Abstract:

It is great to hear about this project that offers a pest identification system for classifying helpful and harmful pests in crops. The use of a Convolutional Neural Network (CNN) for pest identification and classification is an innovative approach, and the use of a dataset of 1,500 photos of 9 distinct pests for training the model is commendable. The accuracy rate of 90% achieved by the proposed technique is indeed impressive and suggests that the model is effective in identifying and categorizing pests. It is also good to know that the system has been validated against other traditional classification models and has been evaluated with a large amount of data. However, it is essential to note that the accuracy of the model may depend on the quality and quantity of the training dataset, and it is important to ensure that the dataset used for training is representative of the real-world scenarios. Additionally, the effectiveness of the system in identifying pests in different crops and environments may also need to be evaluated. Overall, this project offers a promising solution for pest identification and classification in crops, and it has the potential to be a valuable tool for farmers and researchers in the field of agriculture.

Description:

Convolutional Neural Network, Classification, Deep Learning. Python – Keras, Tensor flow, Accuracy.