Open AccessDeep hashing network for material defect image classification
Author(s) -
Yang Kai,
Sun Zhiyi,
Wang Anhong,
Liu Ruizhen,
Sun Qianlai,
Wang Yin
Publication year - 2018
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2018.5286
Subject(s) - computer science , hash function , artificial intelligence , pattern recognition (psychology) , convolutional neural network , deep learning , convolution (computer science) , feature (linguistics) , feature vector , pooling , binary code , feature extraction , autoencoder , artificial neural network , contextual image classification , feature hashing , binary number , image (mathematics) , hash table , mathematics , linguistics , philosophy , computer security , arithmetic , double hashing
Common non‐destructive material testing technology has some well‐known problems such as slow detection, low detection accuracy, and low level of information obtained. To solve these problems, this study applied recent advances in convolution neural networks to propose an effective deep learning network using casting datasets. The approach achieves non‐destructive material testing with automatic, intelligent detection technology. For most existing deep learning networks, an image is eventually transformed into a multidimensional visual feature vector for comparison and classification. However, such vectors may not optimally improve detection precision and speed, and can lead to significant storage problems. A deep hashing network is proposed in which images are mapped into compact binary codes. There are three key components: (i) a sub‐network with multiple convolution‐pooling layers to capture image representations; (ii) a hashing layer to generate compact binary hash codes; (iii) an encoder module to divide the image feature vector from the output of the sub‐network above into multiple branches, each encoded into one hash bit. Extensive experiments using a casting dataset show promising performance compared with the state‐of‐the‐art approach.