File(s) under permanent embargo

Reason: This item is currently closed access.

Automatic counting and classification of silkworm eggs using deep learning

conference contribution
posted on 07.02.2019, 11:07 by Shreedhar Rangappa, A. Ajay, G.S. Rajanna
We describe the use of convolution neural networks to identify and quantify the silkworm eggs that are laid on a sheet of paper by female silk moth. The method is also capable of identifying individual egg and classifying them into Hatched egg class and Unhatched egg class, thus outperforming image processing tech-niques used earlier. We identify few limitations in the techniques employed earlier and attempted to increase accuracy using uniform illumination of a digital scan-ner. Use of digital scanner increases repeatability. Accordingly, we illustrate the use of standard key marker that helps to transform any silkworm egg sheet into a standard image, which can be used as input to a trained convolution neural net-work model to get predictions. We have also prepared silkworm datasets of over 100K images for each category that can be used to train CNN. The experimental results on test image sets show that our approach yields an accuracy of above 97% coupled with high repeatability.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Citation

RANGAPPA, S., AJAY, A. and RAJANNA, G.S., 2019. Automatic counting and classification of silkworm eggs using deep learning. Presented at the International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, NIT Kurukshetra, India, 3-4 March 2019.

Version

AM (Accepted Manuscript)

Publisher statement

This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/

Acceptance date

27/12/2018

Publication date

2019

Notes

This conference paper is closed access.

Publisher version

Language

en