Cognitive Aspects of Object Recognition - Recognition of Objects by Texture

Abstract To study human image cognition is more than ever an important topic since the number of vision-based materials has been increased over the years. Texture seems to be a powerful tool to describe the appearances of objects. Therefore, very flexible and powerful texture descriptors are of importance that allow to recognize the texture and to understand what makes up the texture. The most used texture descriptor is the well-known texture descriptor based on the co-occurrence matrix. We propose a texture descriptor based on random sets. This descriptor gives us more freedom in describing different textures. In this paper, we compare the two texture descriptors based on a medical data set. We review the theory of the two texture descriptors and describe the procedure for the comparison of the two methods. Polyp images are used that are derived from colon examination. Decision tree induction is used to learn a classifier model. Cross-validation is used to calculate the error rate. The comparison of the two texture descriptors is based on the error rate, the properties of the two best classification models, the runtime for the feature calculation, the selected features, and the semantic meaning of the texture descriptors. The medical data set was chosen since texture seems to play an important role in describing medical objects.

[1]  Tony F. Chan,et al.  Structure-Texture Image Decomposition—Modeling, Algorithms, and Parameter Selection , 2006, International Journal of Computer Vision.

[2]  Robert M. Gray,et al.  Image classification by a two dimensional hidden Markov model , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[3]  Thomas S. Huang,et al.  Image processing , 1971 .

[4]  Roziati Zainuddin,et al.  Analysis of visual features in local descriptor for multi-modality medical image , 2014, Int. Arab J. Inf. Technol..

[5]  Petra Perner.  Classificaiton of HEp-2 Cells Using Fluorescent Image Analysis and Data Mining , 2001, ISMDA.

[6]  Luc Van Gool,et al.  Texture analysis Anno 1983 , 1985, Comput. Vis. Graph. Image Process..

[7]  Sasan Mahmoodi,et al.  Gaussian Markov random field based improved texture descriptor for image segmentation , 2014, Image Vis. Comput..

[8]  J. Macgregor,et al.  Image texture analysis: methods and comparisons , 2004 .

[9]  Wei Chen,et al.  Establishment and ultrasound characteristics of atherosclerosis in rhesus monkey , 2015, Biomedical engineering online.

[10]  Fabrice Mériaudeau,et al.  SIFT Texture Description for Understanding Breast Ultrasound Images , 2014, Digital Mammography / IWDM.

[11]  Rama Chellappa,et al.  Multiresolution Gauss-Markov random field models for texture segmentation , 1997, IEEE Trans. Image Process..

[12]  Xiaoyi Jiang,et al.  Colorectal Polyps Detection Using Texture Features and Support Vector Machine , 2008, MDA.

[13]  Yong Xu,et al.  A distinct and compact texture descriptor , 2014, Image Vis. Comput..

[14]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[15]  Petra Perner,et al.  Mining knowledge for HEp-2 cell image classification , 2002, Artif. Intell. Medicine.

[16]  Tieniu Tan,et al.  Brief review of invariant texture analysis methods , 2002, Pattern Recognit..

[17]  Gabriel Cristóbal,et al.  Automated pollen identification using microscopic imaging and texture analysis. , 2015, Micron.

[18]  Tuan D. Pham.  Automated identification of mitochondrial regions in complex intracellular space by texture analysis , 2014, International Conference on Graphic and Image Processing.

[19]  Gabriel Cristóbal,et al.  Texture descriptor approaches to level set segmentation in medical images , 2014, Photonics Europe.

[20]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[21]  G. Matheron.  Random Sets and Integral Geometry , 1976 .

[22]  Yi Guo,et al.  Robust phase-based texture descriptor for classification of breast ultrasound images , 2015, BioMedical Engineering OnLine.

[23]  Bailing Zhang,et al.  Multiple features based two-stage hybrid classifier ensembles for subcellular phenotype images classification , 2010 .

[24]  Pascale Dubois-Fernandez,et al.  Retrieval of Forest Stand Age From SAR Image Texture for Varying Distance and Orientation Values of the Gray Level Co-Occurrence Matrix , 2014, IEEE Geoscience and Remote Sensing Letters.

[25]  F. Cendes,et al.  Texture analysis of medical images. , 2004, Clinical radiology.

[26]  D. Stoyan,et al.  Stochastic Geometry and Its Applications , 1989 .

[27]  Jia-Lin Chen,et al.  Automatic unsupervised texture segmentation using hidden Markov model , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[28]  A. R. Rao,et al.  A Taxonomy for Texture Description and Identification , 1990, Springer Series in Perception Engineering.

[29]  Q. M. Jonathan Wu,et al.  Gaussian-Mixture-Model-Based Spatial Neighborhood Relationships for Pixel Labeling Problem , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[30]  Lance M. Kaplan.  Extended fractal analysis for texture classification and segmentation , 1999, IEEE Trans. Image Process..

[31]  Ramakrishnan Mukundan,et al.  Local Tchebichef Moments for Texture Analysis , 2014 .

[32]  Odemir Martinez Bruno,et al.  Texture descriptor combining fractal dimension and artificial crawlers , 2013, ArXiv.

[33]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..