Automatic image annotation method based on a convolutional neural network with threshold optimization.
In this study, a convolutional neural network with threshold optimization (CNN-THOP) is proposed to solve the issue of overlabeling or downlabeling arising during the multilabel image annotation process in the use of a ranking function for label annotation along with prediction probability. This mod...
Main Authors: | Jianfang Cao, Aidi Zhao, Zibang Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2020-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0238956 |
Similar Items
-
Application of a Modified Generative Adversarial Network in the Superresolution Reconstruction of Ancient Murals
by: Jianfang Cao, et al.
Published: (2020-01-01) -
CM-supplement network model for reducing the memory consumption during multilabel image annotation.
by: Jianfang Cao, et al.
Published: (2020-01-01) -
Ancient mural restoration based on a modified generative adversarial network
by: Jianfang Cao, et al.
Published: (2020-01-01) -
Particle Swarm Optimization for Automatically Evolving Convolutional Neural Networks for Image Classification
by: Tom Lawrence, et al.
Published: (2021-01-01) -
Video annotation using convolution neural network
by: Wan Abd. Kadir, Wan Zahiruddin
Published: (2018)