A Novel Machine-Learning Framework-based on LBP and GLCM Approaches for CBIR System

This paper presents a Multiple-features extraction and reduction-based approaches for Content-Based Image Retrieval (CBIR). Discrete Wavelet Transforms (DWT) on colored channels is used to decompose the image at multiple stages. The Gray Level Co-occurrence Matrix (GLCM) concept is used to extract statistical characteristics for texture image classification. The definition of shared knowledge is used to classify the most common features for all COREL dataset groups. These are also fed into a feature selector based on the particle swarm optimization which reduces the number of features that can be used during the classification stage. Three classifiers, called the Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Decision Tree (DT), are trained and tested, in which SVM give high classification accuracy and precise rates. In several of the COREL dataset types, experimental findings have demonstrated above 94 percent precision and 0.80 to 0.90 precision values.

Remote Sensing and Texture Image Classification Network Based on Deep Learning Integrated with Binary Coding and Sinkhorn Distance

In the past two decades, traditional hand-crafted feature based methods and deep feature based methods have successively played the most important role in image classification. In some cases, hand-crafted features still provide better performance than deep features. This paper proposes an innovative network based on deep learning integrated with binary coding and Sinkhorn distance (DBSNet) for remote sensing and texture image classification. The statistical texture features of the image extracted by uniform local binary pattern (ULBP) are introduced as a supplement for deep features extracted by ResNet-50 to enhance the discriminability of features. After the feature fusion, both diversity and redundancy of the features have increased, thus we propose the Sinkhorn loss where an entropy regularization term plays a key role in removing redundant information and training the model quickly and efficiently. Image classification experiments are performed on two texture datasets and five remote sensing datasets. The results show that the statistical texture features of the image extracted by ULBP complement the deep features, and the new Sinkhorn loss performs better than the commonly used softmax loss. The performance of the proposed algorithm DBSNet ranks in the top three on the remote sensing datasets compared with other state-of-the-art algorithms.