English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Defect detection is a basic and essential task in automatic parts production,especially for automotive engine precision parts. In this paper, we propose anew idea to construct a deep convolutional network combining related knowledgeof feature processing and the representation ability of deep learning. Ouralgorithm consists of a pixel-wise segmentation Deep Neural Network (DNN) and afeature refining network. The fully convolutional DNN is presented to learnbasic features of parts defects. After that, several typical traditionalmethods which are used to refine the segmentation results are transformed intoconvolutional manners and integrated. We assemble these methods as a shallownetwork with fixed weights and empirical thresholds. These thresholds are thenreleased to enhance its adaptation ability and realize end-to-end training.Testing results on different datasets show that the proposed method has goodportability and outperforms the state-of-the-art algorithms.

PartsNet: A Unified Deep Network for Automotive Engine Precision Parts Defect Detection