Can Exposure, Noise and Compression Affect Image Recognition? An Assessment of the Impacts on State-of-the-Art ConvNets

Steffens, Cristiano Rafael; Messias, Lucas Ricardo Vieira; Drews, Paul; Botelho, Sílvia Silva da Costa

doi:10.1109/lars-sbr-wre48964.2019.00019

Cited by 11 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Steffens, C.R. et al [25] evaluated the robustness of several high-level image recognition models and examined their performance in the presence of different image distortions. They proposed a testing framework that emulated bad exposure conditions, low-range image sensors, lossy compression, and commonly observed noise types.…”

Section: Related Workmentioning

confidence: 99%

Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

Benbarrad

Eloutouate

Arioua

et al. 2021

JSAN

View full text Add to dashboard Cite

Machine vision is increasingly replacing manual steel surface inspection. The automatic inspection of steel surface defects makes it possible to ensure the quality of products in the steel industry with high accuracy. However, the optimization of inspection time presents a great challenge for the integration of machine vision in high-speed production lines. In this context, compressing the collected images before transmission is essential to save bandwidth and energy, and improve the latency of vision applications. The aim of this paper was to study the impact of quality degradation resulting from image compression on the classification performance of steel surface defects with a CNN. Image compression was applied to the Northeastern University (NEU) surface-defect database with various compression ratios. Three different models were trained and tested with these images to classify surface defects using three different approaches. The obtained results showed that trained and tested models on the same compression qualities maintained approximately the same classification performance for all used compression grades. In addition, the findings clearly indicated that the classification efficiency was affected when the training and test datasets were compressed using different parameters. This impact was more obvious when there was a large difference between these compression parameters, and for models that achieved very high accuracy. Finally, it was found that compression-based data augmentation significantly increased the classification precision to perfect scores (98–100%), and thus improved the generalization of models when tested on different compression qualities. The importance of this work lies in exploiting the obtained results to successfully integrate image compression into machine vision systems, and as appropriately as possible.

show abstract

Section: Related Workmentioning

confidence: 99%

Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

Benbarrad

Eloutouate

Arioua

et al. 2021

JSAN

View full text Add to dashboard Cite

show abstract

“…We did not train our networks for dealing with these distortions. These scenarios were emulated with the application of gamma power transformation and quantile-based truncation, as proposed in [24]. As Adaptive LIFT-SLAM fine-tuned with Euroc sequences obtained the best overall results, we tested it under the described scenarios and compared its performance with ORB-SLAM under the same scenarios.…”

Section: Robustness Testsmentioning

confidence: 99%

LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method

Bruno

Colombini

2020

Anais Estendidos Do XII Simpósio Brasileiro De Robótica E XVII Simpósio Latino Americano De Robótica (SBR/LARS Estendido 2020)

View full text Add to dashboard Cite

The Simultaneous Localization and Mapping (SLAM) problem addresses the possibility of a robot to localize itself in an unknown environment and simultaneously build a consistent map of this environment. Recently, cameras have been successfully used to get the environment’s features to perform SLAM, which is referred to as visual SLAM (VSLAM). However, classical VSLAM algorithms can be easily induced to fail when the robot motion or the environment is too challenging. Although new approaches based on Deep Neural Networks (DNNs) have achieved promising results in VSLAM, they still are unable to outperform traditional methods. To leverage the robustness of deep learning to enhance traditional VSLAM systems, we propose to combine the potential of deep learning-based feature descriptors with the traditional geometry-based VSLAM, building a new VSLAM system called LIFT-SLAM. Experiments conducted on KITTI and Euroc datasets show that deep learning can be used to improve the performance of traditional VSLAM systems, as the proposed approach was able to achieve results comparable to the state-of-the-art while being robust to sensorial noise. We enhance the proposed VSLAM pipeline by avoiding parameter tuning for specific datasets with an adaptive approach while evaluating how transfer learning can affect the quality of the features extracted.

show abstract

“…This allowed us to evaluate the algorithms' robustness to camera sensor noise, simulating camera ill exposure conditions. We simulated camera overexposure and underexposure with the application of gamma power transformation, as proposed in [24].…”

Section: Datasetsmentioning

confidence: 99%

A Comparative Evaluation of Learned Feature Descriptors on Hybrid Monocular Visual SLAM Methods

Bruno

Colombini

2020

2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Educ

View full text Add to dashboard Cite

Classical Visual Simultaneous Localization and Mapping (VSLAM) algorithms can be easily induced to fail when either the robot's motion or the environment is too challenging. The use of Deep Neural Networks to enhance VSLAM algorithms has recently achieved promising results, which we call hybrid methods. In this paper, we compare the performance of hybrid monocular VSLAM methods with different learned feature descriptors. To this end, we propose a set of experiments to evaluate the robustness of the algorithms under different environments, camera motion, and camera sensor noise. Experiments conducted on KITTI and Euroc MAV datasets confirm that learned feature descriptors can create more robust VSLAM systems.

show abstract

Can Exposure, Noise and Compression Affect Image Recognition? An Assessment of the Impacts on State-of-the-Art ConvNets

Cited by 11 publications

References 20 publications

Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method

A Comparative Evaluation of Learned Feature Descriptors on Hybrid Monocular Visual SLAM Methods

Contact Info

Product

Resources

About