Terahertz Images for Grass Seed Detection

This dataset comprises Terahertz (THz) images collected to support the research presented in the IEEE Access paper titled Diagnosing Grass Seed Infestation: Convolutional Neural Network Based Terahertz Imaging. The dataset is intended for the detection and classification of grass seeds embedded in biological samples, specifically ham, covered with varying thicknesses of wool. The images were captured at different frequencies within the THz spectrum, providing valuable data for the development of deep-learning models for seed detection. Each image is labeled based on the frequency at which it was taken and the specific seed within the sample. For instance, an image labeled 20 corresponds to a THz image taken at 0.2 THz for a sample containing four seeds. The individual seeds within the sample are further labeled as 20s1, 20s2, etc., denoting specific seed locations in the 0.2 THz image. This structured labeling facilitates precise training and validation of machine learning models, enabling accurate detection and classification of seeds even when obscured by wool layers.