Deep feature learnt by conventional deep neural network

Huan Niu, Wei Xu, Hamidreza Akbarzadeh, Hamid Parvin, Amin Beheshti, Hamid Alinejad-Rokny

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)


In this paper, we introduce an approach to discriminate unconventional images and their intelligent filtering. As the target data to this issue are huge and consequently, a handling approach might potentially be a very time consuming one, one of the major challenges to be solved by this introduced approach is its ability for dealing with large-scale datasets. A deep neural network might be a good option to resolve this challenge. It can provide a good accuracy while dealing with huge databases. In the proposed approach, the new architecture is introduced using a combination of AlexNet and LeNet architectures. It uses convolutional, polling and fully-connected layers. The results are tested on two large-scale datasets. These tests show that the introduced architecture is more accurate than the other recently developed methods in identifying unconventional images. The proposed approach may be used in different applications such as intelligent filtering of unconventional images or medical images analysis.
Original languageEnglish
Article number106656
Pages (from-to)1-11
Number of pages11
JournalComputers and Electrical Engineering
Publication statusPublished - Jun 2020


  • Intelligent filtering system
  • Image classification
  • Deep feature
  • Deep neural network
  • Convolutional neural network
  • Data analytics


Dive into the research topics of 'Deep feature learnt by conventional deep neural network'. Together they form a unique fingerprint.

Cite this