Abstract
We argue that in order to understand which features are used by humans to group textures, one must start by computing thousands of features of diverse nature, and select from those features those that allow the reproduction of perceptual groups or perceptual ranking created by humans. We use the Trace transform to produce such features here. We compare these features with those produced from the co-occurrence matrix and its variations. We show that when one is not interested in reproducing human behaviour, the elements of the co-occurrence matrix used as features perform best in terms of texture classification accuracy. However, these features cannot be “trained” or “selected” to imitate human ranking, while the features produced from the Trace transform can. We attribute this to the diverse nature of the features computed from the Trace transform.
Similar content being viewed by others
Notes
Each subject created their own perceptual groups. They were in large agreement between them. The final grouping was created by taking into consideration the majority opinion. Finally, the sets created were shown back to the subjects who agreed with them.
References
Abbadeni N, Ziou D, Shengrui W (2000) Autocovariance-based perceptual textural features corresponding to human visual perception. In: Proceedings of the 15th international conference on pattern recognition, vol 3, pp 901–904, 3–7 September 2000
Chang T, Kuo CCJ (1993) Texture analysis and classification with the tree-structured wavelet transform. IEEE Trans Image Process 2:429–441
Cohen FS, Fan Z, Patel MA (1991) Classification of rotated and scaled textured images using Gaussian Markov random field models. IEEE Trans Pattern Anal Mach Intell 13(2):192–202
Haddon JF, Boyce JF (1992) Texture segmentation and region classification by orthogonal decomposition of co-occurrence matrices. In: Proceedings of the 11th international conference on pattern recognition, conference a: computer vision and applications, vol 1, pp 692–694
Haddon JF, Boyce JF (1994) Texture classification of segmented regions of FLIR images using neural networks. In: IEEE Proceeding of the 1st international conference on image processing, pp 660–664
Healey CG, Enns JT (1998) Building perceptual textures to visualize multidimensional datasets. In: Proceedings of Visualization, pp 111–118, 18–23 Octobter 1998
Haley GM, Manjunath BS (1999) Rotation-invariant texture classification using a complete space-frequency model. IEEE Trans Image Process 8(2):255–269
Haralick RM (1986) Handbook of pattern recognition and image processing. In: Young TY, Fu KS (eds) Chapter statistical image texture analysis. Academic, New York, pp 247–279
Hoogs A, Collins R, Kaucic R (2002) Classification of 3D macro texture using perceptual observables. In: Proceedings of the 16th international conference on pattern recognition, vol 4, pp 113–117
Iqbal Q, Aggarwall JK (1990) Applying perceptual grouping to content-based image retrieval: building images. IEEE Comput Soc Conf Comput Vis Pattern Recogn 1:42–48
Kadyrov A, Petrou M (1998) Application of the Trace transform to change detection. In: Singh S (ed) International conference on advances in pattern recognition. Plymouth, UK, November 23–25 1998, pp 55–62
Kadyrov A, Petrou M (2001) The trace transform and its applications. IEEE Trans Pattern Anal Mach Intell 23:811–828
Kadyrov A, Talebpour A, Petrou M (2002) Texture classification with thousands of features. In: Rosin PL, Marshall D (eds) British Machine Vision Conference, ISBN 1 901725 19 7, vol 2, pp 656–665, 2–5 September, 2002, Cardiff
Kovalev V, Petrou M (1996) Multidimensional co-occurrence matrices for object recognition and matching. Graph Models Image Process 58(3):187–197
Kovalev V, Volmer S (1998) Color co-occurrence descriptors for querying-by-example. In: Proceedings of the multimedia modeling, pp 32–38, 12–15 October 1998
Liu F, Picard R (1996) Periodicity, directionality and randomness: wold features for image modelling and retrieval. IEEE Trans Pattern Anal Mach Intell 18:722–733
Long H, Leow WK (2002) A hybrid model for invariant and perceptual texture mapping. In: Proceedings of the 16th international conference on pattern recognition, vol 1, pp 135–138
Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 18:837–842
Orrite C, Roy A, Alcolea (1999) Surface segmentation based on perceptual grouping. In: Proceedings of the international conference on image analysis and processing, pp 328–333, 27–29 September 1999
Palmer SE (1983) The psychology of perceptual organization: a transformational approach. In: Beck J, Hope B, Rosenfeld A (eds) Human and machine vision, pp 269–339
Payne JS, Heppelwhite L, Stonham TJ (1999) Perceptually based metrics for the evaluation of textural image retrieval methods. IEEE Int Conf Multimed Comput Syst 2:793–797
Petrou A, Kadyrov A (2004) Affine invariant features from the trace transform. IEEE Trans Pattern Anal Mach Intell 26(1):30–44
Rao R, Lohse GL (1993) Towards a texture naming system: identifying relevant dimensions of texture. In: Proceedings of the 4th conference on visualisation 1993, San Jose, CA, October 1993, pp 220–227
Reed T, Du Buf JMH (1993) Review of recent texture segmentation feature extraction techniques. Graph Image Process (CVGIP): Image Understand Comput Vis 57(3):359–372
Sayeed A, Petrou M, Spyrou N, Kadyrov A, Spinks T (2002) Diagnostic features of Alzheimer’s disease extracted from PET sinograms. Phys Med Biol 47:137–148
Talebpour A (2004) Texture analysis using the trace transform. PhD Thesis, University of Surrey
Teuner A, Pichler O, Santos Conde JE, Hosticka BJ (1997) Orientation- and scale-invariant recognition of textures in multi-object scenes. In: Proceedings of the international conference on image processing, vol 3, pp 174–177, 26–29 October 1997
Unser M (1986) Sum and difference histograms for texture classification. IEEE Trans Pattern Anal Mach Intell 8:118–125
Yow KC, Cipolla R (1996) A probabilistic framework for perceptual grouping of features for human face detection. In: Proceedings of the second international conference on automatic face and gesture recognition. pp 16–21, 14–16 October 1996
http://www.ux.his.no/tranden/brodatz.htm. Brodatz Album
Acknowledgments
This project was supported by the RCUK Basic Technology grant “Reverse Engineering the human vision system”.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Petrou, M., Talebpour, A. & Kadyrov, A. Reverse engineering the way humans rank textures. Pattern Anal Applic 10, 101–114 (2007). https://doi.org/10.1007/s10044-006-0054-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-006-0054-6