Grey‐level co‐occurrence matrix (GLCM) is a widely used texture feature descriptor that is extracted from grey‐level images. A considerable amount of work in the literature has been done trying to combine colour with GLCM features. The aim of this study is to examine the effect of integrating colour with GLCM. To this end, 14 descriptors that have been proposed in literature based on different colour combining approaches, four Convolutional Neural Networks‐based, two aggregation‐based, and five other handcrafted descriptors have been engaged in this comparison. Five widely known data sets have been used to experimentally evaluate each descriptor. The evaluation has been conducted for image classification and image retrieval. Results indicated that there is no co‐occurrence‐matrix‐based descriptor that overcomes all the others in all data sets. Nevertheless, some descriptors have shown a remarkably higher performance than the others.

Date fruit is among the major crops in the middle-east region, where millions of tons are harvested every year. Date is a healthy fruit, which involves sugars, minerals and vitamins. In addition, it helps preventing human body from several diseases such as cancer and heart diseases. Date sorting is a fundamental step in the date industry. However, manually conducting such an operation, by human labors, is expensive and time-consuming. In this paper, we propose a method for classifying the type of date fruit by incorporating supervised and unsupervised deep networks. Specifically, we use discriminant correlation analysis (DCA) algorithm to fuse features learned from convolution neural networks (VGG-F) and an unsupervised network called PCANet. DCA jointly performs feature fusion and dimensionality reduction with a low computational complexity. To carry out experiments, we introduce a new benchmark dataset of date fruit images from 20 date varieties. Our benchmark is, to the best of our knowledge, the largest one in terms of number of varieties. Note that the dataset is publicly available at https://unsat.000webhostapp.com/dataset . Experimental results demonstrate the utility of DCA as well as the complementarity of the fused features. It has also been shown the effectiveness of the proposed method compared to several relevant methods.

Accurate building detection is a critical task in urban development and digital city mapping. However, current building detection models for high-resolution remote sensing images are still facing challenges due to complex object characteristics and similarities in appearance. To address this issue, this paper proposes a novel algorithm for building detection based on in-depth feature extraction and classification of adaptive superpixel shredding. The proposed approach consists of four main steps: image segmentation into homogeneous superpixels using a modified Simple Linear Iterative Clustering (SLIC), in-depth feature extraction using an variational auto-encoder (VAE) scale on the superpixels for training and testing data collection, identification of four classes (buildings, roads, trees, and shadows) using extracted feature data as input to an Convolutional Neural Network (CNN), and extraction of building shapes through regional growth and morphological operations. The proposed approach offers more stability in identifying buildings with unclear boundaries, eliminating the requirement for extensive prior segmentation. It has been tested on two datasets of high-resolution aerial images from the New Zealand region, demonstrating superior accuracy compared to previous works with an average F1 score of 98.83%. The proposed approach shows potential for fast and accurate urban monitoring and city planning, particularly in urban areas.

The accurate and efficient classification of steel surface defects is critical for ensuring product quality and minimizing production costs. This paper proposes a novel method based on wavelet transform and texture descriptors for the robust and precise classification of steel surface defects. By leveraging the multiscale analysis capabilities of wavelet transforms, our method extracts both broad and fine-grained textural features. It involves decomposing images using multi-level wavelet transforms, extracting a series set of statistical and textural features from the resulting coefficients, and employing Recursive Feature Elimination (RFE) to select the most discriminative features. A comprehensive series of experiments was conducted on two datasets, NEU-CLS and X-SDD, to evaluate the proposed method. The results highlight the effectiveness of the method in accurately classifying steel surface defects, outperforming the state-of-the-art techniques. Our method achieved an accuracy of 99.67% for the NEU-CLS dataset and 98.24% for the X-SDD dataset. Furthermore, we demonstrate the robustness of our method in scenarios with limited data, maintaining high accuracy, making it well-suited for practical industrial applications where obtaining large datasets can be challenging.