• Corpus ID: 28131016

ISION T ECHNIQUES AND D EEP L EARNING M ODEL

@inproceedings{Petricca2016ISIONTE,
  title={ISION T ECHNIQUES AND D EEP L EARNING M ODEL},
  author={Luca Petricca and Tomas Moss and Gonzalo Figueroa and Stian Broen},
  year={2016}
}
In this paper we present a comparison between standard computer vision techniques and Deep Learning approach for automatic metal corrosion (rust) detection. For the classic approach, a classification based on the number of pixels containing specific red components has been utilized. The code written in Python used OpenCV libraries to compute and categorize the images. For the Deep Learning approach, we chose Caffe, a powerful framework developed at “Berkeley Vision and Learning Center” (BVLC… 

Figures from this paper

References

SHOWING 1-5 OF 5 REFERENCES
Backpropagation Applied to Handwritten Zip Code Recognition
TLDR
This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Advanced Robot System for Automated Bridge Inspection and Monitoring
Conventional bridge inspection process is time consuming, hazardous, and may be affected by environmental conditions. It is of great interest, therefore, that an automated and/or teleoperated
Climbing robot for corrosion monitoring of reinforced concrete structures
This paper introduces a climbing robot for corrosion monitoring of reinforced concrete structures such as cooling towers, dams or bridges. The robot combines a vortex adhesion mechanism with a wheel
Classification of Defects in Sewer Pipes Using Neural Networks
Deterioration of underground infrastructure facilities such as sewer pipes poses a serious problem to most developed urban centers today. As distribution piping networks age, they deteriorate and m...
Rust Surface Area Determination of Steel Bridge Component for Robotic Grit-Blast Machine