Texture classification using rotation invariant models on integrated local binary pattern and Zernike moments

Abstract

More and more attention has been paid to the invariant texture analysis, because the training and testing samples generally have not identical or similar orientations, or are not acquired from the same viewpoint in many practical applications, which often has negative influences on texture analysis. Local binary pattern (LBP) has been widely applied to texture classification due to its simplicity, efficiency, and rotation invariant property. In this paper, an integrated local binary pattern (ILBP) scheme including original rotation invariant LBP, improved contrast rotation invariant LBP, and direction rotation invariant LBP is proposed which can effectively overcome the deficiency of original LBP that is ignoring contrast and direction information. In addition, for surmounting another major drawback of LBP such as locality which can result in the lack of shape and space expression of the holistic texture image, Zernike moment features are fused into the improved LBP texture features in the proposed method because they comprise orthogonal and rotation invariant property and can be easily and rapidly calculated to an arbitrary high order. Experimental results show that the proposed method can be remarkably superior to the other state-of-the-art methods when rotation invariant texture features are extracted and classified.

Using Regularized Multi-Task Learning for Schizophrenia MRI Data Classification

“…For verifying the role of multiple texture features, local binary pattern (LBP) [38] features are used to fuse in series GLCM ones because of the their advantages such as simpleness, validity, and spectrum form.…”

Texture classification of machined surfaces using image processing and machine learning techniques

“…In the GLCM, component (1, 1) holds the esteem 1 because there is one and just case in the image where two, on a level plane bordering pixels have the qualities 1 and 1. Component (1,2) in the GLCM hold the esteem 2 since there are two cases in the image where two, equitably nearby pixels have the qualities 1 and 2. Component (1,3) in the GLCM has the esteem 0 because there are no events of two on a level plane neighboring pixels with the qualities 1 and 3.…”

“…Component (1,2) in the GLCM hold the esteem 2 since there are two cases in the image where two, equitably nearby pixels have the qualities 1 and 2. Component (1,3) in the GLCM has the esteem 0 because there are no events of two on a level plane neighboring pixels with the qualities 1 and 3. Grey co framework keeps preparing the info image, checking the image for other pixel sets (i, j) and recording the total in the relating component of the GLCM.GLCM tabulates the frequency of appearance of combination of gray levels in images.…”

“…Investigation on surface texture is an intriguing topic in the image processing and machine learning domain and has applications in remote sensing, object tracking, object recognition, segmentation of images etc. [1].…”

Applying machine learning methods for characterization of hexagonal prisms from their 2D scattering patterns – an investigation using modelled scattering data

“…Building on Zernike polynomials and the general theory of moments, Teague [26] derived the Zernike moments, in which the Zernike polynomials have been used as the basis functions for the moments, and applied them to visual pattern recognition [27]. This method has been widely applied in pattern recognition [28][29][30][31].…”