GACNet: Generate Adversarial-Driven Cross-Aware Network for Hyperspectral Wheat Variety Identification

Wheat variety identification from hyperspectral images holds significant importance in both fine breeding and intelligent agriculture. However, the discriminatory accuracy of some techniques is limited due to insufficient datasets, data redundancy, and noise interference. To address these issues, we propose a wheat variety identification framework called generate adversarial-driven cross-aware network (GACNet), comprising a semi-supervised generative adversarial network (GAN) for data augmentation and a cross-aware attention network (CAANet) for variety identification. First, the semi-supervised GAN (SSGAN) alleviates data scarcity by generating fake hyperspectral images as realistically as possible through learning the distribution hypothesis of real hyperspectral images, while the discriminator distinguishes between real and fake hyperspectral images. Subsequently, the CAANet is employed for wheat variety identification, which leverages a cascading cross-learning of 3-D and 2-D convolutions to fully exploit spectral, spatial, and texture features and refines the features through an embedded attention mechanism in the cross-convolutional module. Additionally, we constructed a hyperspectral wheat variety dataset (HWVD) comprising 4560 samples of 19 categories. Extensive experiments on our dataset demonstrate that our GACNet outperforms state-of-the-art methods for wheat variety identification. The HWVD will be made available.

I. Introduction

With a wide variety of wheat varieties entering the market and meeting the needs of different populations, the risk of wheat variety mixing has increased. However, mixing seeds presents many challenges for fine breeding in intelligent agriculture [1]. Traditional chemometric methods for seed identification face limitations regarding seed destruction and time-consuming identification processes, failing to meet the demand for efficient and rapid identification of seed varieties in modern agriculture. Hyperspectral imaging, on the other hand, offers non-destructive, fast, and efficient identification capabilities by capturing and analyzing spectral information point by point in a spatial region, making it increasingly attractive for agricultural seed identification [2], [3].