Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179938,
        author = {Nikhil Bare and Rohan Doifode and Godavari Kadam and Bhakti Shirsat},
        title = {DEEP LEARNING BASED AGRICULTURE WEED DETECTION AND CLASSIFICATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8932-8936},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179938},
        abstract = {Weed detection using deep learning is a 
cutting-edge application of artificial intelligence in 
agriculture. This technology offers a sophisticated 
solution to the age-old problem of weed management, 
aiming to revolutionize farming practices worldwide. 
The process begins with the acquisition of image data 
depicting agricultural fields, captured through various 
means. These images serve as the raw material for 
training the CNN model, providing a rich source of 
information about the crops and the surrounding 
environment, including the presence of weeds. The 
essence of CNNs lies in their ability to automatically 
learn and extract intricate patterns and features from 
images. Through multiple layers of convolution and 
pooling, these neural networks transform raw pixel data 
into meaningful representations, enabling them to 
discern subtle differences between crops and weeds. 
Training a CNN model for weed detection involves a 
complex interplay of data preprocessing, model 
architecture selection, and optimization. The dataset is 
carefully curated, normalized, and augmented to ensure 
diversity and robustness.},
        keywords = {weed detection, Image processing, deep  learning; CNN.},
        month = {May},
        }