Hyperspectral Imaging Technology and Transfer Learning Utilized in Haploid Maize Seeds Identification

Abstract

It is extremely important to correctly identify the cultivars of maize seeds in the breeding process of maize. In this paper, the transfer learning as a method of deep learning is adopted to establish a model by combining with the hyperspectral imaging technology. The haploid seeds can be recognized from large amount of diploid maize ones with great accuracy through the model. First, the information of maize seeds on each wave band is collected using the hyperspectral imaging technology, and then the recognition model is built on VGG-19 network, which is pre-trained by large-scale computer vision database (Image-Net). The correct identification rate of model utilizing seed spectral images containing 256 wave bands (862.5-1704.2nm) reaches 96.32%, and the correct identification rate of the model utilizing the seed spectral images containing single-band reaches 95.75%. The experimental results show that, CNN model which is pre-trained by visible light image database can be applied to the near-infrared hyperspectral imaging-based identification of maize seeds, and high accurate identification rate can be achieved. Meanwhile, when there is small amount of data samples, it can still realize high recognition by using transfer learning. The model not only meets the requirements of breeding recognition, but also greatly reduce the cost occurred in sample collection.

Computer-vision classification of corn seed varieties using deep convolutional neural network

“…They claimed 100% accuracy of the proposed model. Liao et al (2019) investigated the feasibility of haploid corn seeds classification, using hyperspectral images. A VGG-19 network was used to extract the image properties.…”

Fully Convolutional Networks with Multiscale 3D Filters and Transfer Learning for Change Detection in High Spatial Resolution Satellite Images

“…As the ultimate goal of transfer learning is to improve the change detection performance, the low-level features learned by deep networks from the source domain are transferred to the target domain. This provides excellent initial configurations in the transfer learning method to quickly initiate meaningful feature extraction from the multi-temporal high spatial resolution satellite images; proper initialization is crucial for network training [44]. The hypothesis is that the lowest layers of the FCN extract general features from the images; therefore, the learned weights are extended to other recognition tasks, as these mostly detect generic features.…”

“…Although the LSTM learns the rules for change detection between temporal data, the images must be flattened for use with the fully connected LSTM network. Therefore, the LSTM is unsuitable for image analysis because it ignores spatial connectivity and the large weight matrix size increases the computational cost [44]. Therefore, change detection methods using LSTM, such as LSTM and 2D CNN-LSTM, relatively detect changes as unchanged areas than FCN-based change detection methods.…”

Research on plant seeds recognition based on fine-grained image classification

“…Through CNNs, features are extracted without manual operation. In 2019, Liao et al 25 . used hyperspectral and transfer learning techniques to identify corn seeds through a pre-trained VGG19 model, with the accuracy of 95.75%.…”

“…Through CNNs, features are extracted without manual operation. In 2019, Liao et al 25 used hyperspectral and transfer learning techniques to identify corn seeds through a pre-trained VGG19 model, with the accuracy of 95.75%. In 2020, Lei et al 26 used hyperspectral and CNNs to estimate the vigor and germination of corn seeds and the accuracy of 1DCNN and 2DCNN was 90.11% and 99.96%, respectively.…”