Wavelet Texture Analysis Research Articles

Image texture analysis to evaluate the microtexture of coarse aggregates for pavement surface courses

ABSTRACT The microtexture of the asphalt pavement, which is critical for the skid resistance, is dictated by the microtexture of the coarse aggregates used in the surface courses. The existing standard test methods can only capture the combined measure of coarse aggregate surface texture which can be influenced by other aggregate characteristics such as shape and angularity. Consequently, the surface texture of aggregates cannot be quantified explicitly using these tests, and therefore image analysis methods that can extract textural features are gaining more significance. In the present study, various image texture analysis methods are evaluated to identify a reliable texture indicator. Methods include traditional statistical approaches such as histogram method, Grey Level Co-occurrence Matrix (GLCM) methods, and transform-based wavelet texture analysis. The image analysis was carried out on the grey-scale scanning electron microscope (SEM) images before and after accelerated polishing. To compare the image texture parameters, the average surface roughness (Sa) measured from aggregate surface profile data obtained from a 3D Optical Surface Profilometer (3D OSP) was considered as a direct measure of surface texture. A detailed correlation analysis with Sa indicates that the surface texture index (STI) from the wavelet analysis quantifies the microtexture more accurately compared to statistical methods.

Assessment of Power Transformer Paper Ageing Using Wavelet Texture Analysis of Microscopy Images

This paper presents a wavelet texture analysis of microscopy images acquired from artificially-aged samples of power transformer winding insulation paper. Oil-impregnated Kraft paper samples are prepared for experimental tests where they are thermally stressed in an oven at temperatures above what would normally occur in operation. This accelerated ageing test arrangement is used to produce a set of paper samples with varying levels of insulation deterioration. From the paper samples, microscopy images of the paper surface are obtained using a standard optical microscope. These microscopic images are analyzed using a texture analysis method that utilizes a two-dimensional wavelet transform to extract detailed information from the wavelet decomposition coefficient matrices. These features are analyzed to assess how the texture of paper changes in response to thermal deterioration and ageing. The results suggest that the texture features are correlated to the commonly-used degree of polymerization test. Additionally, statistical classification is performed on the wavelet texture features using both supervised and unsupervised machine learning methods. The results demonstrate that differentiation between oil-impregnated paper samples with different levels of thermal degradation using wavelet texture analysis is effective.

Digital UV/VIS imaging: A rapid PAT tool for crushing strength, drug content and particle size distribution determination in tablets.

The Process Analytical Technology (PAT) and the Quality-by-Design (QbD) approaches can efficiently facilitate the shift to the desired continuous manufacturing and real time release testing (RTRT). By this, it is vital to develop new, in-line analytical methods which fulfil the pharmaceutical requirements. The fast-developing digital imaging-based machine vision systems can provide revolutionary solutions not just in the automotive industry but in the pharmaceutical technology, as well. This study aimed to explore the capabilities of UV/VIS-based machine vision in tablet inspection as a PAT tool for the determination of compression force and crushing strength, drug content and drug distribution in tablets using meloxicam a yellow model drug. In the case of determining the compression force and crushing strength, the application of multivariate wavelet texture analysis (MWTA) based models provided relatively low prediction errors. To predict the drug content of meloxicam tablets CIELAB or RGB colorspace based algorithms were successfully developed and validated. UV/VIS imaging was also used to map the particle size distribution and spatial distribution of meloxicam, the results were compared to chemical maps obtained by Raman microscopy. Digital imaging combined with multivariate data analysis might be a valuable, high throughput, in-line PAT tool for automated inspection of pharmaceutical tablets.

Measurement of Vibrated Bulk Density of Coke Particle Blends Using Image Texture Analysis

A rapid and nondestructive machine vision sensor was developed for predicting the vibrated bulk density (VBD) of petroleum coke particles based on image texture analysis. It could be used for making corrective adjustments to a paste plant operation to reduce green anode variability (e.g., changes in binder demand). Wavelet texture analysis (WTA) and gray level co-occurrence matrix (GLCM) algorithms were used jointly for extracting the surface textural features of coke aggregates from images. These were correlated with the VBD using partial least-squares (PLS) regression. Coke samples of several sizes and from different sources were used to test the sensor. Variations in the coke surface texture introduced by coke size and source allowed for making good predictions of the VBD of individual coke samples and mixtures of them (blends involving two sources and different sizes). Promising results were also obtained for coke blends collected from an industrial-baked carbon anode manufacturer.

Textural image classification of foams based on variographic analysis

Froths can be characterised according to several features, such as colour, bubble size distribution, velocity, mobility or texture. In the case of texture, there are some alternatives that can be used to analyse and classify them, like the texture spectrum analysis, the grey-level co-occurrence matrix, or the wavelet texture analysis. In this work, a variogram-based technique is introduced. Variograms are a widely used geostatistical technique to describe the degree of spatial dependence between sample values as separation between them increases, and have been used before to analyse textures in applications that range from microscopy to satellite images. The purpose of the current work is to introduce the variogram-based technique to compare and classify foams (water-air froths) according to their texture, and studying the effect of frother type on the texture of foams generated in a quasi-2D cell and in a laboratory column. In the case of the quasi-2D foams, the variogram-based textural classification algorithm was able to classify foam images according to the frother used, with an accuracy of 88.9%. In the case of the foam images generated in the laboratory column, the results suggest that foam texture is mainly defined by froth type, with some effect of foam height. The column foam images did not show similar characteristics when grouped by foam gas holdup, which was confirmed with the variogram-based textural analysis.

Ranking of fibre-reinforced composite plate surface finish quality by wavelet texture analysis

In the automotive and other industries, the visual appearance of external surfaces is a key factor in perceived product quality. Traditionally, the quality of an automotive surface finish has been judged by expert human auditors. A set of 17 fibre-reinforced composite plates was previously manufactured to have a range of surface finish qualities and these plates were ranked by three expert observers and also optically digitally imaged. Following validation of the previous rankings, the wavelet texture analysis (WTA) technique was applied to the digital photographs to derive an instrumental measure of surface finish quality based on the panel images. The rank correlation between the human expert surface finish quality ratings and those from the W TA image analysis process was found to be positive, large and statistically significant. This finding indicates that WTA could form the basis of an inexpensive and practical instrumental method for the ranking of fibre-reinforced composite surface finish quality.

Wavelet transform analysis of chromatin texture changes during heat shock.

Texture analysis can be a useful tool to investigate the organization of chromatin. Approaches based on multiscale analysis and in particular the 'à trou' wavelet analysis has already been used for microscopy (Olivo Marin). In order to analyse texture changes, the statistical properties of the wavelet coefficient images were summarized by the first four statistical orders: mean, standard deviation, skewness and kurtosis of the coefficient image histogram. The 'à trou' transform provided a representation of the wavelet coefficients and texture parameters with the same statistical robustness throughout the scale spaces. It was applied for quantifying chromatin texture and heat-induced chromatin changes in living cells. We investigated the changes by both laser scanning and spinning disk confocal microscopies and compared the texture parameters before and after increasing duration of heat shock exposure (15 min, 30 min and 1 h). Furthermore, as activation of the heat shock response also correlates with a rapid localization of HSF1 within a few nuclear structures termed nuclear stress bodies (nSBs), we compared the dynamics of nSBs formation with that of textural changes during 1 h of continuous heat shock. Next, we studied the recovery phase following a 1-h heat shock. Significant differences were observed, particularly affecting the perinucleolar region, even for the shortest heat shock time affecting mostly the skewness and standard deviation. Furthermore, progressive changes could be observed according to the duration of heat shock, mostly affecting fine details (pixel-wise changes) as revealed by the parameters, obtained from the first- and second-order wavelet coefficients. 'A trou' wavelet texture analysis provided a sensitive and efficient tool to investigate minute changes of chromatin.

An integrated multiscale and multivariate image analysis framework for process monitoring of colour random textures: MSMIA

We present an integrated approach for conducting on-line and off-line image-based monitoring of processes whose products (raw materials, intermediate or final) consist of colour random textures. The methodology combines the principles underlying wavelet texture analysis and multivariate image analysis into a single framework, able to detect both abnormal changes in texture and colour. By taking into account a scale-dependent description of colour, it can detect subtle changes on how colour interacts with texture across the several length-scales considered. The proposed methodology was studied and characterized following best practice procedures for developing statistical process control methods, where controlled simulated test scenarios are employed to generate normal operation condition (NOC) data, as well as faults of different types and magnitudes. By simulating normal operation and faulty images in this way, it is possible to assess the monitoring potential of the proposed methodology to detect abnormal situations under a diversity of monotonically increasing faulty conditions. Results show that the proposed methodology is able to effectively detect changes in both colour and texture characteristics and one type of monitoring statistics in particular leads the performance in most of the tested scenarios: the PCA statistics for monitoring multiscale textural features. For this reason and for encompassing less computational and programming effort, its adoption is particularly recommended.

Seam detection of inhomogeneously textured fabrics based on wavelet transform

A large amount of seam detection for inhomogeneously textured fabrics makes those performing it fatigued, which leads to misjudgments by human vision, especially for the seam detection of patterned inhomogeneously textured fabrics. The traditional wavelet texture analysis is no longer applicable to fabrics with inhomogeneous textures and irregular patterns. In this paper, a novel mean weighting factor is proposed to obtain an optimized discriminant measure to detect the fabric seams. Firstly, the wavelet coefficients are extracted in individual decomposition levels. Then a mean weighting factor is calculated on the use of the difference of the coefficient values between two consecutive decomposition levels, and a better discriminant measure for seam detection is obtained. Lastly, a thresholding process is used to segment the seam information from the background. The experimental results show that the proposed approach effectively carries out the seam detection in the inhomogeneously textured fabric images.

Evaluation of the Robustness of Surface Characterisation of Carbon Fibre Composites Using Wavelet Texture Analysis

The mechanical properties of advanced composites are essential for their structural performance, but the surface finish on exterior composite panels is of critical importance for customer satisfaction. Previous work by the authors established the feasibility of wavelet texture analysis (WTA) for the task of automatically classifying the surface finish of carbon fibre reinforced polymer (CFRP) samples based on computer image processing. This paper presents an evaluation of the robustness of the WTA method to common process errors that can occur in the imaging of material samples. WTA creates a rich representation of the texture in an image that includes features related to both scale and orientation. Principal components analysis was used to reduce the dimensionality of the texture feature vector to a single principal component that could be used as the basis for discrimination between grades of CRFP sample surface finish quality. The results obtained indicate that the WTA method is robust to: significant horizontal and/or vertical translations of the sample being imaged; significant rotation of the sample being imaged; and significant dilation of the sample being imaged. The results obtained suggest that as long as reasonable precautions are taken in sample imaging, then the WTA method will yield repeatable results.

Automatic image-based estimation of texture analysis as a monitoring tool for crystal growth

Online monitoring and feedback control are crucial elements in a commercial crystallization operation because they ensure that key production variables are closely regulated so as to achieve specified textural and physical properties of the end-product. Digital image texture analysis is a promising method in monitoring and control systems, and is becoming increasingly more attractive due to availability of high speed imaging devices and equally powerful computers. This paper investigates the use of texture analyses in the form of fractal dimension (FD) and energy signatures as characteristic parameters to track the crystal growth. This methodology deals with issues such as touching and overlapping problem in crystal images which limit available off-line and on-line imaging techniques. The algorithm uses a combination of thresholding and wavelet-texture analysis. The thresholding method is used to identify crystal clusters and remove empty backgrounds. Wavelet–fractal and energy signatures are performed afterwards to estimate texture on crystal clusters. A series of images obtained at different crystal growth stages during a NaCl–water–ethanol anti-solvent crystallization system is investigated and their texture characteristics as well as transform tendency during the crystallization process are evaluated.

Objective Surface Evaluation of Fiber Reinforced Polymer Composites

The mechanical properties of advanced composites are essential for their structural performance, but the surface finish on exterior composite panels is of critical importance for customer satisfaction. This paper describes the application of wavelet texture analysis (WTA) to the task of automatically classifying the surface finish properties of two fiber reinforced polymer (FRP) composite construction types (clear resin and gel-coat) into three quality grades. Samples were imaged and wavelet multi-scale decomposition was used to create a visual texture representation of the sample, capturing image features at different scales and orientations. Principal components analysis was used to reduce the dimensionality of the texture feature vector, permitting successful classification of the samples using only the first principal component. This work extends and further validates the feasibility of this approach as the basis for automated non-contact classification of composite surface finish using image analysis.

The visual quality recognition of nonwovens using a novel wavelet based contourlet transform

In this paper, a novel wavelet based contourlet transform for texture extraction is presented. The visual quality recognition of nonwovens based on image processing approach can be considered as a special case of the application of computer vision and pattern recognition on industrial inspection. For concreteness, the method proposed in this paper can be divided into two stages, i.e., the feature extraction is solved by wavelet based contourlet transform, which is followed by the grade recognition with support vector machine (SVM). For the texture analysis, we propose a novel wavelet based contourlet transform, which can be considered as a simplified but more sufficient for texture analysis for nonwoven image compared with version of the one introduced by Eslami in theory view. In experiment, nonwoven images of five different visual quality grades are decomposed using wavelet based contourlet transform with `PKVA' filter as the default filter of Laplacian Pyramid (LP) and Directional Filter Bank (DFB) at 3 levels firstly. Then, two energy-based features, norm-1 L 1 and norm-2 L 2, are calculated from the wavelet coefficients at the first level and contourlet coefficients of each high frequency subband. Finally, the SVM is designed to be a classifier to be trained and tested with the samples selected from the feature set. Experimental results indicate that when the nonwoven images are decomposed at 3 levels and 16 L 2s are extracted, with 500 samples to train the SVM, the average recognition accuracy of test set is 99.2 %, which is superior to the comparative method using wavelet texture analysis.

Intelligent characterization and evaluation of yarn surface appearance using saliency map analysis, wavelet transform and fuzzy ARTMAP neural network

The evaluation of yarn surface appearance is an important routine in assessing yarn quality in textile industry. Traditionally, this evaluation is subjectively carried out by manual inspection, which is much skill-oriented, judgmental and inconsistent. To resolve the drawbacks of the manual method, an integrated intelligent characterization and evaluation model is proposed in this paper for the evaluation of yarn surface appearance. In the proposed model, attention-driven fault detection, wavelet texture analysis and statistical measurement are developed and incorporated to fully extract the characteristic features of yarn surface appearance from images and a fuzzy ARTMAP neural network is employed to classify and grade yarn surface qualities based on the extracted features. Experimental results on a database of 576 yarn images show the proposed intelligent evaluation system achieves a satisfactory performance both for the individual yarn category and global yarn database. In addition, a comparative study among the fuzzy ARTMAP, Back-Propagation (BP) neural network, and Support Vector Machine (SVM) shows the superior capacity of the proposed fuzzy ARTMAP in classifying yarn surface qualities of the database.

A case study of the generalized frame for the uniformity recognition of nonwovens

Previous work has shown that the uniformity recognition of nonwoven can be considered as a special case of pattern recognition. In this paper, a generalized frame for uniformity recognition based on computer vision and pattern recognition is introduced briefly. To validate the proposed generalized frame, a case study id carried out in experiment. In the experiment section, the uniformity recognition of nonwovens will be solved by unifying wavelet texture analysis, generalized Gaussian density (GGD) model and learning vector quantization (LVQ) neural network. 625 nonwoven images of 5 different uniformity grades, 125 of each grade, are decomposed at four levels with five different wavelet bases of Symlets family. And wavelet coefficients in each subband are independently modeled by the GGD model, while the scale and shape parameters of GGD model are extracted using maximum likelihood (ML) estimator as features to train and test LVQ neural network. For comparison, two energy-based features are also extracted from wavelet coefficients directly and jointly used as textural features. Experimental results coming from 625 nonwoven samples indicate the GGD parameters are more expressive and powerful in characterizing textures than the energy-based ones, especially when the number of decomposition levels is 4.

Determination of steel quality based on discriminating textural feature selection

Image data can be acquired from a product surface in real time by image sensor systems in chemical plants. For quality determination based on these image datasets, effective texture classification methodology is essential to handle highly dimensional images and to extract quality-related information from these product surface images. Wavelet texture analysis is useful for reducing the dimension and extracting textural information from images. Although wavelet texture analysis extracts only textural characteristics from images, the extracted features still contain unnecessary information for classification. The texture analysis method can be improved by retaining only class-dependent features and removing common features. In previous works, best basis and local discriminant basis are the most popular techniques for selecting an important basis from the wavelet packet basis. However, feature selection based on wavelet texture analysis has been studied for texture classification. Because previous methods are designed for wavelet coefficients with features for analysis, their performance is poor with wavelet texture analysis. We propose a novel texture classification methodology for quality determination based on feature selection using wavelet texture analysis. The proposed methodology applies the sequential forward floating selection (SFFS) algorithm as a feature selection strategy to select discriminating wavelet signatures using wavelet texture analysis. The proposed methodology is validated through quality determination for industrial steel surfaces. The results show that the proposed method has fewer classification errors with fewer number of features than previous methods.

Surface evaluation of carbon fibre composites using wavelet texture analysis

Strong and lightweight fibre reinforced polymeric composites now dominate the aerospace, marine and low-volume automotive sectors. The surface finish on exterior composite panels is of critical importance for customer satisfaction. This paper describes the application of wavelet texture analysis (WTA) to the task of automatically classifying the surface finish of Carbon Fibre Reinforced Plastic (CFRP) samples into two quality grades. Automatic classification was successful for all but four samples out of 14,400 classification trial configurations, representing 403,200 sample classification attempts (28 attempts per configuration). This work establishes the principle of WTA as a basis for automatic surface finish classification of composite materials.

Wavelet texture analysis in process industries

Wavelet texture analysis has been applied to solve many problems in process industries as well as in other industries. In solving problems from process industries however, its potentials have never been explored to the full extent yet. This is not only because techniques used in wavelet texture analysis are still unfamiliar to researchers and practitioners in process industries, but also because characteristics of the scenes displayed by the images in process industries are difficult to analyze: products and processes in process industries mostly have stochastic outside appearance. The purpose of this article is to give an overview of state-of-the-art methods in wavelet texture analysis through an illustrative example from process industries.

The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform

In this paper, a novel wavelet based contourlet transform for texture extraction is presented. In the texture analysis section, we propose a novel wavelet based contourlet transform, which can be considered as a simplified but more sufficient for texture analysis for nonwoven image compared with version of the one introduced by Eslami in theory view. In experiment, nonwoven images of five different visual quality grades, 125 of each grade, are decomposed using wavelet based contourlet transform with ‘PKVA’ filter as the default filter of Laplacian Pyramid (LP) and Directional Filter Bank (DFB) at 3 levels and two energy-based features, norm-1 L1 and norm-2 L2, are calculated from the wavelet coefficients at the first level and contourlet coefficients of each high frequency subband at different levels and directions to train and test SVM. When the nonwoven images are decomposed at 3 levels and 16 L1s are extracted, with 500 samples to train the SVM, the average recognition accuracy of test set is 98.4%, which is superior to the comparative method using wavelet texture analysis.

Quality Determination of Steel Surfaces Based on Best Feature Selection

We propose a quality classification methodology based on optimal textural feature selection. This method employs the wavelet packet transform to decompose the original image into multiple-resolution images. Wavelet texture analysis is applied to extract quality-related features from subimages. Optimal textural feature selection is employed to select the discriminative texture in accordance with class information. The previously used best basis approach is incapable of optimal texture classification when combined with wavelet texture analysis. The proposed texture classification method unifies the best basis approach with wavelet texture analysis. Further, we improve the previous best basis to obtain an optimal basis using a simple rule to select discriminative signatures. The proposed methodology is applied and validated for classifying the surface quality of rolled steel sheets. Experimental results show that features extracted using the proposed method are more discriminative than those obtained using the best basis in terms of classification performance and Fisher's index.