English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Advanced Steel Microstructure Classification by Deep Learning Methods

Azimi, S. M., Britz, D., Engstler, M., Fritz, M., & Mücklich, F. (2017). Advanced Steel Microstructure Classification by Deep Learning Methods. Retrieved from http://arxiv.org/abs/1706.06480.

Item is

Files

show Files
hide Files
:
arXiv:1706.06480.pdf (Preprint), 2MB
Name:
arXiv:1706.06480.pdf
Description:
File downloaded from arXiv at 2017-07-05 11:16
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Azimi, Seyed Majid1, Author           
Britz, Dominik2, Author
Engstler, Michael2, Author
Fritz, Mario1, Author           
Mücklich, Frank2, Author
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV, Condensed Matter, Materials Science, cond-mat.mtrl-sci
 Abstract: The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which opens doors for huge uncertainties. Since the microstructure could be a combination of different phases with complex substructures its automatic classification is very challenging and just a little work in this field has been carried out. Prior related works apply mostly designed and engineered features by experts and classify microstructure separately from feature extraction step. Recently Deep Learning methods have shown surprisingly good performance in vision applications by learning the features from data together with the classification step. In this work, we propose a deep learning method for microstructure classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Networks (FCNN) accompanied by max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy, indicating the effectiveness of pixel-wise approaches. Beyond the success presented in this paper, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.

Details

show
hide
Language(s): eng - English
 Dates: 2017-06-202017
 Publication Status: Published online
 Pages: 14 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1706.06480
URI: http://arxiv.org/abs/1706.06480
BibTex Citekey: DBLP:journals/corr/AzimiBEFM17
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show