Approach For Texture Classification Research Articles

A Deep Learning Based Soil Type Classification and Recommendation of Crops to the Soil Type

Accurate classification of soil surface texture plays a pivotal role in agriculture, environmental management, and land-use planning. However, the classification of soil textures from RGB images obtained under uncontrolled field conditions remains a challenging task due to the inherent complexities of natural environments. In this study, we propose a novel approach for Soil Surface Texture Classification using Convolutional Neural Networks to address these challenges.

Texture Recognition Based on Perception Data from a Bionic Tactile Sensor.

Texture recognition is important for robots to discern the characteristics of the object surface and adjust grasping and manipulation strategies accordingly. It is still challenging to develop texture classification approaches that are accurate and do not require high computational costs. In this work, we adopt a bionic tactile sensor to collect vibration data while sliding against materials of interest. Under a fixed contact pressure and speed, a total of 1000 sets of vibration data from ten different materials were collected. With the tactile perception data, four types of texture recognition algorithms are proposed. Three machine learning algorithms, including support vector machine, random forest, and K-nearest neighbor, are established for texture recognition. The test accuracy of those three methods are 95%, 94%, 94%, respectively. In the detection process of machine learning algorithms, the asamoto and polyester are easy to be confused with each other. A convolutional neural network is established to further increase the test accuracy to 98.5%. The three machine learning models and convolutional neural network demonstrate high accuracy and excellent robustness.

An Improved Convolutional Neural Network with LSTM Approach for Texture Classification

An Improved Convolutional Neural Network with LSTM Approach for Texture Classification

Computing fractal descriptors of texture images using sliding boxes: An application to the identification of Brazilian plant species

This work proposes a new model based on fractal descriptors for the classification of grayscale texture images. The method consists of scanning the image with a sliding box and collecting statistical information about the pixel distribution. Varying the box size, an estimation of the fractality of the image can be obtained at different scales, providing a more complete description of how such parameter changes in each image. The same strategy is also applied to a especial encoding of the image based on local binary patterns. Descriptors both from the original image and from the local encoding are combined to provide even more precise and robust results in image classification. A statistical model based on the theory of sliding window detection probabilities and Markov transition processes is formulated to explain the effectiveness of the method. The descriptors were tested on the identification of Brazilian plant species using scanned images of the leaf surface. The classification accuracy was also verified on three benchmark databases (KTH-TIPS2-b, UIUC and UMD). The results obtained demonstrate the power of the proposed approach in texture classification and, in particular, in the practical problem of plant species identification.

A Texture Classification Approach Based on the Integrated Optimization for Parameters and Features of Gabor Filter via Hybrid Ant Lion Optimizer

Texture classification is an important topic for many applications in machine vision and image analysis, and Gabor filter is considered one of the most efficient tools for analyzing texture features at multiple orientations and scales. However, the parameter settings of each filter are crucial for obtaining accurate results, and they may not be adaptable to different kinds of texture features. Moreover, there is redundant information included in the process of texture feature extraction that contributes little to the classification. In this paper, a new texture classification technique is detailed. The approach is based on the integrated optimization of the parameters and features of Gabor filter, and obtaining satisfactory parameters and the best feature subset is viewed as a combinatorial optimization problem that can be solved by maximizing the objective function using hybrid ant lion optimizer (HALO). Experimental results, particularly fitness values, demonstrate that HALO is more effective than the other algorithms discussed in this paper, and the optimal parameters and features of Gabor filter are balanced between efficiency and accuracy. The method is feasible, reasonable, and can be utilized for practical applications of texture classification.

Texture image Classification based on improved local Quinary patterns

Texture image classification is an active research topic in computer vision that play an important role in many applications such as visual inspection systems, object tracking, medical image analysis, image segmentation, etc. So far, there are many descriptors for texture image analysis such as local binary patterns (LBP). LBP is a nonparametric operator, which describes the local spatial structure and the local contrast of an image. Local quinary patterns (LQP) is one of the improved versions of LBP in terms of classification accuracy. Statistic input parameters and don’t providing significant binary patterns are some disadvantages of LQP. In this paper a new version of LBP is proposed, which is known as improved local quinary patterns (ILQP). In this paper, a new definition is proposed to divide local quinary codes to four binary patterns. Each extracted binary patterns represent a subset of local features. Also, a new algorithm is proposed here to provide dynamic thresholds in dividing process of LQP. The proposed approach is evaluated using Outex, and Brodatz data sets. Our approach has been compared with some state-of-the-art methods. It is experimentally demonstrated that the proposed approach achieves the highest accuracy in comparison with most of the state-of-the-art texture classification approaches. Low computational complexity, rotation invariant, low impulse-noise sensitivity and high usability are advantages of the proposed texture analysis descriptor.

Galois Field-based Approach for Rotation and Scale Invariant Texture Classification

Galois Field-based Approach for Rotation and Scale Invariant Texture Classification

Gray level run length matrix based on various illumination normalization techniques for texture classification

Texture classification under varying illumination conditions is one of the most important challenges. This paper presents a new texture classification approach by taking the combinations of robust illumination normalization techniques applied on gray level run length matrix (GLRLM) for texture features extraction. The purpose of selecting the GRLM, as texture descriptor is that, it extracts information of an image from its gray level runs. A set of consecutive, collinear picture points having the same gray level values is considered as a gray level run. The textured materials usually go through a deep change in their images with variations in illumination and camera pose. For instance, keeping all the parameters fixed but just changing the scale and rotation can result in a completely new texture. Hence, change in gray level values also occurred. Dealing with these variations successfully by utilizing GRLM descriptor for texture classification is the main purpose of this paper. In the suggested approach, 2D wavelet, Tan and Triggs (TT) normalization methods are employed to compensate illumination variations. Experimental results on the Brodatz, VisTex, STex and ALOT databases show that the suggested approach improves the performance significantly as compared to the classical GLRLM descriptor.

TCvBsISM: Texture Classification via B-Splines-Based Image Statistical Modeling

This paper presents an image statistical modeling-based texture classification (TC) approach via the Bayesian-driven B-splines probability density estimation of the image textural surface appearance (ITSA), termed TCvBsISM. It approximates the probability density functions (pdfs) of the marginal distribution and joint distribution, involving the global organization and the locally structural layout of local homogeneous patches in the texture surface, respectively, of both the image raw pixel space and the filter response space, by the linear combination of B-spline basis functions (BsBFs) for ITSA feature characterization. The corresponding linear weighting coefficients (LWCs) are determined by an entropy-based optimization criterion with a prior smooth constraint over the LWCs. By leveraging the B-spline-based pdf modeling, distinctive ITSA structural features of texture images are characterized by the LWCs of the pre-defined BsBFs, which are then embedded in an integrated statistical feature dictionary learning, texture pattern representation, and discrimination model to perform TC. Extensive confirmative and comparative experiments on three different texture databases and one natural environmental scene database demonstrate that the proposed TCvBsISM is very promising, especially when the images of different texture patterns appear to be quite similar with the limited training samples. The effects of various parameters on TCvBsISM, such as the choice of the filter bank, the size of the image statistical feature dictionary, as well as the number of BsBFs, are also discussed.

Enhancing the laws filter descriptor on DTCWT coefficients by thresholding approach for texture classification

Enhancing the laws filter descriptor on DTCWT coefficients by thresholding approach for texture classification

Enhancing the laws filter descriptor on DTCWT coefficients by thresholding approach for texture classification

In this paper, we propose a new approach of combining dual-tree complex wavelet transform with traditional Laws' filter descriptor for texture classification using thresholding method. The dual-tree complex wavelet transform (DTCWT) is a recent technique to discrete wavelet transform, with important additional properties. It has been observed that the thresholding is a method to keep significant information of the image while discarding the unimportant part. On this basis for further enhancement of texture classification, we have acquired the texture images by applying thresholding technique to the entire texture database. These thresholded images are then applied to the fusion model of DTCWT with Laws' filter descriptor. We verify the effectiveness of the proposed method by utilising two texture databases such as Brodatz and UIUC. The proposed methods are compared with the classical Laws' filter descriptor. Results demonstrate that the proposed method greatly enhanced the classification accuracies by using k-NN as classifier.

A new approach for rotation-invariant and noise-resistant texture analysis and classification

The analysis and classification of images, such as texture images, is one of the substantial and important fields in image processing. Due to destructive effects of image rotation and noise, the stability and efficiency of texture analysis and classification methods are an important research area. In this paper, a new method for texture analysis and classification has been proposed which is based on a particular combination of wavelet, ridgelet and Fourier transforms as well as support vector machine. The proposed method has been evaluated for 13 texture datasets produced by three original datasets containing 25 and 111 original textures from Brodatz database and 24 original textures from OUTEX database. These datasets comprise 415584 and 93600 rotated noise-free and noisy texture images for Brodatz database and also 49920 noisy and 4320 noise-free texture images for OUTEX database, respectively. Simulation results demonstrate the capability, efficiency and also stability of the proposed method especially for real-time rotation-invariant and noise-resistant texture analysis and classification.

Multi-resolution Laws’ Masks based texture classification

Abstract Wavelet transforms are widely used for texture feature extraction. For dyadic transform, frequency splitting is coarse and the orientation selection is even poorer. Laws’ mask is a traditional technique for extraction of texture feature whose main approach is towards filtering of images with five types of masks, namely level, edge, spot, ripple, and wave. With each combination of these masks, it gives discriminative information. A new approach for texture classification based on the combination of dyadic wavelet transform with different wavelet basis functions and Laws’ masks named as Multi-resolution Laws’ Masks (MRLM) is proposed in this paper to further improve the performance of Laws’ mask descriptor. A k-Nearest Neighbor (k-NN) classifier is employed to classify each texture into appropriate class. Two challenging databases Brodatz and VisTex are used for the evaluation of the proposed method. Extensive experiments show that the Multi-resolution Laws’ Masks can achieve better classification accuracy than existing dyadic wavelet transform and Laws’ masks methods.

LBP-and-ScatNet-based combined features for efficient texture classification

In this paper, we propose a micro-macro feature combination approach for texture classification. The two disparate yet complementary categories of features are combined. By this way, Local Binary Pattern (LBP) plays the role of micro-structure feature extractor while the scattering transform captures macro-structure information. In fact, for extracting the macro-type features, coefficients are aggregated from three different layers of the scattering network. It is a handcrafted convolution network which is implemented by computing consecutively wavelet transforms and modulus non-linear operators. By contrast, in order to extract micro-structure features which are rotation-invariant, relatively robust to noise and illumination change, the completed LBP is utilized alongside the biologically-inspired filtering (BF) preprocessing technique. Overall, since the proposed framework can exploit the advantages of both feature types, its texture representation is not only invariant to rotation, scaling, illumination change but also highly discriminative. Intensive experiments conducted on many texture benchmarks such as CUReT, UIUC, KTH-TIPS-2b, and OUTEX show that our framework has a competitive classification accuracy.

A FPGA-based Hardware Architecture for Real-time Texture Classification Using Local Binary Patterns

Local Binary Pattern (LBP) is a simple yet efficient texture operator which has become a popular approach in texture classification. In this paper, we propose a novel hardware architecture for texture classification algorithms based on local binary patterns that can be executed efficiently on a field-programmable gate arrays (FPGAs). A new memory structure and window operations have been used in this hardware design to accelerate images processing. The new architecture is implemented on Xilinx Virtex-6 FPGA. The experiments show that this new method exhibits more efficient execution compared with standard implementations based on central processing units and graphics processing units.

Texture classification based on curvelet transform and extreme learning machine with reduced feature set

In this work, a novel approach for texture classification is proposed. We present a highly discriminative and simple descriptor to achieve feature learning and classification simultaneously for texture classification. The proposed method introduces the application of digital curvelet transform and explores feature reduction properties of locality sensitive discriminant analysis (LSDA) in conjunction with extreme learning machine (ELM) classifier. The image is mapped to the curvelet space. However, the curse of dimensionality problem arises when using the curvelet coefficients directly and therefore a reduction method is required. LSDA is used to reduce the data dimensionality to generate relevant features. These reduced features are used as the input to ELM classifier to analytically learn an optimal model. In contrast to traditional methods, the proposed method learns the features by the network itself and can be applied to more general applications. Extensive experiments conducted in two different domains using two benchmark databases, illustrate the effectiveness of the proposed method. In addition, empirical comparisons of the proposed method against curvelet transform in conjunction with traditional dimensionality reduction tools show that the suggested method does not only lead to a more reduced feature set, but it also outperforms all the compared methods in terms of accuracy.

Improved Weber’s law based local binary pattern for dynamic texture recognition

Dynamic texture is the moving sequence of images that shows some form of temporal regularity. Various static texture descriptors have been extended to spatiotemporal domain for dynamic texture classification. Local Binary Pattern (LBP) is a simple descriptor computationally but sensitive to noise and sometimes fails to capture different patterns. In view of this, a novel approach for dynamic texture classification is introduced that maintains the advantageous characteristics of uniform LBP. Inspired by the Weber's law, a simple yet very powerful, robust texture descriptor, i.e., Weber's law based LBP with center pixel (WLBPC) is proposed from the local patches based on the conventional Local Binary Pattern approach. A noise resistant variant of Weber's law based LBP with center pixel (NR-WLBPC) is also proposed. To do this, WLBPC is extended to a 3-valued code based on a new threshold. Proposed noise resistant variant of WLBPC descriptor makes use of the indecisive bit and the uniform pattern to compute the feature vector. Center pixel information is fused with both the dynamic texture descriptors to improve the discriminative power. Extensive experimental evaluations on representative dynamic texture databases (DynTex++ and UCLA) show that the proposed descriptors show better performance in comparison to recent state-of-the-art LBP variants and other methods under both normal and noisy conditions. Noise invariant of the proposed descriptor also performs better in the presence of noise due to its robustness and discriminating capabilities.

Robust Texture Classification by Aggregating Pixel-Based LBP Statistics

This letter addresses the texture classification problem through a pixel-based local binary pattern (LBP) statistics aggregation mechanism. Real-world texture images often present challenges for classification algorithms in terms of intra-class variability due, among others, to variable illumination. The LBP operator, a state-of-the-art texture descriptor, possesses key properties for tackling real-world texture images: discriminative power and invariance against monotonic gray level changes. We propose a novel texture classification approach that increases the robustness of LBP-based methods with respect to any type of intra-class variations. The method locally characterizes each pixel with an LBP code histogram and globally computes the label of a textured image by aggregating pixel labels through a voting process. Our approach can be in principle applied to any LBP version, as it focuses on how statistics are computed from LBP codes. We show that the proposed pixel-based approach improves upon traditional LBP block-based approaches in terms of classification accuracy by up to 5.1 p.p. on the public Outex database for the classic LBP with various neighborhoods as well as for various LBP extensions.

Nonnegative Multiresolution Representation-Based Texture Image Classification

Effective representation of image texture is important for an image-classification task. Statistical modelling in wavelet domains has been widely used to image texture representation. However, due to the intraclass complexity and interclass diversity of textures, it is hard to use a predefined probability distribution function to fit adaptively all wavelet subband coefficients of different textures. In this article, we propose a novel modelling approach, Heterogeneous and Incrementally Generated Histogram (HIGH), to indirectly model the wavelet coefficients by use of four local features in wavelet subbands. By concatenating all the HIGHs in all wavelet subbands of a texture, we can construct a nonnegative multiresolution vector (NMV) to represent a texture image. Considering the NMV’s high dimensionality and nonnegativity, we further propose a Hessian regularized discriminative nonnegative matrix factorization to compute a low-dimensional basis of the linear subspace of NMVs. Finally, we present a texture classification approach by projecting NMVs on the low-dimensional basis. Experimental results show that our proposed texture classification method outperforms seven representative approaches.

Characterization of Architectural Distortion in Mammograms Based on Texture Analysis Using Support Vector Machine Classifier with Clinical Evaluation.

Architecture distortion (AD) is an important and early sign of breast cancer, but due to its subtlety, it is often missed on the screening mammograms. The objective of this study is to create a quantitative approach for texture classification of AD based on various texture models, using support vector machine (SVM) classifier. The texture analysis has been done on the region of interest (ROI) selected from the original mammogram. A comprehensive analysis has been done on samples from three databases; out of which, two data sets are from the public domain, and the third data set is for clinical evaluation. The public domain databases are IRMA version of digital database for screening mammogram (DDSM) and Mammographic Image Analysis Society (MIAS). For clinical evaluation, the actual patient's database has been obtained from ACE Healthways, Diagnostic Centre Ludhiana, India. The significant finding of proposed study lies in appropriate selection of the size of ROIs. The experiments have been done on fixed size of ROIs as well as on the ground truth (variable size) ROIs. Best results pertain to an accuracy of 92.94% obtained in case of DDSM database for fixed-size ROIs. In case of MIAS database, an accuracy of 95.34% is achieved in AD versus non-AD (normal) cases for ground truth ROIs. Clinically, an accuracy of 88% was achieved for ACE dataset. The results obtained in the present study are encouraging, as optimal result has been achieved for the proposed study in comparison with other related work in the same area.