Читать книгу Machine Learning Algorithms and Applications - Группа авторов - Страница 28

Shreedhar Rangappa1*, Ajay A.1 and G. S. Rajanna2

1Intelligent Vision Technology, Bengaluru, India

2Maharani Cluster University, Sheshadri Road, Bengaluru, India

Abstract

The method of using convolutional 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 segmenting individual egg and classifying them into hatched egg class and unhatched egg class, thus outperforming image processing techniques used earlier. Fewer limitations of the techniques employed earlier are described and attempt to increase accuracy using uniform illumination of a digital scanner is illustrated. The use of a 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 network model to get predictions, is discussed briefly. The deep learning model is trained on silkworm datasets of over 100K images for each category. The experimental results on test image sets show that our approach yields an accuracy of above 97% coupled with high repeatability.

Keywords: Deep learning, convolution neural network, datasets, accuracy, silkworms, fecundity, hatching percentage