Abstract
Ambiguous appearance discrimination plays an important role in the impurity detection task. Among the majority of deep learning models, images from every sequence are processed separately instead of being considered collectively. Therefore, the outputs of these models given a single region proposal might not be accurate. In this paper, a gallery-guided graph architecture is proposed and integrated to overcome such limitations. Specifically, region proposals are firstly generated using a two-stream fusion network; then their feature embeddings are extracted from a convolutional neural network by reducing intra-class variations while increasing inter-class ones. Secondly, a graph representing clusters among different training sequences updates relationships between region proposals in the test sequence. Finally, the features of the graph are classified by a graph convolutional neural network. Different from those learned weights in conventional common object detectors, region features from all the training sequences are explicitly integrated into a gallery-guided graph architecture. Extensive experiments on IML-DET dataset demonstrate that our proposed method can obtain competitive performances compared with previous state-of-the-art object detection approaches transferred into this task.
Highlights
Demands for impurity detection have been rapidly growing as the expanding constructions of high-speed production lines in the wine industry
He et al.: Gallery-Guided Graph Architecture for Sequential Impurity Detection backgrounds, inter-frame correlations among region proposal pairs may be efficient to discriminate impurities and backgrounds in most cases, feature embeddings cannot be explicitly obtained through a two-stream convolutional neural network
To address the first issue, we propose a simple two-stream fusion network and a feature embedding model to obtain discriminative feature embeddings for region proposals
Summary
Demands for impurity detection have been rapidly growing as the expanding constructions of high-speed production lines in the wine industry. Backgrounds, inter-frame correlations among region proposal pairs may be efficient to discriminate impurities and backgrounds in most cases, feature embeddings cannot be explicitly obtained through a two-stream convolutional neural network. To overcome the above problems, a gallery-guided architecture is proposed to integrate a graph-based region proposal classification framework to learn discriminative feature embeddings for the impurity detection task. The contributions of this paper are summarized as follows: 1) A two-stream fusion network is constructed to efficiently generate region proposals, and an online semi-hard triplet sampling scheme is experimented in an impurity feature embedding model to extract discriminative features. 2) A gallery-guided graph architecture is proposed by considering all the other node embeddings from a feature gallery, and a simple graph convolutional network is constructed to classify region proposals in a test sequence.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
