Deep Learning Based Zucchini Leaf Diseases Detection: A Commercial Agriculture Development in Bangladesh

Abstract

"The economic growth of Bangladesh is heavily

dependent on agricultural production, but the several

diseases have significantly impeded the growth of crops.

The zucchini plant is commonly afflicted by diseases such

as alternaria blight, anthracnose, and angular leaf spot. As

a result, it is now crucial to detect leaf diseases at an early

stage to prevent damage to the entire crop. However,

farmers often lack of sufficient knowledge regarding leaf

diseases and resort to manual methods for identifying

disorders. The accuracy of detection is inadequate and time

consuming. Therefore, it is crucial to develop an automated

and precise identification system to solve this issue. This

article introduces a new method for diagnosing and

categorizing diseases in zucchini plants. Deep learning,

which is a modern and effective approach, is suggested as a

means to recognize the disorder and determine the

appropriate treatment. Our primary focus was on training

the raw dataset using the CNN algorithm, which resulted in

an accuracy rate of 88.30 percent. Detecting and identifying

diseases in the zucchini plant would contribute to the

economic growth of Bangladesh by enhancing the

production rate of the crop."