A FRAMEWORK FOR ANALYZING TEXTURE DESCRIPTORS
Timo Ahonen and Matti Pietik¨ ainen
Machine Vision Group, University of Oulu, PL 4500, FI-90014 Oulun yliopisto, Finland
Local Binary Pattern, KTH-TIPS, MR8, Gabor, Texture descriptor.
This paper presents a new unified framework for texture descriptors such as Local Binary Patterns (LBP)
and Maximum Response 8 (MR8) that are based on histograms of local pixel neighborhood properties. This
framework is enabled by a novel filter based approach to the LBP operator which shows that it can be seen
as a special filter based texture operator. Using the proposed framework, the filters to implement LBP are
shown to be both simpler and more descriptive than MR8 or Gabor filters in the texture categorization task. It
is also shown that when the filter responses are quantized for histogram computation, codebook based vector
quantization yields slightly better results than threshold based binning at the cost of higher computational
Texture is a fundamental property of surfaces, and
automated analysis of textures has applications rang-
ing from remote sensing to document image analysis
(Tuceryan and Jain, 1998). Recent findings in apply-
ing texture methods to face image analysis, for ex-
ample, indicate that texture might have applications
in new fields of computer vision that have not been
considered texture analysis problems. Because of the
importance of texture analysis, a wide variety of dif-
ferent texture descriptors have been presented in the
literature. However, there is no formal definition of
the phenomenon of texture itself that the researchers
would agree upon. This is possibly one of the reasons
that so far no unified theory or no unified framework
of texture descriptors has been presented.
The Local Binary Pattern (LBP) (Ojala et al.,
2002), Maximum Response 8 (Varma and Zisserman,
2005) and Gabor filter based texture descriptors are
among the most studied and best known recent tex-
ture analysis techniques. Despite the large number
of publications discussing these methods, the connec-
tions and differences between them are not well un-
derstood. This paper presents a new unified frame-
work for these texture descriptors, which allows for a
systematic comparison of these widely used descrip-
tors and the parts that they are built of.
LBP is an operator for image description that is
based on the signs of differences of neighboring pix-
els. It is fast to compute and invariant to monotonic
gray-scale changes of the image. Despite being sim-
ple, it is very descriptive, which is attested by the
wide variety of different tasks it has been success-
fully applied to. The LBP histogram has proven to
be a widely applicable image feature for, e.g., texture
classification, face analysis, video background sub-
traction, etc. (The Local Binary Pattern Bibliography,
Another frequently used approach in texture de-
scription is using distributions of quantized filter re-
sponses to characterize the texture (Leung and Malik,
2001), (Varma and Zisserman, 2005). In the field of
texture analysis, filtering and pixel value based tex-
ture operators have been seen as somewhat contradic-
tory. However, in this paper we show that the local
binary pattern operator can be seen as a filter oper-
ator based on local derivative filters at different ori-
entations and a special vector quantization function.
Apart from clarifying the connections between LBP
and filter based methods, this also helps analyzingthe
properties of the LBP operator.
2 THE LOCAL BINARY PATTERN
The local binary pattern operator (Ojala et al., 2002)
is a powerful means of texture description. The orig-
inal version of the operator labels the pixels of an
image by thresholding the 3x3-neighborhoodof each
5 DISCUSSION AND
In this paperwe have presenteda novelunified frame-
work under which the histogram based texture de-
scription methods such as local binary pattern and
MR8 descriptors can be explained and analyzed. This
framework allows for systematic comparison of dif-
ferent texture descriptors and the parts that the de-
scriptors are built of. Such novel approach can be
useful in analyzing texture descriptors since they are
usually presented as a sequence of steps whose rela-
tion to other texture description methods is unclear.
The framework presented in this work allows for ex-
plicitly illustrating the connection between the parts
of the LBP and MR8 descriptors and experimenting
with the performance of each part.
The filter sets and vector quantization techniques
for LBP, MR8 and Gabor filter based texture descrip-
tors were compared in the this paper. In this com-
parison it was found out that the local derivative fil-
ter responses are both fastest to compute and most
descriptive. This somewhat surprising result further
attests the previous findings that texture descriptors
relying on small-scale pixel relations yield compara-
ble or even superior results to those based on filters of
larger spatial support (Ojala et al., 2002), (Varma and
When comparing the different vector quantization
methods, codebook based quantization was discov-
ered to be slightly more descriptive than thresholding
combining local derivative and Gabor filter responses
showed that these filter sets may be complementary
and may yield better performance than either of the
Not only does the presented frameworkcontribute
to understanding and comparison of existing texture
descriptors but it can be utilized for more systematic
development of new, even better performing meth-
ods. The framework is simple to implement and to-
gether with the publicly available KTH-TIPS2 image
database it can be easily used for comparing novel
descriptors with the current state-of-the-art methods.
and vectorquantizerdesign are possible, especially as
new invariancepropertiesof the descriptorsare aimed
Caputo, B., Hayman, E., and Mallikarjuna, P.(2005). Class-
specific material categorisation. In Proc. ICCV 2005,
Clausi, D. A. and Jernigan, M. E. (2000). Designing Gabor
filters for optimal texture separability. Pattern Recog-
Gray, R. M. and Neuhoff, D. L. (1998). Quantization. IEEE
Trans. Image Process, 44(6):2325–2383.
Grigorescu, S. E., Petkov, N., and Kruizinga, P. (2002).
Comparison of texture features based on Gabor filters.
IEEE Trans. Image Process., 11(10):1160–1167.
Leung, T. and Malik, J. (2001). Representing and recog-
nizing the visual appearance of materials using three-
dimensional textons. Int. J. Comput. Vision, 43(1):29–
Mallikarjuna, P., Fritz, M., Targhi, A. T., Hayman,
Manjunath, B. S. and Ma, W.-Y. (1996). Texture features
for browsing and retrieval of image data. IEEE Trans.
Pattern Anal. Mach. Intell., 18(8):837–842.
Ojala, T., Pietik¨ ainen, M., and M¨ aenp¨ a¨ a, T. (2002). Mul-
tiresolution gray-scale and rotation invariant texture
classification with local binary patterns. IEEE Trans.
Pattern Anal. Mach. Intell., 24(7):971–987.
Ojala, T., Valkealahti, K., Oja, E., and Pietik¨ ainen, M.
(2001). Texture discrimination with multidimensional
distributions of signed gray-level differences. Pattern
Pudil, P., Novovicov´ a, J., and Kittler, J. (1994). Floating
search methods in feature selection. Pattern Recogni-
tion Letters, 15(10):1119–1125.
TheLocal Binary Pattern
Tuceryan, M. and Jain, A. K. (1998). Texture analysis. In
Chen, C. H., Pau, L. F., and Wang, P. S. P., editors,
The Handbook of Pattern Recognition and Computer
Vision (2nd Edition), pages 207–248. World Scientific
Varma, M. andZisserman, A.(2003). Textureclassification:
Are filter banks necessary? In Proc. CVPR 2003, vol-
ume 2, pages 691–698.
Varma, M. and Zisserman, A. (2004). Unifying statistical
texture classification frameworks. Image Vision Com-
Varma, M. and Zisserman, A. (2005). A statistical approach
to texture classification from single images. Interna-
tional Journal of Computer Vision, 62(1–2):61–81.
Yan, S., Wang, H., Tang, X., and Huang, T. S. (2007). Ex-
ploring feature descriptors for face recognition.
Proc. ICASSP 2007.
VISAPP 2008 - International Conference on Computer Vision Theory and Applications