Image Classification Based on the Boost Convolutional Neural Network

Sj Lee, Tonglin Chen, Lun Yu, Chin Hui Lai*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

39 Scopus citations


Convolutional neural networks (CNNs), which are composed of multiple processing layers to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years. However, these models can have millions of parameters and many layers, which are difficult to train, and sometimes several days or weeks are required to tune the parameters. Within this paper, we present the usage of a trained deep convolutional neural network model to extract the features of the images, and then, used the AdaBoost algorithm to assemble the Softmax classifiers into recognizable images. This method resulted in a 3% increase of accuracy of the trained CNN models, and dramatically reduced the retraining time cost, and thus, it has good application prospects.

Original languageEnglish
Pages (from-to)12755-12768
Number of pages14
JournalIEEE Access
StatePublished - 24 Jan 2018


  • Convolutional neural network
  • boosting
  • deep learning
  • ensemble learning

Fingerprint Dive into the research topics of 'Image Classification Based on the Boost Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this