Image robust recognition based on feature-entropy-oriented differential fusion capsule network

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 51; no. 2; pp. 1108 - 1117
• Main Authors: Qian, Kui, Tian, Lei, Liu, Yiting, Wen, Xiulan, Bao, Jiatong
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2021; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Science; Convolution; Entropy; Feature extraction; Feature recognition; Machines; Manufacturing; Mechanical Engineering; Neural networks; Object recognition; Processes; Robustness; Transformations; Differential fusion; Robust recognition; Capsule network; Feature-entropy-oriented
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-020-01873-3

In solving the black box attribute problem of neural networks, how to extract feature information in data and generalize inherent features of data are the focus of artificial intelligence research. Aiming at the problem of the weak generalization ability of large image transformation under deep convolutional networks, a new method for image robust recognition based on a feature-entropy-oriented differential fusion capsule network (DFC) is proposed, the core of which is feature entropy approximation. First, convolution feature entropy is introduced as the transformation metric at the feature extraction level, and a convolution difference scale space is constructed using a residual network to approximate the similar entropy. Then, based on this scale feature, convolution feature extraction in a lower scale space is carried out and fused with the last scale feature to form a convolution differential fusion feature. Finally, a capsule network is used to autonomously cluster using dynamic routing to complete the semantic learning of various high-dimensional features, thereby further enhancing the recognition robustness. Experimental results show that feature entropy can effectively evaluate the transformation image recognition effect, and the DFC is effective for robust recognition with large image transformations such as image translation, rotation, and scale transformation.