Despite recent advances in deep texture recognition, existing methods still lack representational diversity and struggle to capture and preserve discriminative cues across stages of representation hierarchies. Moreover, many rely on loss formulations that prioritize recognition accuracy while overlooking spatial coherence and statistical consistency in the feature space. To address these issues, we propose three key innovations: (1) Stochastic Local Texture Masking (SLTM), a regularization strategy that randomly occludes small texture patches to promote the learning of broader spatial and contextual dependencies; (2) the Chebyshev Attention Depth Permutation Texture Network (CAPTN), a novel architecture that learns expressive and persistent Latent Texture Attribute (LTA) representations. CAPTN integrates a Texture Frequency Attention (TFA) module that generates Latent Texture Attributes (LTAs) and enables frequency-aware interpretability, a Dual Depth Permutation (D2P) module to expose complementary channel adjacency patterns, and Learnable Chebyshev Polynomials (LCPs) to model high-order orderless LTA transformations via recursive Chebyshev basis expansion; and (3) a Latent Texture Attribute Loss that jointly optimizes classification accuracy, statistical alignment, and spatial fidelity. CAPTN supports end-to-end training without relying on fine-tuned CNN backbones and achieves state-of-the-art performance on several texture and material recognition benchmarks. (Code: https://github.com/RavishankarEvani/CAPTN)

Recent advances in Large Language Models (LLMs) have enabled the semantic description of textures in natural language, aiming to capture them in richer detail. However, most methods are confined to either depending on supervised training with pairs of images and manually annotated visual attributes that most texture datasets lack or using Vision-Language Models (VLMs) such as CLIP. In this paper, we develop an encoder-agnostic Weakly supervised Texture Description Generator (WTDG) that employs a novel Scaled Ranked Kullback-Leibler divergence (SR-KL) loss between image and text modalities. Within the SR-KL loss formulation, we leverage category information, which is always available as ground-truths for all benchmark texture recognition datasets. We further extend our proposed WTDG to assist in texture recognition by using its generated texture descriptions. Thus, we develop a multimodal framework, called$T e x^2$, which is adept at simultaneous generation of texture description and recognition. Our approach exhibits promising performance in describing and recognizing textures on benchmark datasets.

Inspection of metal surface textures using computer vision and machine learning techniques plays an important role in Automated Visual Inspection (AVI) systems. Texture recognition on metal surface is challenging because the characteristics of each texture type are dependent on the properties of the metal surface when captured under different lighting conditions. Since these textures have no obvious repetitive patterns like general textures, this results in high intra-class diversities. Prior knowledge has shown that surface properties such as surface curvature and depth are discriminant to different texture types on metal surface. Since scale, shapes and location of textures within the same type are not fixed, scale property and spatial ordering information are less important for differentiating between texture types. There-fore, surface property, scale invariance and order-less property should be considered when exploring a suitable image feature for metal surface texture recognition. This paper proposes Order-less Scale Invariant Gradient Local Auto-Correlation (OS-GLAC) which meets all three requirements for robust texture recognition. The experiment results show that OS-GLAC is robust to separate different metal surface texture types. In addition, we observed that OS-GLAC is not only useful for texture recognition on metal surface but also for general texture recognition when combined with pre-trained deep learning features as these two features capture complimentary information. The experiment results show that such a combination of OS-GLAC achieves competitive results on three well-established general texture datasets i.e., KTH-TIP-2a, KTH-TIPS-2b and FMD.

With a drastic growth in the development of Automated Visual Inspection (AVI) systems in the industries, the capabilities of such applications to aid human inspectors for anomaly localization and identification have also increased. However, some issues with anomaly detection and classification in AVI systems are that such anomalies are rare in occurrence and exhibit behaviours that are unique to the application. Hence, these anomaly datasets are small and imbalanced, and a robust framework is required for such datasets. This paper proposes a Salient Textural Anomaly Proposal (STAP) framework to generate and classify salient textural proposals of regions of anomalies on metal surfaces. These anomalies have both salient and texture characteristics that are dependent on the properties of the metal surface. Furthermore, when observed across different lighting conditions, the anomalies in this AVI anomaly dataset have a small inter-class variance and large intraclass variance. The proposed STAP framework uses a Fourier transformation based technique to generate proposals of salient and textural anomaly regions. Transfer learning of Convolutional Neural Network (CNN) learned from a large dataset is used to train a linear Support Vector Machine (SVM) to classify the generated proposals. The proposed STAP framework performs the best when compared to state-of-the-art object recognition techniques on an AVI anomaly industrial dataset that has salient and texture anomalies on metal surfaces.

A biological neural network is constituted by numerous subnetworks and modules with different functionalities. For an artificial neural network, the relationship between a network and its subnetworks is also important and useful for both theoretical and algorithmic research, i.e. it can be exploited to develop incremental network training algorithm or parallel network training algorithm. In this paper we explore the relationship between an Extreme Learning Machine (ELM) trained neural network and its subnetworks. To the best of our knowledge, we are the first to prove a theorem that shows an ELM trained neural network can be scattered into subnetworks and its optimal solution can be constructed recursively by the optimal solutions of these subnetworks. Based on the theorem we also present two algorithms to train a large ELM neural network efficiently: one is a parallel network training algorithm and the other is an incremental network training algorithm. The experimental results demonstrate the usefulness of the theorem and the validity of the developed algorithms.