University of Cambridge > > Electron Microscopy Group Seminars > On Gray Scale Features-Based Image Classification of Textural Type Continuous Objects

On Gray Scale Features-Based Image Classification of Textural Type Continuous Objects

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Edmund Ward.

A novel approach to Gray Scale Features-based Image Classification is presented. Used by us classifier is Support Vector Machine (SVM). Images were obtained for unbounded non-structured textural type continuous 3D objects without contour lines or layers. These were cylindrical samples (cores) drilled from amorphous porous carbon material, to be sorted into seven classes based on their structure. Their 3D X-ray microtomography (XRMT) data were studied. Although this method can be applied to a wide range of 2D and 3D raster and vector images, we present here only results related to XRMT images. The calculation of Gray Scale Features was done in a way similar to (Ronneberger et al., 2002), but we had to deal with almost completely chaotic textures without any noticeable regularity inside or well defined boundaries that could be used as key registration points for Pattern Recognition or Image Classification. These principal differences between data sets and 3D images (Ronneberger et al., 2002) led us to develop several pioneering ideas and techniques. See also (Schulz-Mirbach, 1995). Seven types of mineral carbon material were studied. It was found that it is very difficult to classify them by using traditional image analysis tools because of their complex natural structure and the fact that even different samples of the same material from the same source often exhibit significant differences in structural texture. More conservative routine of visual categorization by human operator is labour consuming and is not fully error-proof. Computational procedure was established to solve this problem. Firstly, we randomly selected 10 cylindrical cores of material in addition to a statistically proven random way of positioning drilling. Data sets of size 1024×1024x1024, obtained for these 10 cores, were later used as original 3D images. The structure of each core differed from the other cores and there was significant variation of porosity and wall topology inside a particular core. To cope with this we used a statistically viable procedure of defining approximately 100 sub-volumes each of 256×256x256 size. This sub- sampling acquired the role played before by boundary and completely black background (Ronneberger et al., 2002). Inside each sub-volume we built a mesh of randomly distributed sets of concentric spherical shells of 12 radii. We then performed Monte Carlo numerical integration over each sphere using 3 functions based on the Gray Values themselves and their local combinatorial relationships similar to (Ronneberger et al., 2002). For each texture type 240 vectors of Invariant Gray Scale Features were obtained and then used as input data for SVM statistical classification. The corresponding numerical output showed exceptionally good recognition and classification results with successful recognition in more than 97% of case. Further modification of the standard classification procedure is suggested that makes close to 100% recognition possible.

As part of recommended data scaling for SVM analysis we computed multidimensional Mean and Standard Deviation Vectors and used them later for the computational stability characterisation, since it is impossible to obtain stability characterisation analytically. We applied some controlled noise, fluctuation to Gray Scale Feature data and verified how much the SVM output changed. The shape of the obtained stability curve and computed gradient in the point of original state (i.e. with no noise applied) characterised stability itself, SVM and porous material. See (Reztsov & Jones, 2006; Jones et al., 2006) for other methods of utilising Invariant Gray Scale Features for textural type continuous objects, different internal properties of the data domain and the use of out technique for 2D density distributions of amorphous materials and for analysis of vector form data as used in atom probe style instrumentation.


Schulz-Mirbach, H. (1995). Invariant features for gray scale images. In 17 DAGM - Symposium “Mustererkennung’’, Bielefeld, 1995. Sagerer, G., Posch, S. & Kummert, F. (Eds), pp. 1-14. Reihe Informatik aktuell, Springer.

Ronneberger, O., Schultz, E., & Burkhardt, H. (2002). Automated Pollen Recognition using 3D Volume Images from Fluorescence Microscopy. Aerobiologia 18, 107 115.

Reztsov A.,V. & Jones A.S. (2006). Invariant Gray Scale Features for Pattern Recognition and Image Classification of textural type continuous objects. In Australian Conference in Microscopy and Microanalysis, Sydney, 5th-9th February 2006, p. 64.

Jones A.S., Reztsov A.V. & Loo C.E. (2006). Application of Invariant Grey Scale Features for Analysis of Porous Minerals. Micron 38, to appear.

This talk is part of the Electron Microscopy Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2019, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity