Identification of Corn Seeds with Different Freezing Damage Degree Based on Hyperspectral Reflectance Imaging and Deep L
- PDF / 936,764 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 184 Views
Identification of Corn Seeds with Different Freezing Damage Degree Based on Hyperspectral Reflectance Imaging and Deep Learning Method Jun Zhang 1 & Limin Dai 1 & Fang Cheng 1 Received: 1 July 2020 / Accepted: 25 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Seed freezing damage is an agricultural disaster, which has a great impact on seed quality assurance. The feasibility of combining hyperspectral imaging with deep convolutional neural network (DCNN) to classify different freeze-damaged corn seeds was studied in this paper. At first, the hyperspectral images of corn seeds subjected to five different freezing temperatures at 400– 1000 nm were acquired, and then the average spectra were extracted from the region of embryo hyperspectral images over the wavelength range of 450–979 nm. Next, four models (K nearest neighbors (KNN), support vector machine (SVM), extreme learning machine (ELM), and DCNN) were developed for five-category (5 frozen conditions) and four-category (“no freezing,” “slight freezing,” “moderate freezing,” and “severe freezing”) classifications, and the values of the evaluation indexes (accuracy, sensitivity, specificity, and precision) were calculated for comparison. The results show that DCNN model had the most satisfactory result with accuracy rates of 100% (training set), 96.9% (validation set), and 97.5% (testing set) for five-category classification, with accuracy rates of 100% (training, validation, and testing set) for four-category classification, and DCNN model also had the best performance in the evaluation indexes. At last, the visual classification map was generated according to the results of DCNN. It shows that hyperspectral imaging and DCNN can provide a novel method to detect the freezing damage of corn seeds quickly and inexpensively. Keywords Identification . Freeze-damaged corn seed . Hyperspectral imaging . Deep convolutional neural network . Performance evaluation index . Image visualization
Introduction Corn (Zea mays L.) is widely planted in China and other countries, which is one of the most common food crops (Ambrose et al. 2016). It is well known that the seed embryo is the most important part of the seed. It contains most of the nutrients in the seed, and eventually it is developed into the root, stem, and leaf of the plant. If damage exists in this part, it
* 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
must have great impact on subsequent growth of the seed (Akinyosoye et al. 2014). In China, most of the corn seeds are produced in the north, such as Gansu province or Heilongjiang province. In those places, corn seeds are usually planted in April and harvested in October and November each year. Due to the geographical location, the weather is relatively cold at the harvesting time, and sometimes frost occurs. Thus, the corn seed is often damaged due t
Data Loading...
