Details

Autor(en) / Beteiligte

• Lee, Seyun
• Kim, Ji-Hwan
• Heo, Jae-Pil

Titel

Super-Resolution of License Plate Images via Character-Based Perceptual Loss

Ist Teil von

• 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), 2020, p.560-563

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEL

Beschreibungen/Notizen

• License Plate Recognition (LPR) is an highly influential problem in computer vision. In this paper, we present a super-resolution model specialized for the license plate images, CSRGAN, trained with a novel character-based perceptual loss. Specifically, we focus on the character-level recognizability of the super-resolved images rather than the pixel-level reconstruction. Experimental results validate the benefits of our proposed method in both quantitative and qualitative aspects. In particular, our method achieves a higher character-level recognition accuracy over the state-of-the-art image super-resolution techniques.