Smart Seed Classification System based on MobileNetV2 Architecture

The agricultural transformation in the last decade using artificial intelligence has led to significant gains in productivity and profitability. The traditional machine learning approaches present inherent limitations in extracting features and information from image data. Deep learning techniques,...

Full description

Saved in:
Bibliographic Details
Published in2022 2nd International Conference on Computing and Information Technology (ICCIT) pp. 217 - 222
Main Authors Hamid, Yasir, Wani, Sharyar, Soomro, Arjumand Bano, Alwan, Ali A., Gulzar, Yonis
Format Conference Proceeding
LanguageEnglish
Published IEEE 25.01.2022
Subjects
Agriculture
Artificial Intelligence
Convolutional Neural Network
Deep learning
Feature extraction
Machine Learning
Memory architecture
MobileNetV2 architecture
Precision Agriculture
Productivity
Profitability
Seed Classification
Training
Online AccessGet full text
DOI10.1109/ICCIT52419.2022.9711662

Cover

More Information
Summary:The agricultural transformation in the last decade using artificial intelligence has led to significant gains in productivity and profitability. The traditional machine learning approaches present inherent limitations in extracting features and information from image data. Deep learning techniques, particularly CNN's, help to overcome these limitations due to their multi-level architecture. Various deep learning applications in agriculture include crop disease identification, fruit classification, and germination rate monitoring. Seed image analysis is considered a significant task for the preservation of biodiversity and sustainability. This research uses MobileNetV2, a deep learning convolutional neural network (DCNNs) for seed classification. This model has been preferred due to its simple architecture and memory-efficient characteristics. A total of 14 different classes of seeds were used for the experimentation. The results indicate accuracies of 98% and 95% on training and test sets, respectively.
DOI:10.1109/ICCIT52419.2022.9711662