MSc Dissertation: Carlos Lopez
Novel image processing of 3D textures ,
Heriot-Watt University.
Entire MSc Dissertation PDF
Abstract
A new invariant-rotation texture operator, known as LBPROT (Local Binary Pattern Rotation-Invariant), has been recently developed by M. Pietikäinen, T. Ojala and Z. Xu. It has demonstrated much better performance at classifying textures than the well-known CSAR (Circular-Symmetric Autoregressive Random Field). This paper extends the experiments carried out then, and boards an alternative series of experiments in order to find out further information regarding LBPROT operator's behaviour.
Among the experiments performed, an analysis of the operator's variability before distinct samples of the same texture under equal illumination conditions was accomplished. Furthermore, a research aiming at understanding the operator's response when applied to different directionality features is widely presented. Moreover, some extra experiments utilize the operator output distribution to classify textures by using the G Statistic log-likelihood pseudo-metric. Finally, all these investigations are assessed leading to a series of interesting results which are discussed in dept .
Table of Contents
List of figures and tables
Acknowledgements
Abstract
Chapter 1 – Introduction
1.1 Motivation & Objectives
1.2 Document Organization
Chapter 2 - Background Theories
2.1 Introduction
2.2 Illumination direction factors
2.3 Texture directionality taxonomy
2.4 Texture measures
Chapter 3 - LBPROT operator
3.1 Introduction
3.2 LBP Algorithm
3.3 LBPROT Algorithm
Chapter 4 - Classification based on LBPROT outputs
4.1 Patterns Distribution
4.2 Discrimination using G Statistic
Chapter 5 – Experimental research
5.1 Introduction
5.2 Output variability based on the same texture
5.2.1 Results
5.2.2 Assessments
5.3 Investigation of unidirectional textures
5.3.1 Results
5.3.2 Assessments
5.4 Investigation of bidirectional textures
5.4.1 Results
5.4.2 Assessments
5.5 Investigation of multidirectional textures
5.5.1 Results
5.5.2 Assessments
5.6 G statistic experiments
5.6.1 Results5.6.2 Assessments
Chapter 6 – Conclusions
Chapter 7 – Future work
References
Appendix A: Source code
Appendix B: Excel format files