2000 character limit reached
Forensic License Plate Recognition with Compression-Informed Transformers (2207.14686v3)
Published 29 Jul 2022 in cs.CV and cs.AI
Abstract: Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., from surveillance cameras. In this work, we propose a side-informed Transformer architecture that embeds knowledge on the input compression level to improve recognition under strong compression. We show the effectiveness of Transformers for license plate recognition (LPR) on a low-quality real-world dataset. We also provide a synthetic dataset that includes strongly degraded, illegible LP images and analyze the impact of knowledge embedding on it. The network outperforms existing FLPR methods and standard state-of-the art image recognition models while requiring less parameters. For the severest degraded images, we can improve recognition by up to 8.9 percent points.
- “Learning to Decipher License Plates in Severely Degraded Images,” in Pattern Recognition. ICPR International Workshops and Challenges, 2021, pp. 544–559.
- “Deciphering Severely Degraded License Plates,” Electronic Imaging, vol. 2017, no. 7, pp. 138–143, 2017.
- “Forensic Reconstruction of Severely Degraded License Plates,” Electronic Imaging, vol. 2019, no. 5, pp. 529–1–529–7, 2019.
- “Neural Network for Denoising and Reading Degraded License Plates,” in International Conference on Pattern Recognition, 2021, pp. 484–499.
- “Sequence-Based Recognition of License Plates with Severe Out-of-Distribution Degradations,” in International Conference on Computer Analysis of Images and Patterns, 2021, pp. 175–185.
- G. K. Wallace, “The JPEG Still Picture Compression Standard,” IEEE Transactions on Consumer Electronics, vol. 38, no. 1, pp. xviii–xxxiv, 1992.
- “JPEG Quantization Step Estimation and its Applications to Digital Image Forensics,” IEEE Transactions on Information Forensics and Security, vol. 12, no. 1, pp. 123–133, 2016.
- “Attention Is All You Need,” in Advances in Neural Information Processing Systems, 2017, pp. 5998–6008.
- R. Laroca and D. Menotti, “Automatic License Plate Recognition: an Efficient and Layout-Independent System Based on the YOLO Detector,” in Anais Estendidos do XXXIII Conference on Graphics, Patterns and Images, 2020, pp. 15–21.
- “A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector,” in 2018 IEEE Jnternational Joint Conference on Neural Networks, 2018, pp. 1–10.
- “License Plate Detection and Recognition in Unconstrained Scenarios,” in Proceedings of the European Conference on Computer Vision, 2018, pp. 580–596.
- “A Robust Attentional Framework for License Plate Recognition in the Wild,” IEEE Transactions on Intelligent Transportation Systems, 2020.
- “An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and its Application to Scene Text Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 11, pp. 2298–2304, 2016.
- “CNN-RNN Based Method for License Plate Recognition,” CaaI Transactions on Intelligence Technology, vol. 3, no. 3, pp. 169–175, 2018.
- B. Suvarnam and V. Sarma Ch, “Combination of CNN-GRU Model to Recognize Characters of a License Plate Number Without Segmentation,” in 5th International Conference on Advanced Computing & Communication Systems, 2019, pp. 317–322.
- “License Plate Recognition Model Based on CNN + LSTM + CTC,” in International Conference of Pioneering Computer Scientists, Engineers and Educators, 2019, pp. 657–678.
- “Holistic Recognition of Low Quality License Plates by CNN Using Track Annotated Data,” in 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2017, pp. 1–6.
- “A Survey of the Usages of Deep Learning for Natural Language Processing,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 604–624, 2020.
- “An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale,” in International Conference on Learning Representations, 2020.
- “Transformers in Vision: A Survey,” ACM Computing Surveys, 2021.
- “Parallel Recurrent Neural Network Architectures for Feature-Rich Session-Based Recommendations,” in Proceedings of the 10th ACM Conference on Recommender Systems, 2016, pp. 241–248.
- “Integrating Keywords into BERT4Rec for Sequential Recommendation,” in German Conference on Artificial Intelligence, 2020, pp. 275–282.
- Independent JPEG Group, “Libjpeg,” accessed: 2022-01-15, http://libjpeg.sourceforge.net/.
- D. Cozzolino and L. Verdoliva, “Noiseprint: a CNN-Based Camera Model Fingerprint,” IEEE Transactions on Information Forensics and Security, vol. 15, pp. 144–159, 2019, Implementation for JPEG QF Estimation, accessed 2021-11-01: https://github.com/grip-unina/noiseprint/blob/afd0b8e7dd6c33a345ef9f09eb0b456cf0a28ee6/noiseprint/utility/utilityRead.py.
- R. J. Williams and D. Zipser, “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,” Neural Computation, vol. 1, no. 2, pp. 270–280, 1989.
- BMVBS, “Verordnung über die Zulassung von Fahrzeugen zum Straßenverkehr,” 2011.
- “3D Rendering Framework for Data Augmentation in Optical Character Recognition,” in 2021 International Symposium on Signals, Circuits and Systems, 2021, pp. 1–4.
- M. Tan and Q. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in International Conference on Machine Learning, 2019, pp. 6105–6114.
- Pytorch Vision Models, “torchvision.models — Torchvision 0.11.0 documentation,” accessed: 2021-12-02, https://pytorch.org/vision/stable/models.html.