Naive Bayes Image Classification Based on Multiple Features

Kun Fang

Article ID: 1171
Vol 2, Issue 1, 2019, Article identifier:12-15

VIEWS - 261 (Abstract) 44 (PDF)


In the field of computer science, in order to realize the classification of images, a naive Bayes method based on multiple features has been proposed. This method is widely used and rich. It uses four features, such as extracting gray histogram features, SIFT features, SURF features, and reducing the dimensions of the dataset from data image sets. Naive Bayesian methods are used to obtain The accuracy, recall, and F1 value of the image for each feature. This paper analyzes the application and feature comparison of Naive Bayes method in images, and shows that image representation using SURF feature description can achieve better classification results.


Naive Bayes Method; Naive Image Feature Classification; SURF Image Feature

Full Text:



Naive Bayes Classification (very simple and clear interpretation) (in Chinese) [Internet]. 2018. Available from:

Image Grayscale Features-first--order Statistical Features / Grayscale Histogram Features (Matlab Implementation) (in Chinese) [Internet]. 2019. Available from:

Shen Y. Research on criminal image classification and retrieval based on machine learning. Xi'an Technological University 2018.

Zhang B. Naive bayesian classifier method based on the classification of the probability weighted. Journal of Chongqing University of Technology (Natural Science) 2012; 26(7): 81-83. doi: 10.3969/j.issn.1674-8425-B.2012.07.017.

Machine learning methods of low-dose CT imaging have achieved good results (in Chinese). Journal of Health and Science 2019.

Zhang X, Jiang J, Hong R, et al. Accelerated image classification algorithm based on naive Bayes K-nearest neighbor. Journal of Beijing University of Aeronautics and Astronautics 2015; 41(2): 302-310. doi: 10.13700/

Liu C. Image recognition comparison based on naive bayes and semi-naive bayes. Information Technology and Network Security 2018; 37(12): 48-51. doi: 10.19358/j.issn.2096-5133.2018.12.010.

Accuracy, Precision, Recall, F1 Value, ROC / AUC Collation Notes (in Chinese) [Internet]. 2018. Available from:



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.