An efficient FCN based neural network for image semantic segmentation

Ruixin Yang, Chengpo Mu, Yu Yang, Xuejian Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationEleventh International Conference on Digital Image Processing, ICDIP 2019
EditorsJenq-Neng Hwang, Xudong Jiang
PublisherSPIE
ISBN (Electronic)9781510630758
DOIs
Publication statusPublished - 2019
Event11th International Conference on Digital Image Processing, ICDIP 2019 - Guangzhou, China
Duration: 10 May 201913 May 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11179
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference11th International Conference on Digital Image Processing, ICDIP 2019
Country/TerritoryChina
CityGuangzhou
Period10/05/1913/05/19

Keywords

  • Convolutional neural network
  • FCN
  • Focal loss
  • Image segmentation

Fingerprint

Dive into the research topics of 'An efficient FCN based neural network for image semantic segmentation'. Together they form a unique fingerprint.

Cite this