This article discusses the presence of useful information in highly degraded images and that convolutional neural networks can be trained to decipher the contents of very low-quality images, specifically, of license plates.
Extremely low-quality images, on the order of 20 pixels in width, appear with frustrating frequency in many forensic investigations. Even advanced de-noising and super-resolution technologies are unable to extract useful information from such low-quality images. However, in this paper, the authors show that useful information is present even in such highly degraded images. The authors also show that convolutional neural networks can be trained to decipher the contents of highly degraded images of license plates, and that these networks significantly outperform human observers. Publisher Abstract Provided
Downloads
Similar Publications
- Certification of Standard Reference Material 2323: Step Height Standard for Areal Surface Topography Measurement
- Pressure-based alkaline lysis with immunocapture a method for enhanced recovery in differential extraction
- Forcible, Drug-Facilitated, and Incapacitated Rape in Relation to Substance Use Problems: Results from a National Sample of College Women