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

TL;DR

This study combines hyperspectral imaging and transfer learning with a VGG-19 model to accurately identify haploid maize seeds, achieving over 95% accuracy and reducing sample collection costs.

Contribution

It introduces a novel application of transfer learning with hyperspectral imaging for maize seed identification, demonstrating high accuracy with limited data.

Findings

Correct identification rate of 96.32% with multi-band images

Single-band spectral images achieve 95.75% accuracy

Transfer learning enables high accuracy with small datasets

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.