A Machine Learning Approach for Image Registration Accuracy Estimation

This work continues our previous paper devoted to the application of machine learning to predict the accuracy of intensity-based image registration algorithms. Now we consider the estimation of a more complex geometric transformation involving translation, scaling and rotation. The proposed approach includes the training data creation using the Monte Carlo simulation based on the image formation model typical for image-based navigation. Then, based on the generated data, we calculate seventeen features that we have determined to be relevant for this task. The analysis of the feature importances and different machine learning algorithms performances is carried out. As the source maps, we used real images obtained by the AVIRIS radiometer and taken from Yandex maps. The proposed approach is superior to the separately taken Cramér-Rao bound method or the bootstrap simulation which is not surprising since the use of machine learning allows you to combine different sources (algorithms) using their estimates as features.

[1]  Jing Li,et al.  A Comment on “Performance Bounds on Image Registration” , 2009, IEEE Transactions on Signal Processing.

[2]  Ben Glocker,et al.  Quantitative Error Prediction of Medical Image Registration using Regression Forests , 2019, Medical Image Anal..

[3]  Vladimir V. Lukin,et al.  Efficient Discrimination and Localization of Multimodal Remote Sensing Images Using CNN-Based Prediction of Localization Uncertainty , 2020, Remote. Sens..

[4]  Joel Nothman,et al.  SciPy 1.0-Fundamental Algorithms for Scientific Computing in Python , 2019, ArXiv.

[5]  Vitaliy Dushepa,et al.  A learning-based approach for rigid image registration accuracy estimation , 2020, 2020 IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO).

[6]  Rüdiger Westermann,et al.  A Learning-Based Approach to Evaluate Registration Success , 2010, MIAR.

[7]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[8]  Imam Samil Yetik,et al.  Performance bounds on image registration , 2005, IEEE Transactions on Signal Processing.

[9]  Philippos Mordohai,et al.  Correctness Prediction, Accuracy Improvement and Generalization of Stereo Matching Using Supervised Learning , 2015, International Journal of Computer Vision.

[10]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[11]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Jan Kybic,et al.  Bootstrap Resampling for Image Registration Uncertainty Estimation Without Ground Truth , 2010, IEEE Transactions on Image Processing.

[14]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.