Total contribution score and fuzzy entropy based two‐stage selection of FC, ReLU and inverseReLU features of multiple convolution neural networks for erythrocytes detection

Total contribution score and fuzzy entropy based two‐stage selection of FC, ReLU and inverseReLU features of multiple convolution neural networks for erythrocytes detection

The proposed system aims at automatic erythrocytes detection using ensemble of selected features of multiple convolution neural networks (CNNs) to overcome the shortcomings of existing works arising due to the highly overlapping characteristics of handcrafted features. The main merit of this work li...

Full description

Bibliographic Details
Main Authors: Sriparna Banerjee, Sheli Sinha Chaudhuri
Format: Article
Language:English
Published: Wiley 2019-10-01
Series:IET Computer Vision
Subjects:
inverseReLU features
multiple convolution neural networks
two-stage feature selection algorithm
negative values
feature dimensionality
fully connected ReLU
Online Access:https://doi.org/10.1049/iet-cvi.2018.5545

Internet

https://doi.org/10.1049/iet-cvi.2018.5545

Similar Items