Preparing IceBreaking party

SCIA 2005 HighLights

IceBreaking party

Conference Banquet in
Valamo Monastery

Post-conference tour to St.Petersburg

Texture Analysis with Local Binary Patterns: Theory and Applications

The local binary pattern (LBP) texture analysis operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. For each pixel in an image, a binary code is produced by thresholding its value with the value of the center pixel. A histogram is created to collect up the occurrences of different binary patterns. The basic version of the LBP operator considers only the eight neighbors of a pixel, but the definition has been extended to include all circular neighborhoods with any number of pixels.

Through its extensions, the LBP operator has been made into a really powerful measure of image texture, showing excellent results in terms of accuracy and computational complexity in many empirical studies. The LBP operator can be seen as a unifying approach to the traditionally divergent statistical and structural models of texture analysis. The LBP method has already been used in a large number of applications all over the world, including visual inspection, image retrieval, remote sensing, biomedical image analysis, face image analysis, motion analysis, environment modeling, and outdoor scene analysis. For more details, see

The first part of this tutorial, lectured by Prof. Matti Pietikäinen, presents the theoretical foundations of the LBP operator and introduces its different extensions.

The second part, given by Markus Turtinen, M.Sc., deals with applications of the LBP in real-time surface inspection. In addition, the learning in texture analysis is considered. The usefulness of the LBP has been recently shown in on-line paper texture characterization. This part of the tutorial shows the construction of a real-world texture classification system from fast feature extraction to on-line classification. The learning problems in texture analysis are reviewed under the terms of unsupervised feature analysis and training of a classifier. Efficient methods for labeling and visualizing high-dimensional LBP texture data are shown, providing a useful set of tools for real-world texture analysis with LBP.

The final part, lectured by Abdenour Hadid, M.Sc., deals with the application of LBP to facial image analysis, demonstrating that LBP features are also efficient in nontraditional texture analysis tasks. This part of the tutorial explains how to easily derive an efficient LBP-based facial representation which combines both the global shape and the texture of facial features into a single feature vector. The obtained representation is then applied to face detection and recognition problems yielding in excellent performance. The usefulness of the LBP-based facial representation is further investigated in a challenging problem which is the detection and recognition of low-resolution face images. The experimental results indicate that the same feature space can be used for both tasks. Finally, the application of the same methodology to several other object detection/recognition tasks is discussed.


Matti Pietikäinen received his Doctor of Technology degree in electrical engineering from the University of Oulu, Finland, in 1982. In 1981, he established the Machine Vision Group at the University of Oulu. The research results of his group have been widely exploited in industry. Currently, he is a professor of information technology, the scientific director of Infotech Oulu Research Center, and the leader of the Machine Vision Group at the University of Oulu. From 1980 to 1981 and from 1984 to 1985, he visited the Computer Vision Laboratory at the University of Maryland, USA. His research interests are in machine vision and image analysis. His current research focuses on texture analysis, face image analysis, and machine vision for sensing and understanding human actions. He has authored about 165 papers in international journals, books, and conference proceedings, and nearly 100 other publications or reports. He is Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence and Pattern Recognition journals. He was the guest editor (with L.F. Pau) of a two-part special issue on “Machine Vision for Advanced Production” for the International Journal of Pattern Recognition and Artificial Intelligence (also reprinted as a book by World Scientific in 1996). He was also the editor of the book Texture Analysis in Machine Vision (World Scientific, 2000) and has served as a reviewer for numerous journals and conferences. He was the president of the Pattern Recognition Society of Finland from 1989 to 1992. Since 1989, he has served as a member of the governing board of the International Association for Pattern Recognition (IAPR) and became one of the founding fellows of the IAPR in 1994. He has also served on committees of several international conferences. He is a senior member of the IEEE and Vice-Chair of IEEE Finland Section.

M.Sc. Abdenour Hadid

M.Sc. Markus Turtinen

Pattern Recognition Society of Finland

The International Association for Pattern Recognition