Nataliia Semenenko Tõnis Saar and Marlon Dumas nataliiamarlondumasutee Institute of Computer Science University of Tartu Estonia tonissaarstaccee Browsrbite and STACC Tallinn Estonia ID: 484774
Download Presentation The PPT/PDF document "Browserbite: Accurate Cross-Browser Test..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Browserbite: Accurate Cross-Browser Testing via Machine Learning Over Image Features
Nataliia Semenenko*,
Tõnis Saar
** and
Marlon Dumas*
*{nataliia,marlon.dumas}@ut.ee,
Institute of Computer Science,
University of Tartu, Estonia
**tonis.saar@stacc.ee,
Browsrbite and STACC, Tallinn, EstoniaSlide2
OutlineIntroduction
Visual cross-browser testing
Machine learning model
Results and future workSlide3
Cross-browser visual testing
Internet Explorer 9
Internet
Explorer 8
Where’s
that
button
?Slide4
Goal Develop method for cross-browser visual layout testing
Replace human labor in visual testing
Evaluate detected errorsSlide5
MethodsDOM (Document Object Model) based: Mogotest (www.mogotest.com), Browsera (www.browsera.com)
Image processing – non-invasive black box testing –
Our current approach
Web page
Static imageSlide6
Cross-Browser Visual testingSlide7
Web page visual segmentationImage segmentation into regions of interest (ROI)
ROI comparison
www.htcomp.eeSlide8
ROI comparison
Position
Size
Geometry
Correlation
ROI from WIN7 Chrome
ROI from WIN7 IE8
VSSlide9
Visual testing results
Test set of 140 web pages from
alexa.com
98% recall
66% precision
Example of true positive
Example of false positiveSlide10
ROI comparison + ML
Web page
Static image
Image
segmentation
(
into ROIs
)
ROI
comparison
Classification
Slide11
Machine learning140 most popular websites of Estonia according to
www.alexa.com
1200 potential incompatibilities
40 subjects from 6
countries
Two classes :False positive vs True postive
Each ROI pair had 8 judgments
Inter-rater reliability 0,94 Slide12
ROI features10 histogram bins
Correlation index
Horizontal and vertical position
Horizontal and vertical size
Configuration index
Mismatch DensitySlide13
Machine learningNeural network
Three layers
11 neurons in hidden layer
Five-fold cross-validation
Classification treeSlide14
Results and Conclusions
Measure
Plain Browserbite
Mogotest
Classification tree
Neural network
Precision
0.66
0.75
0.844
0.964
Recall
0.98
0.82
0.792
0.886
F-score
0.79
0.78
0.81
0.923Slide15
Results and conclusions
Choudhary
, S.R., Prasad, M.R., and
Orso
, A. (2012).
CrossCheck
: Combining Crawling and Differencing to Better Detect Cross-browser Incompatibilities in Web Applications.
(
ICST), 2012 IEEE Fifth International Conference On, pp. 171–180.Choudhary, S.R., Versee, H., and
Orso, A. (2010). WEBDIFF: Automated identification of cross-browser issues in web applications. (ICSM), pp. 1–10.
Tool
Mogotest
CrossCheck [1]
WebDiff [2]
BB+ML
Precision
75%
36%
21%96%Slide16
Future workCombination of image processing and DOM methods
Dynamic content suppressionSlide17
Thank You!