Carrot is a famous nutritional vegetable and developed all over the world. Different diseases of Carrot has become a massive issue in the carrot production circle which leads to a tremendous effect on the economic growth in the agricultural sector. An automatic carrot disease detection system can help to identify malicious carrots and can provide a guide to cure carrot disease in an earlier stage, resulting in a less economical loss in the carrot production system. The proposed research study has developed a web application Carrot Cure based on Convolutional Neural Network (CNN), which can identify a defective carrot and provide a proper curative solution. Images of carrots affected by cavity spot and leaf bright as well as healthy images were collected. Further, this research work has employed Convolutional Neural Network to include birth neural purposes and a Fully Convolutional Neural Network model (FCNN) for infection order. Different avenues regarding different convolutional models with colorful layers are explored and the proposed Convolutional model has achieved the perfection of 99.8%, which will be useful for the drovers to distinguish carrot illness and boost their advantage.

翻译：胡萝卜是一种全球广泛种植的知名营养蔬菜。胡萝卜的多种病害已成为胡萝卜生产领域的重大问题，对农业部门的经济增长造成巨大影响。自动化胡萝卜病害检测系统能够识别病变胡萝卜，并在早期阶段提供病害防治指导，从而减少胡萝卜生产系统中的经济损失。本研究开发了一个基于卷积神经网络（CNN）的网络应用程序"胡萝卜杀手"，该程序能够识别缺陷胡萝卜并提供相应的治疗方案。研究收集了感染腔斑病和叶斑病的胡萝卜图像以及健康胡萝卜图像。此外，本研究采用卷积神经网络（包含出生神经功能）和全卷积神经网络模型（FCNN）进行病害分类。研究探索了具有不同网络层的多种卷积模型结构，所提出的卷积模型达到了99.8%的准确率，这将有助于种植者识别胡萝卜病害并提高收益。