Litcius/Paper detail

Low Light Image Enhancement in License Plate Recognition using URetinex-Net and TRBA

Vriza Wahyu Saputra, Nanik Suciati, Chastine Fatichah

2024Procedia Computer Science14 citationsDOIOpen Access PDF

Abstract

The license plate recognition system currently in use is susceptible to interference from the external environment and performs poorly in low-light conditions. This paper presents a solution for license plate recognition under a low-light environment. We adopted URetinex-Net methods that unfold an optimization issue into a learnable network to decompose a low illumination image into reflectance and illumination layers. We also adopted TRBA, an end-to-end recognition method involving no character segmentation. The experimental results show that the accuracy of the night environment of the proposed method is 80.11% increased by 5.11% compared to without the low light image enhancement method.

Topics & Concepts

Computer scienceLicenseArtificial intelligenceComputer visionImage (mathematics)Net (polyhedron)Image enhancementComputer graphics (images)Pattern recognition (psychology)Operating systemMathematicsGeometryVehicle License Plate RecognitionHandwritten Text Recognition TechniquesAdvanced Steganography and Watermarking Techniques
Low Light Image Enhancement in License Plate Recognition using URetinex-Net and TRBA | Litcius