International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
A Survey on Comprehensive Rice Grain Quality Analysis using Machine Learning Rambabu Pasumarthy1, Naga Lakshmi Spandana Atyam2, Thanuja Mattaparthi3, Nani Pasupuleti4, Sujini Meripo5 1Associate Professor, Dept. of Computer Science and Engineering, Sasi Institute of Technology & Engineering,
Tadepalligudem, A.P., India
2,3,4,5 Students of Computer Science and Engineering, Sasi Institute of Technology & Engineering, Tadepalligudem,
A.P., India ---------------------------------------------------------------------***--------------------------------------------------------------------automation in grain quality testing remains limited, Abstract - Rice, the most extensively cultivated crop in primarily relying on manual labour. India, plays a crucial role as a primary dietary staple. It feeds a significant portion of the global population and The assessment of grain quality is still only partially underscores its pivotal position in ensuring food security. automated, the majority of the work is still done by humans. Approximately 70% of the Indian population consumes Rice is particularly important, being one of the most rice twice daily. The quality of rice is determined by consumed cereal grains in India. The quality of grains greatly various attributes that influence its taste, appearance, affects both the national and international rice market. This texture, and suitability for different culinary purposes. identification process is presently carried out manually by The quality of rice grains holds paramount importance human inspectors, which guarantees a certain level of accuracy [5]. However, it requires a lot of work, takes a lot of in determining consumer satisfaction and economic time, and is judgment-based. For identifying the rice quality, value. In earlier times, identifying rice quality relied on a sample of rice must be separated into the following six manual inspection conducted by human inspectors an categories: complete rice, cracked rice, paddy, stones, and approach that was both time-consuming and prone to foreign items. low accuracy. However, there are still difficulties in creating quick and inexpensive methods for assessing the features of commercial rice grain quality. Therefore, it is good to use machine learning algorithms. This adoption of machine learning not only ensures food security but also modernizes the agricultural landscape of India. Key Words: Rice, Rice grain quality, supervised machinelearning algorithm, quality grading.
1.INTRODUCTION The primary source of agricultural revenue in our nation is grains. While grains are growing, farmers pay the most attention to yields. However, quality becomes the main priority when rice is processed and sold. Various pollutants, like as stones, weed seeds, chaff, and cracked seeds, may be present in that grains. Grain quality testing is currently not highly automated, with the majority of the work being done by humans. This manual process can lead to worker fatigue and increase both the cost and duration of testing. To address these issues, a machine learning model for assessing and identifying quality grades has been developed. This model utilizes features such as major and minor axis parameters, size, eccentricity, roundness and area, employing image processing and other technologies. Grains are a crucial crop in our nation, and their quality significantly impacts agricultural income. However, the level of
© 2024, IRJET
|
Impact Factor value: 8.226
Fig -1: Flow chart of complete process
|
ISO 9001:2008 Certified Journal
|
Page 174