AI Article Synopsis
- - A new method for object classification using a single-pixel neural network is introduced, allowing direct classification from bucket measurements without the need for full image reconstruction.
- - This method achieves a high classification accuracy of 94.23% using only 16 measurements, significantly below the Nyquist limit, and employs parallel computing to speed up data processing.
- - The approach improves performance over existing techniques for both binary and grayscale images in challenging conditions, making it potentially useful in areas like remote sensing and military defense.
Article Abstract
A single-pixel neural network object classification scenario in the sub-Nyquist ghost imaging system is proposed. Based on the neural network, objects are classified directly by bucket measurements without reconstructing images. Classification accuracy can still be maintained at 94.23% even with only 16 measurements (less than the Nyquist limit of 1.56%). A parallel computing scheme is applied in data processing to reduce the object acquisition time significantly. Random patterns are used as illumination patterns to illuminate objects. The proposed method performs much better than existing methods for both binary and grayscale images in the sub-Nyquist condition, which is also robust to environment noise turbulence. Benefiting from advantages of ghost imaging, it may find applications for target recognition in the fields of remote sensing, military defense, and so on.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/AO.438392 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!