Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 94 | DOWNLOAD 4

Automatic defect recognition in x-ray imaging by machine learning

Download
Leroy, Pascal ULiège
Promotor(s) : Geurts, Pierre ULiège ; Marée, Raphaël ULiège
Date of defense : 6-Sep-2018/7-Sep-2018 • Permalink : http://hdl.handle.net/2268.2/5520
Details
Title : Automatic defect recognition in x-ray imaging by machine learning
Author : Leroy, Pascal ULiège
Date of defense  : 6-Sep-2018/7-Sep-2018
Advisor(s) : Geurts, Pierre ULiège
Marée, Raphaël ULiège
Committee's member(s) : Louppe, Gilles ULiège
Libertiaux, Vincent 
Greffe, Christophe 
Language : English
Discipline(s) : Engineering, computing & technology > Computer science
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] Digital radiography is widely used in medicine (e.g.: to evaluate and diagnose bones) and is increasingly used in industrial nondestructive testing (NDT) where it replaces photographic films. The latter is the focus of this work. Typically, a very efficient expert needs at least five minutes to process a single image (depending of its size), hence performing the quality assessment of a single object is very time consuming.

The purpose of this project is to decrease the work load of the human operator: specifically, the goal is to identify suspicious areas and not to classify defects with their type nor automate the whole NDT process, the human agent will always deliver the final decision according to its own expertise on those suspicious zones. Because defect recognition is usually performed on sensitive objects (e.g.: parts of aircrafts), the mandatory constraint imposed is that the detection algorithm must be tuned to never miss a real defect.

The protocol is explained. Tree-based ensemble methods, especially extremely randomized trees, have been used to learn defect representation from small patches sampled in the image. Defect patches are sampled using the annotation polygons provided in the datasets. No-defect patches are sampled randomly, with the possibility to use a mask to restrict the possible areas of extraction. To test a never seen image, a sliding window is used to extract consecutive patches that are then given a defectiveness probability by the model. Finally, these probabilities are aggregated to form a score heat map for each pixel.

To assess the quality of the protocol, specifically the amount of false positive achieved when tuning it to not miss any defect, four datasets are used. Two are composed of synthetic defects (of the same type) that we have generated and two are real ones, provided by \textit{X-RIS}.

The best achieved result is for the synthetic dataset of high intensity defects where only 6 additional non-defective zones must be analyzed by the human operator in addition to the 17 generated one. For the two real datasets, the amount of no-defective zones detected is high. For the best one, there are 2108 misclassified zones for 130 correctly classified zones representing 124 defects.

Finally, the entire protocol seems to be relevant but the patch classifier must be improved. On one hand, there are multiple of other image descriptors that can be evaluated, either engineered ones or learned ones (e.g.: with neural networks). On the other hand, there exist other classifiers than random forest and extremely randomized trees: a softmax layer in neural networks or support vector machines.


File(s)

Document(s)

File
Access Leroy_TFE_Abstract.pdf
Description: -
Size: 57.4 kB
Format: Adobe PDF
File
Access Leroy_TFE_Report.pdf
Description: -
Size: 6.52 MB
Format: Adobe PDF

Annexe(s)

File
Access Leroy_TFE_code.zip
Description: -
Size: 45.11 kB
Format: Unknown

Author

  • Leroy, Pascal ULiège Université de Liège > Master ingé. civ. info., à fin.

Promotor(s)

Committee's member(s)

  • Louppe, Gilles ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
    ORBi View his publications on ORBi
  • Libertiaux, Vincent X-Ray Imaging Solutions
  • Greffe, Christophe X-Ray Imaging Solutions
  • Total number of views 94
  • Total number of downloads 4










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.