Abstract:
"
Banana is a famous fruit that commonly available across the world because it instantly
boosts your energy. Bananas are one most consumed fruit in the world. According to
modern calculations, Bananas are grown in around 107 countries since it makes a
difference to lower blood pressure and to reduce the chance of cancer and asthma.
Banana plant diseases have become a severe problem in Sri Lanka and all over the
world. This damages banana cultivation by affecting the banana quality and quantity.
The classical and ancient strategy for reconditioning and identifying banana plant
diseases is based on bare eye observation. Identifying from the naked eyes is not a good
method cause it spends time and it depends on the knowledge. And the main reason is
the less availability of experts.
In order to identify banana plant leaf diseases, the author has decided to develop a
Convolutional Neural Network (CNN) followed by a residual architecture. There
wasn’t an open-source dataset so the author had to create a dataset by doing image
augmentations. Two models were created with removing the background and without
removing the background and was able to get 97.14% and 98.7%."
