The important task of 2D image classification and segmentation is the extraction of the local geometrical features. The convolution neural network is the common approach last years in this field. Usually, the neighborhood of each pixel of the image is implemented to collect local geometrical information. The information for each pixel is stored in a matrix. Then, Convolutional Auto-Encoder (CAE) is utilized to extract the main geometrical features. In this paper, we propose a neural network based on CAE to solve the extraction of local geometrical features problem for noisy images. Computer simulation results are provided to illustrate the performance of the proposed method.
Convolutional auto-encoder to extract local features of 2D images
Applications of Digital Image Processing XLVI ; 2023 ; San Diego, California, United States
Proc. SPIE ; 12674
2023-10-04
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic anomaly detection method based on graph convolutional neural network auto-encoder
Europäisches Patentamt | 2023
|NRZ Data Asymmetry Corrector and Convolutional Encoder
NTRS | 1983
|