Research on Classification Method of Maize Seed Defect Based on Machine Vision

Traditionally, the classification of seed defects mainly relies on the characteristics of color, shape, and texture. This method requires repeated extraction of a large amount of feature information, which is not efficiently used in detection. In recent years, deep learning has performed well in the...

Full description

Saved in:
Bibliographic Details
Published in:Journal of sensors 2019, Vol.2019 (2019), p.1-9
Main Authors: Shen, Yanlu, Sun, Lei, Fan, Xiaofei, Huang, Sheng, Suo, Xuesong
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Automation
Classification
Corn
Deep learning
Defects
Feature extraction
Feature maps
Graphical representations
International conferences
Machine learning
Machine vision
Neural networks
Object recognition
Pattern recognition
Probabilistic inference
Researchers
Seeds
Vision systems
Watersheds
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditionally, the classification of seed defects mainly relies on the characteristics of color, shape, and texture. This method requires repeated extraction of a large amount of feature information, which is not efficiently used in detection. In recent years, deep learning has performed well in the field of image recognition. We introduced convolutional neural networks (CNNs) and transfer learning into the quality classification of seeds and compared them with traditional machine learning algorithms. Experiments showed that deep learning algorithm was significantly better than the machine learning algorithm with an accuracy of 95% (GoogLeNet) vs. 79.2% (SURF+SVM). We used three classifiers in GoogLeNet to demonstrate that network accuracy increases as the depth of the network increases. We used the visualization technology to obtain the feature map of each layer of the network in CNNs and used the heat map to represent the probability distribution of the inference results. As an end-to-end network, CNNs can be easily applied for automated seed manufacturing.
ISSN:1687-725X
1687-7268
DOI:10.1155/2019/2716975