Non-stationary Texture Research Articles

A novel approach to texture recognition combining deep learning orthogonal convolution with regional input features.

Textures provide a powerful segmentation and object detection cue. Recent research has shown that deep convolutional nets like Visual Geometry Group (VGG) and ResNet perform well in non-stationary texture datasets. Non-stationary textures have local structures that change from one region of the image to the other. This is consistent with the view that deep convolutional networks are good at detecting local microstructures disguised as textures. However, stationary textures are textures that have statistical properties that are constant or slow varying over the entire region are not well detected by deep convolutional networks. This research demonstrates that simple seven-layer convolutional networks can obtain better results than deep networks using a novel convolutional technique called orthogonal convolution with pre-calculated regional features using grey level co-occurrence matrix. We obtained an average of 8.5% improvement in accuracy in texture recognition on the Outex dataset over GoogleNet, ResNet, VGG and AlexNet.

Wavelet-based Normalized Flow for Anomaly Detection in Photovoltaic Electroluminescent with non-stationary textures

Wavelet-based Normalized Flow for Anomaly Detection in Photovoltaic Electroluminescent with non-stationary textures

Deep Scattering Network With Fractional Wavelet Transform

Deep convolutional neural networks (DCNNs) have recently emerged as a powerful tool to deliver breakthrough performances in various image analysis and processing applications. However, DCNNs lack a strong theoretical foundation and require massive amounts of training data. More recently, the deep scattering network (DSN), a variant of DCNNs, has been proposed to address these issues. DSNs inherit the hierarchical structure of DCNNs, but replace data-driven linear filters with predefined fixed multi-scale wavelet filters, which facilitate an in-depth understanding of DCNNs and also offer the state-of-the-art performance in image classification. Unfortunately, DSNs suffer from a major drawback: they are suitable for stationary image textures but not non-stationary image textures, since 2D wavelets are intrinsically linear translation-invariant filters in the Fourier transform domain. The objective of this paper is to overcome this drawback using the fractional wavelet transform (FRWT) which can be viewed as a bank of linear translation-variant multi-scale filters and thus may be well suited for non-stationary texture analysis. We first propose the fractional wavelet scattering transform (FRWST) based upon the FRWT. Then, we present a generalized structure for the DSN by cascading fractional wavelet convolutions and modulus operators. Basic properties of this generalized DSN are derived, followed by a fast implementation of the generalized DSN as well as their practical applications. The theoretical derivations are validated via computer simulations.

Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions

Convolutional Neural Networks (CNN) have brought spectacular improvements in several fields of machine vision including object, scene and face recognition. Nonetheless, the impact of this new paradigm on the classification of fine-grained images—such as colour textures—is still controversial. In this work, we evaluate the effectiveness of traditional, hand-crafted descriptors against off-the-shelf CNN-based features for the classification of different types of colour textures under a range of imaging conditions. The study covers 68 image descriptors (35 hand-crafted and 33 CNN-based) and 46 compilations of 23 colour texture datasets divided into 10 experimental conditions. On average, the results indicate a marked superiority of deep networks, particularly with non-stationary textures and in the presence of multiple changes in the acquisition conditions. By contrast, hand-crafted descriptors were better at discriminating stationary textures under steady imaging conditions and proved more robust than CNN-based features to image rotation.

Non-stationary texture synthesis by adversarial expansion

The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.

Range Distributed Floating Target Detection in Sea Clutter via Feature-Based Detector

We investigate the detection of range distributed floating target in sea clutter that consists of stationary speckle modulated by nonstationary texture. With the elimination of the nonstationary part of sea clutter, here a feature-based detector using the consistency factor of speckle is proposed. Experimental results of IPIX radar data sets show that the proposed feature-based detector achieves the better detection performance in comparison with other methods. The nonstationary property of sea clutter has a negative effect on the probability of detection, thus warrant consideration in designing the detector.

An Intensity-Texture model based level set method for image segmentation

In this paper, a novel level set segmentation model integrating the intensity and texture terms is proposed to segment complicated two-phase nature images. Firstly, an intensity term based on the global division algorithm is proposed, which can better capture intensity information of image than the Chan–Vese model (CV). Particularly, the CV model is a special case of the proposed intensity term under a certain condition. Secondly, a texture term based on the adaptive scale local variation degree (ASLVD) algorithm is proposed. The ASLVD algorithm adaptively incorporates the amplitude and frequency components of local intensity variation, thus, it can extract the non-stationary texture feature accurately. Finally, the intensity term and the texture term are jointly incorporated into level set and used to construct effective image segmentation model named as the Intensity-Texture model. Since the intensity term and the texture term are complementary for image segmentation, the Intensity-Texture model has strong ability to accurately segment those complicated two-phase nature images. Experimental results demonstrate the effectiveness of the proposed Intensity-Texture model.

Error rate analysis of partial response channels in the presence of texture noise

A model for error rate analysis including the effect of texture noise is described. The impact of long-range correlated and nonstationary texture noise on system performance is examined for various types of partial response (PR4 and EPR4) channels and replay heads [magnetoresistive and giant magnetoresistive (GMR)]. A higher-order partial response polynomial (EPR4) is found to have better tolerance to disk substrate texture. It is also found that the recording medium noise dominates the error rate of systems using GMR heads for a typical recording system. The evaluations of the signal, noise, and the consequential probability of error for a PR4 system are illustrated in detail.

Multicomponent Multidimensional Signals

In this brief paper, we extend the notion of multicomponent signal into multiple dimensions. A definition for multidimensional instantaneous bandwidth is presented and used to develop criteria for determining the multicomponent nature of a signal. We demonstrate application of the criteria by testing the validity of a multicomponent interpretation for a complicated nonstationary texture image.