Abstract
In this chapter, we introduce the concepts of “view” and “characteristic view”. This view concept is quite different from those of gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP). We emphasize on how to precisely describe the features of a texture and how to extract texture features directly from a sample patch (i.e., sub-image), and how to use these features to classify an image texture. The view concepts and related methods work with a group of pixels instead of a single pixel. Three principles are used in this work for developing the model: (1) texture features from a view should carry as much information as possible for image classification; (2) the algorithm should be kept as simple as possible; and (3) the computational time to distinguish different texture classes should be the minimum. The view-related concepts are suitable for textures that are generated by one or more basic local patterns and repeated in a periodic manner over some image region. The set of characteristic views is a powerful feature extraction and representation to describe an image texture. As different textures show different patterns, the patterns of a texture also show different views. If a set of characteristic views is properly defined, it is possible to use this set of characteristic views for texture classification. The K-views template is an algorithm that uses many characteristic views, denoted by K, for the classification of images. The K-views algorithm is suitable for classifying image textures that have basic local patterns repeated periodically.
Heaven signifies night and day, cold and heat, times and seasons.
—Sun Zhu
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Carr JR (1999) Classification of digital image texture using variograms. In: Atkinson PM, Tate NJ (ed) Advances in remote sensing and GIS analysis. Wiley, New York, pp 135–146
Carr JR, Miranda FP (1998) The semivariogram in comparison to the co-occurrence matrix for classification for image texture. IEEE Trans Geosci Remote Sens 36(6):1945–1952
Chellappa R, Chatterjee S (1985) Classification of textures using gaussian markov random fields. IEEE Trans Acoust Speech Signal Process 33(4):959–963
Gurney CM, Townshend JRG (1983) The use of contextual information in the classification of remotely sensed data. Photogramm Eng Remote Sens 49(1):55–64
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621
Hung CC, Yang S, Laymon C (2002) Use of characteristic views in image classification. In: Proceedings of 16th international conference on pattern recognition, pp 949–952
Hung CC, Karabudak D, Pham M, Coleman T (2004) Experiments on image texture classification with K-views classifier, markov random fields and cooccurrence probabilities. In: Proceedings of the 2004 IEEE international geoscience & remote sensing symposium (IGARSS), Anchorage, Alaska, 20–24 Sept 2004
Lee JH, Phipot WD (1991) Spectral texture pattern matching: a classifier for digital imagery. IEEE Trans Geosci Remote Sens 29(4):545–554
Tou JT, Gonzalez RC (1974) Pattern recognition principles. Addison-Wesley, Reading
Woods JW (1972) Two-dimensional discrete Markovian fields. IEEE Trans Inf Theory 18:232–240
Xiang M, Hung CC, Pham M, Coleman T (2005) Spatial models for image texture classification: an experiment. In: Proceedings of the 4th international conference on information and management sciences, Kunming, China, 1–10 July 2005, pp 341–343, ISSN 1539-2023
Yang S, Hung CC (2003) Image texture classification using datagrams and characteristic views. In: Proceedings of the 18th ACM symposium on applied computing (SAC), Melbourne, FL, 9–12 March 2003, pp 22–26. https://doi.org/10.1145/952532.952538
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Hung, CC., Song, E., Lan, Y. (2019). Basic Concept and Models of the K-views. In: Image Texture Analysis. Springer, Cham. https://doi.org/10.1007/978-3-030-13773-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-13773-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-13772-4
Online ISBN: 978-3-030-13773-1
eBook Packages: Computer ScienceComputer Science (R0)