification and Ranking for Laparoscopic Image Quality Assessment},
  author={Zohaib Amjad Khan and Azeddine Beghdadi and Mounir Kaaniche and Faouzi Alaya Cheikh},
  journal={2020 IEEE International Conference on Image Processing (ICIP)},
  year={2020},
  pages={176-180}
}
Laparoscopic images and videos are often affected by different types of distortion like noise, smoke, blur and nonuniform illumination. Automatic detection of these distortions, followed generally by application of appropriate image quality enhancement methods, is critical to avoid errors during surgery. In this context, a crucial step involves an objective assessment of the image quality, which is a two-fold problem requiring both the classification of the distortion type affecting the image… 
[PDF] Semantic Reader
7 Citations
Background Citations
2
Methods Citations
3

Figures and Tables from this paper

7 Citations

Transfer Learning and Decision Fusion for Real Time Distortion Classification in Laparoscopic Videos

The problem of multiple distortions in the same video was formulated as a multi-label distortion classification problem and the approach of transfer learning with decision fusion was applied and was found to outperform other solutions in terms of accuracy.

A neural network based framework for effective laparoscopic video quality assessment

Spatio-temporal deep learning model for distortion classification in laparoscopic video

This paper aims to address the laparoscopic video distortion identification problem by developing fast and accurate multi-label distortion classification using a deep learning model that is able to run in real-time with low inference time.

End-to-End Blind Quality Assessment for Laparoscopic Videos using Neural Networks

Experimental results have shown the efficiency of the proposed neural network-based approaches for distortion classification as well as quality prediction compared to recent conventional and deep learning based approaches.

Arthroscopic Multi-Spectral Scene Segmentation Using Deep Learning

This work proposed a scene segmentation method that successfully segments multi structures in knee arthroscopy and confirmed that the surgical site exhibits several limitations, among others, lack of discriminative contextual information such as texture and features which drastically limits this vision task.

A Perceptual Quality-driven Video Surveillance System

This paper proposes an architecture of a smart surveillance system that incorporates the perceptual quality of acquired scenes and shows that some of the state-of-the-art image/video quality metrics do not work in the context of video-surveillance.

A novel multi-branch wavelet neural network for sparse representation based object classification

References

SHOWING 1-10 OF 23 REFERENCES

Deeprn: A Content Preserving Deep Architecture for Blind Image Quality Assessment

This work is the first that applies a fine-tuned residual deep learning network (ResNet-101) to BIQA, and shows clear improvements of the accuracy of the estimated MOS values, compared to current state-of-the-art algorithms.

A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network

  • A. Chetouani
  • Computer Science
    2018 26th European Signal Processing Conference (EUSIPCO)
  • 2018
This paper proposes an image quality framework without reference based on selection of saliency patches and Convolutional Neural Network, which was evaluated using four well-known datasets to show its efficiency.

Learning to Rank for Blind Image Quality Assessment

This paper explores and exploits preference image pairs such as the quality of image Ia is better than that of image Ib for training a robust BIQA model and investigates the utilization of a multiple kernel learning algorithm based on group lasso to provide a solution.

Multiscale deep desmoking for laparoscopic surgery

This paper proposes an end-to-end network which takes the smoke image and its Laplacian image pyramid decomposition as inputs, and outputs a smoke free image directly without relying on any physical models or estimation of intermediate parameters.

Convolutional Neural Networks for No-Reference Image Quality Assessment

A Convolutional Neural Network is described to accurately predict image quality without a reference image to achieve state of the art performance on the LIVE dataset and shows excellent generalization ability in cross dataset experiments.

A deep neural network for image quality assessment

This paper presents a no reference image (NR) quality assessment (IQA) method based on a deep convolutional neural network (CNN). The CNN takes unpreprocessed image patches as an input and estimates…

NIMA: Neural Image Assessment

The proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks and can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline.

Multi-task rank learning for image quality assessment

  • Long XuJia Li Yihua Yan
  • Computer Science
    2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2015
The experimental results confirm that the proposed Multi-task Rank Learning based IQA (MRLIQ) approach is prominent among all state-of-the-art NR-IQA approaches and a novel no-reference (NR) IQA approach can be derived.

Towards a video quality assessment based framework for enhancement of laparoscopic videos

A framework for automatically detecting and identifying distortions and their severity using video quality assessment and a publicly available database for quality assessment of laparoscopic videos evaluated by expert as well as non-expert observers are proposed.

A Two-Step Framework for Constructing Blind Image Quality Indices

A new two-step framework for no-reference image quality assessment based on natural scene statistics (NSS) is proposed, which does not require any knowledge of the distorting process and the framework is modular in that it can be extended to any number of distortions.