An efficient FCN based neural network for image semantic segmentation

Ruixin Yang; Chengpo Mu; Yu Yang; Xuejian Li

doi:10.1117/12.2540137

14 August 2019 An efficient FCN based neural network for image semantic segmentation

Ruixin Yang, Chengpo Mu, Yu Yang, Xuejian Li

Proceedings Volume 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019); 111794J (2019) https://doi.org/10.1117/12.2540137
Event: Eleventh International Conference on Digital Image Processing (ICDIP 2019), 2019, Guangzhou, China

Abstract

Image segmentation has always been a key research issue in the field of computer vision. Image segmentation networks that use deep learning methods require a large number of finely labeled samples, which is difficult to obtain. In this paper, we combine the focal loss function with the fully convolutional networks to improve network performance. And we collected and built a dataset contents 1500 samples with complex background. We trained the improved network with the dataset to achieve 81.55% in mean average precision and 76.13% in mean intersection over union.

Citation Download Citation

Ruixin Yang, Chengpo Mu, Yu Yang, and Xuejian Li "An efficient FCN based neural network for image semantic segmentation", Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 111794J (14 August 2019); https://doi.org/10.1117/12.2540137

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available