AdaNFF: A new method for adaptive nonnegative multi-feature fusion to scene classification. (March 2022)

• Record Type: Journal Article
• Authors: Zou, Zhiyuan; Liu, Weibin; Xing, Weiwei
• Is Part Of: Pattern recognition. Volume 123(2022)
• Publication Date: 2022-03
• Subjects: Scene classification -- Adaptive feature fusion -- Nonnegative matrix factorization -- Feature fusion boosting; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108402
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Adaptive nonnegative feature fusion framework is proposed for multi-feature fusion. Feature fusion boosting algorithm is proposed to improve classificaion performance. Dimension equilibirum strategy is proposed and utilized to optimize nonnegative feature factorization. The proposed methods achieve remarkable classification performance on scene image benchmarks. Graphical abstract: Abstract: Scene classification is an important basis for many modern intelligent applications, however the performance of pattern recognition or deep learning-based methods are still not sufficient since complicated structure and context of scene images. In this paper, we propose a novel fusion framework of adaptive nonnegative feature fusion (AdaNFF) for scene classification. The AdaNFF integrates nonnegative matrix factorization, adaptive feature fusion and feature fusion boosting into an end-to-end process. Firstly, feature fusion is known as a general strategy to strengthen weak features, and we observe that pixel values and most hand-craft features of the scene image are naturally nonnegative. Therefore we are motivated to build a fusion method based on nonnegative matrix factorization, which can preserve features nonnegative properties and improve their representation performance. Secondly, with the results of fused single or multiple features fusion, we develop an adaptive feature fusion and boosting algorithm to improve the efficiency of image features. Finally, a normalized l 2 -norm classifier and a deep-learning like multilayer perceptron (MLP) classifier are trained to predict label of scene image. Under this framework, there are two versions of the proposed feature fusion method for nonnegative single-feature fusion and multi-feature fusion. All methods were validated on scene classification benchmarks. Experiment results suggest that the proposed methods can deal with multi-class scene problems and achieve remarkable classification performance.