International Research Journal of Engineering and Technology (IRJET) Volume: 11 Issue: 05 | May 2024
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
CROP WATCH – Empowering Precision Farming through ML and Image Analysis Dewanshi Pramani1 ,Chandni Yadav2,Gargi Balsaraf3,Niyati Wankhede4,Ishwar Bharambe5 1Department of Computer Engineering Ajeenkya DY Patil School of Engineering ,Pune, India 2Department of Computer Engineering Ajeenkya DY Patil School of Engineering ,Pune, India 3Department of Computer Engineering Ajeenkya DY Patil School of Engineering ,Pune, India 4Department of Computer Engineering Ajeenkya DY Patil School of Engineering ,Pune, India 5Professor, Department of Computer Engineering Ajeenkya DY Patil School of Engineering ,Pune, India
--------------------------------------------------------------------***----------------------------------------------------------------------
Abstract— "CROP WATCH - Empowering Precision
"CROP WATCH" goes further than that, though. In order to further improve crop management, our application expands its capabilities to include the weed plant identification and the detection of agricultural illnesses, and accurate weather predictions. It's a comprehensive toolset for contemporary farming, giving farmers knowledge and warnings to safeguard their crops and increase harvests.
Farming through ML and Image Analysis" uses cuttingedge machine learning and image analysis technology to transform contemporary agriculture. This document gives a summary of the project, emphasizing its main characteristics and functions. Through the simple upload of photos, the app enables users to identify different types of seeds and evaluate their quality, promoting wellinformed agricultural decision-making. Furthermore, it helps identify weed plants and detect plant illnesses early in agricultural fields, improving crop health and yield. It provides localized weather predictions with sophisticated machine learning algorithms for better crop planning. The programme also offers recommended pesticides, cropspecific production guidelines, and essential information. “CROP WATCH” is an effective tool at the nexus of agriculture and technology that makes precision farming practices possible and supports the production of food in a sustainable manner.
"CROP WATCH" is unique because of its customized feel. The programme transforms into a virtual agronomist by letting users choose particular crops, providing customized cultivation advice, suggested pesticides, and an extensive inventory of supplies needed for the crop of choice. It's a virtual assistant that makes farming less complicated. Apart from its distinct functionalities, "CROP WATCH" cultivates a feeling of camaraderie among its users. Through knowledge-sharing and conversation, farmers and hobbyists may connect, share thoughts, and work together to improve farming techniques through the app's "Community" function.
Keywords: Precision farming, Machine learning, Image analysis, Seed Recognition, Plant Disease Detection, Weed Identification, Convolutional Neural Network.
"CROP WATCH - Empowering Precision Farming through ML and Image Analysis is a technological revolution in agriculture, not just a smartphone application. An overview of our study is given in this paper, with a focus on its novel aspects, possible effects, and role in transforming agriculture in the future.
1. INTRODUCTION Creative solutions are critical in the quickly changing agricultural sector. In the field of precision farming, "CROP WATCH" stands out as a trailblazing initiative that uses image analysis and machine learning to revolutionize agricultural methods. This all-inclusive Android application, created for our computer engineering senior project, has the potential to completely transform how farmers and agriculture enthusiasts interact with the land. Fundamentally, "CROP WATCH" presents a fresh method for seed analysis. It enables users to make informed decisions from the planting stage onward by identifying different types of seeds, evaluating their quality, and extracting essential seed information from photographs supplied by users.
© 2024, IRJET
|
Impact Factor value: 8.226
2. LITERATURE SURVEY [1]The potential of Deep Learning (DL), and more especially Convolutional and Deep Neural Networks (CNN and DNN), to transform crop disease detection is examined in this research. The study intends to improve early disease identification in plants by utilizing these cutting-edge ML techniques, with an emphasis on visualizing disease symptoms. These models are assessed using a range of efficiency indicators, and the study finds important gaps in plant disease detection
|
ISO 9001:2008 Certified Journal
| Page 982