Terahertz digital holographic reconstructed images are vulnerable to noise pollution. This paper uses neural network to segment terahertz image, because this method is insensitive to noise. Firstly, the training sample image is decomposed into several sub-images, and the backward propagation(BP) neural network is trained by them. At the same time, the optimal number of hidden layer neurons is selected. Then the trained neural network is applied to the segmentation of terahertz image. Different segmentation results are obtained by changing the variance of noise in the training sample image. The best segmentation results and training samples are determined by using the mean structural similarity(MSSIM). Finally, compared with the classical image segmentation algorithm, the results show that the segmentation effect of the neural network is better.
It is necessary to study the image segmentation of terahertz digital holographic reconstructed images because of the boundary blurring problem. In this paper, a segmentation algorithm based on the region growth is proposed for terahertz digital holographic images. Firstly, the original image is bilaterally filtered and the morphological erosion operation is carried out to obtain the seeds of region growing. Secondly, the genetic algorithm is used to optimize threshold for restricting region growth. Finally, the segmentation results are obtained, and the average structural similarity (MSSIM) is used as an objective evaluation to measure effectiveness of the algorithm. The segmentation results show that the algorithm has a good segmentation effect, and the MSSIM can reach above 0.9.
The terahertz Gabor inline holographic reconstructed images have the characteristics of large backgrounds and small targets, which are different from the standard images of conventional research. Thus, we carried out the connected area disposal method before the Weighted Nuclear Norm Minimization (WNNM) in this paper. Connected area disposal can split the image into multiple independent regions to denoise the large background. The WNNM denoising method can preserve the details of the targets well. The numerical analysis and experimental researches of the denoising results proved that the proposed method in this paper can get a better denoising effect than WNNM algorithm alone.
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.