International Journal of Computer Applications (0975 – 8887) Volume 19– No.7, April 2011 22 Morphological Shape features for Classification of Textures based on Fuzzy Texture Element M. Rama Bai Associate Professor M.G.I.T, JNTUH, Hyderabad Andhra Pradesh, India Dr.V.Venkata Krishna Principal C.I.E.T, JNTUK, Kakinada Rajahmundry, Andhra Pradesh, India J.Sasi Kiran Associate Professor V.V.I.T, JNTUH, Hyderabad Andhra Pradesh, India ABSTRACT Texture is an important spatial feature useful for identifying objects or regions of interest in an image. The present paper derives a new set of texture features, which are morphological shape components derived from the fuzzy texture elements of a 3x3 mask. The proposed fuzzy texture element patterns (FTP‘s) extract textural information of an image with a more complete respect of texture characteristics in all the eight directions instead of only one displacement vector. The proposed FTP‘s retains discriminating power of texture elements. In the present paper, five simple morphological shape components are evaluated on each of the derived FTP. The experimental results on the five groups of texture images clearly show the efficacy and simplicity of the present method. Keywords: Morphological Shape components, Textural information, Classification, Fuzzy texture element. 1. INTRODUCTION The present paper used textural properties for classification of textures [1, 2, 3, 4, 5]. Texture is the term used to characterize the surface of a given object or phenomenon and is undoubtedly one of the main features used in image processing, pattern recognition and multispectral scanner images obtained from aircraft or satellite platforms to microscopic images of cell cultures or tissue samples. That's why the research on texture classification and analysis has received considerable attention in recent years. There are several other areas like metallography [6] and umber processing [7] that make extensive use of textural features such as grain patterns and shapes, size, and distribution for classifying and analyzing specimens. The study of patterns on textures is recognized as an important step in characterization and recognition of texture [17, 18, 24, 25, 26]. Various approaches are in use to investigate the textural and spatial structural characteristics of image data, including measures of texture [8], Fourier analysis [9, 10], fractal dimension [11], variograms [12, 13] and local variance measures [14]. Fourier analysis is found as the most useful when dealing with regular patterns within image data. It is used to filter out speckle in radar data [15] and to remove the effects of regular agricultural patterns in image data [15]. Study of regular patterns based on fundamentals of local variance was carried out recently [16]. Texture and pattern were recognized as important attributes of image data. Patterns are used extensively in the visual interpretation of image data, in which texture is often more important than the other image attributes. Depending on the context, the word pattern has many different interpretations. Textures are classified by pattern based approaches [11, 19, 20, 15]. This explains that the texture is characterized not only by gray value at a given pixel, but also by the gray value pattern in the surrounding pixels. The texture has both local and global meaning, in the sense that it is characterized by the invariance of certain local attributes that are distributed over a region of an image. Based on this texture and pattern relation the present paper attempted to classify various texture images based on fuzzy texture element patterns (FTP‘s), which is different from the earlier studies. The proposed FTP method retains discriminating power of texture elements derived by He and Wang [21, 22] in a better way. The present paper is organized as follows. The section 2 defines morphology and shape features, Section 3 describe the methodology, the results and discussions are presented in section 4 and conclusions are listed in section 5. 2. MORPHOLOGY & SHAPE FEATURES Mathematical morphology is a well-founded non-linear theory of image processing [27, 28, 29, 30, 31]. Its geometry-oriented nature provides an efficient framework for analyzing object shape characteristics such as size and connectivity, which are not easily accessed by linear approaches. Morphological operations take into consideration the geometrical shape of the image objects to be analyzed. Mathematical morphology is theoretically founded on set theory. It contributes a wide range of operators to image processing, based on a few simple mathematical concepts. An image can be represented by a set of pixels. A morphological operation uses two sets of pixels, i.e., two images: the original data image to be analyzed and a structuring element (also called kernel) which is a set of pixels or a pattern constituting a specific shape such as a line, a disk, or a square. A structuring element is characterized by a well- defined shape (such as line, segment, or any pattern), size, and origin. Its shape can be regarded as a parameter to a morphological operation. In mathematical morphology, neighborhoods are, defined by the structuring element, i.e., the shape of the structuring element determines the shape of the neighborhood in the image. Mathematical Morphology is based on logical transformations of the image (this is no constraint when these transformations are generalized in terms of set definitions) carried out by using the set theoretical operations. This would enable us to make several measurements on the image, like trend, directional effect