Home > Accepted Papers >
Accepted 15 October 2019

Stacked Denoising Auto-Encoder Deep Learning-Based Cow Recognition Technique Using Nose Image Pattern

Rotimi-Williams Bello, Abdullah Zawawi Hj Talib, and Ahmad Sufril Azlan Bin Mohamed

Abstract: In order to tackle the problem of cow recognition from the nose, and for the learning and representation of its discriminatory features; stacked denoising auto-encoder deep learning is proposed in this work. Stacked denoising auto-encoder is an encoding technique that initializes deep network and it is applicable in analyzing cow nose image by encoding and decoding the extracted features. Stacked denoising auto-encoder helps in animal biometrics. Biometrics emanated from computer vision and pattern recognition and it plays an important role in the automated animal registration and identification process. Using the visual attributes of cow, and for the fact that the existing visual feature extraction and representation methods are not capable of handling cow recognition; stacked denoising auto-encoder technique is employed. An experiment performed under different conditions of identification indicated that the proposed method outshines the existing methods with approximately 98.99% accuracy. 4000 cow nose images from an existing database of 400 individual cows contribute to the community of research especially in the animal biometrics for identification of individual cow.

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Scopus (since 2017), Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net


Article Metrics