Spatially Variant Convolutional Autoencoder Based on Patch Division for Pill Defect Detection

Spatially Variant Convolutional Autoencoder Based on Patch Division for Pill Defect Detection

Detecting pill defection remains challenging, despite recent extensive studies, because of the lack of defective data. In this paper, we propose a pipeline composed of a pill detection module and an autoencoder-based defect detection module to detect defective pills in pill packages. Furthermore, we...

Full description

Bibliographic Details
Main Authors: Sora Kim, Youngjae Jo, Jungchan Cho, Jiwoo Song, Younyoung Lee, Minsik Lee
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Pill defect detection
deep neural network
convolutional autoencoder
unsupervised learning
Online Access:https://ieeexplore.ieee.org/document/9274349/

Internet

https://ieeexplore.ieee.org/document/9274349/

Similar Items