MRAD: Means for Rapid Algorithm Development

This work presents a generalizable test environment platform which can load multiple algorithms and au-tomatically run them with an image database to determine their performance based on various metrics of interest. This is useful because it enables algorithm developers to develop and test algorithms for various systems without physical access to those systems. The output will be text and graphical data communicating performance such as hit rates, ROC curves, proportion correct, and other methods of estimating detection, as well as the algorithm run time. The platform provides great flexibility by easily integrating algorithms written in various programming languages, allowing for uniform measurement of similar algorithms deployed in different software environments, and working on both Windows and Linux. This platform has many appli-cations within the non-destructive evaluation community, including anomaly detection, feature extraction, and quality assurance. As an example, this work will analyze the performance of algorithms running on a database of duel energy X-rays stored as DICOS files.

References

[1] V. R. Basil and A. J. Turner. Iterative enhancement: A practical technique for software development. IEEE Transactions on Software Engineering, SE-1(4):390–396, Dec 1975.

[2] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool. Speeded-up robust features (surf). Computer Vision and Image Understanding, 110(3):346 – 359, 2008.

[3] Edward S Jimenez, Ismael Perez, and Andrew C Wantuch. A generalizable radiography algorithm test environment for nde applications. In ASNT Annual Conference 2016, pages 66–70, 2016.

[4] Luo Juan and Oubong Gwun. A comparison of sift, pca-sift and surf. International Journal of Image Processing (IJIP), 3(4):143–152, 2009.

[5] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110, 2004.

[6] Domingo Mery, Vladimir Riffo, Irene Zuccar, and Christian Pieringer. Automated x-ray object recog-nition using an efficient search algorithm in multiple views. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 368–374, 2013.

[7] Diana Turcsany, Andre Mouton, and Toby P Breckon. Improving feature-based object recognition for x-ray baggage security screening using primed visualwords. In Industrial Technology (ICIT), 2013 IEEE International Conference on, pages 1140–1145. IEEE, 2013.

[8] NEMA IIC 1 v01. Digital imaging and communications in security (dicos) information object definitions (iods), 2010.

[9] Andrea Vedaldi and Brian Fulkerson. Vlfeat: An open and portable library of computer vision al-gorithms. In Proceedings of the 18th ACM International Conference on Multimedia, MM ’10, pages 1469–1472, New York, NY, USA, 2010. ACM.

[10] Andrew C Wantuch, Joshua A Vita, Edward S Jimenez, and Iliana E Bray. Exploration of available feature detection and identification systems and their performance on radiographs. In SPIE Optical Engineering+ Applications, pages 996907–996907. International Society for Optics and Photonics, 2016.

Metrics
Usage Shares
Total Views
5 Page Views
Total Shares
0 Tweets
5
0 PDF Downloads
0
0 Facebook Shares
Total Usage
5