Learning Discriminative Features for Ground-Based Cloud Classification via Mutual Information Maximization

Abstract

SUMMARYTexture feature descriptors such as local binary patterns (LBP) have proven effective for ground-based cloud classification. Traditionally, these texture feature descriptors are predefined in a handcrafted way. In this paper, we propose a novel method which automatically learns discriminative features from labeled samples for ground-based cloud classification. Our key idea is to learn these features through mutual information maximization which learns a transformation matrix for local difference vectors of LBP. The experimental results show that our learned features greatly improves the performance of ground-based cloud classification when compared to the other state-of-the-art methods. key words: discriminative patterns, mutual information maximization, ground-based cloud classification

Multimodal Ground-Based Cloud Classification Using Joint Fusion Convolutional Neural Network

“…Singh and Glennen [19] evaluated five different feature extraction methods for cloud classification, namely autocorrelation, co-occurrence matrices, edge frequency, Law's features and primitive length. Liu et al [20][21][22][23] presented several approaches to learn discriminative texture features, such as an ensemble approach of multiple random projections, the salient local binary pattern, the soft-signed sparse coding and the mutual information learning features. Zhuo and Cao [24] proposed a three-step algorithm, including applying the preprocessing color census transform, capturing global rough structure information and obtaining the cloud type.…”