Corn seed variety classification based on hyperspectral reflectance imaging and deep convolutional neural network
- PDF / 3,945,525 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 31 Downloads / 206 Views
ORIGINAL PAPER
Corn seed variety classification based on hyperspectral reflectance imaging and deep convolutional neural network Jun Zhang1 · Limin Dai1 · Fang Cheng1 Received: 29 July 2020 / Accepted: 5 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Variety purity is an important indicator in seed quality detection. Different varieties of corn seeds may be mixed in the growth and development process, which affects the growth and yield of the seeds. Thus, it is necessary to find a fast and non-destructively method to detect the purity. In this paper, the feasibility of combining hyperspectral imaging with deep convolutional neural network (DCNN) was studied to classify four corn seed varieties. Firstly, the average spectra from the region of seed in endosperm side hyperspectral images over the wavelength range of 450–979 nm were extracted. Secondly, the performances of three models were compared, including DCNN, K nearest neighbors (KNN) and support vector machine (SVM). DCNN model has the 100% training accuracy rate, 94.4% testing accuracy rate and 93.3% validation accuracy rate, and outperforms KNN and SVM models in most cases. DCNN model also had the best performance in evaluation indexes (sensitivity, specificity and precision). Finally, the visual classification map was generated according to the results of DCNN. Results show that DCNN can be adopted in spectral data analysis for the variety classification of corn seed; and the classification performance can be improved effectively. Keywords Zea mays · Classification · Spectral-imaging technology · Deeping learning · Performance evaluation index · Image visualization
Introduction Corn (Zea mays L.) is one of the most widely-planted cereal grain crops in the world, with the yield of more than 59,000 kg/ha and an output of exceeding 1.1 billion tons in recent years according to the FAOSTAT (https://www.fao. org/faostat/zh/#data/QC) [1]. In the seed quality detection, variety purity is an important indicator, affecting the growth and yield of the seeds [2]. However, different varieties of corn seeds may be mixed in the growth and development process, such as cultivation, harvesting, transportation and storage [3, 4]. If the hybrid corn seeds are mixed with other * Fang Cheng [email protected] Jun Zhang [email protected] Limin Dai [email protected] 1
College of Biosystems Engineering & Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, Zhejiang, China
varieties of corn seeds, a yield loss will be caused. Moreover, it is difficult to distinguish the quality and the variety of corn seeds by the naked eye due to the similar shape. Therefore, relevant techniques should be used to accurately identify the corn variety for breeders, planters, and consumers. Traditional methods, including fluorescent scanning, protein electrophoresis, and deoxyribonucleic acid (DNA) molecular markers [3] have been applied to the variety classification of corn seeds. But these methods have certain limitations,
Data Loading...
