Terahertz (THz) technology has become a new trend in various fields due to its high penetration and harmlessness towards human body and objects. The object detection of concealed and hidden objects based on THz images is of great significance for ensuring public safety. However, the poor quality of original THz images leads to insufficient accuracy in target detection. Therefore, it is necessary to preprocess the images before performing object detection. In this work, in order to investigate the impact of different pre-processing methods on object detection using images, we adopt two methods, namely non-local mean (NLM) filtering and histogram equalization (HE). After pre-processing, YOLOv7 algorithm is used to perform object detection based on the preprocessed THz images. The experimental results show that YOLOv7 achieves highest recognition accuracy on NLM filtered THz images. The experimental results presented in this work provide a reference to select image processing method for performing concealed object detection based on THz images.
The freshness of rice reflects the time that has elapsed since it was harvested and the extent of deterioration in the quality of the rice that has occurred during storage. Therefore, it is crucial to detect the freshness of rice samples; here, we undertake that task using terahertz images and a modified VGG network. Terahertz imaging is non-destructive, permits molecular fingerprinting, and is low in energy consumption. Terahertz imaging technology uses terahertz rays to irradiate the sample and obtains a terahertz image of the sample by processing and analyzing the transmission and reflection spectra of the sample. Terahertz imaging technology has been widely used in applications related to material identification, medical diagnoses, quality detection of agricultural products, and safety inspections. In this paper, terahertz images of rice stored for various lengths of time were analyzed using a terahertz imaging system. Due to a large amount of data and inconspicuous features of the terahertz image, the traditional 1D-VGG network is relatively insufficient in computing power. Thus, it is not well suited to the extraction of features from within the images. To resolve this issue, the Inception-ResNet-A asymmetric convolution module in the Inception-ResNet-V2 network has great computing power,which is introduced into the VGG19 network structure. This proposed network is found to increase identification accuracy up to 99.8%. This work indicates that terahertz images combined with the modified 1D-VGG network represent an efficient and practical method for identifying rice freshness; this work thus has great potential for use as a tool for ensuring food quality and safety.
In this work, terahertz time-domain (THz) spectroscopy and deep learning were used to analyze the spectral characteristics of a sample in the terahertz region. Nonlinear dimensionality reduction of the THz spectral data and a detection model for the freshness of stored wheat were investigated by deep learning and THz-TDS. The aim of this work was to enrich and develop the theory and method for testing stored grain quality, and improving the storage of rice through the use of THz technology. Furthermore, the work will provide theoretical basis for reducing the loss of grain storage.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.