[논문 리뷰] License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks

Syed Zain Masood, Guang Shu외 2명|arXiv (Cornell University)|2017. 03. 21.

Vehicle License Plate Recognition인용 수 87

한 줄 요약

논문은 End-to-end 라이센스 플레이트 검출 및 인식 시스템을 순차적 딥 CNN으로 구축하여 US 및 European 벤치마크에서 OpenALPR보다 높은 정확도를 달성합니다. 지역, 자세 및 조명 변 Variation에 강인한 통합 모델을 강조합니다.

ABSTRACT

This work details Sighthounds fully automated license plate detection and recognition system. The core technology of the system is built using a sequence of deep Convolutional Neural Networks (CNNs) interlaced with accurate and efficient algorithms. The CNNs are trained and fine-tuned so that they are robust under different conditions (e.g. variations in pose, lighting, occlusion, etc.) and can work across a variety of license plate templates (e.g. sizes, backgrounds, fonts, etc). For quantitative analysis, we show that our system outperforms the leading license plate detection and recognition technology i.e. ALPR on several benchmarks. Our system is available to developers through the Sighthound Cloud API at https://www.sighthound.com/products/cloud

연구 동기 및 목표

• Develop an end-to-end pipeline for license plate detection and recognition using deep CNNs.
• Collect and annotate large-scale data for both plate detection and character recognition.
• Train specialized CNNs for plate detection, character detection, and character recognizer.
• Evaluate the system on US and European benchmarks and compare with OpenALPR.
• Demonstrate robustness to variations in plate templates and imaging conditions.

제안 방법

• Collect and prepare data for license plate detection and character recognition.
• Train three CNNs: license plate detector, character detector, and character recognizer.
• Use a multi-step segmentation process for character isolation followed by binary filtering to remove non-characters.
• Recognize characters with a 35-class classifier (0-9 and A-Z excluding O).
• Evaluate with best-sequence matching against ground truth on benchmark datasets.

실험 결과

연구 질문

• RQ1 Can a unified deep CNN-based pipeline detect and recognize license plates across different regions without plate-type priors?
• RQ2 How does the end-to-end system compare to OpenALPR in detection recall and recognition accuracy on USA and European datasets?
• RQ3 Is the pipeline robust to variations in lighting, pose, occlusion, and plate designs across regions?

주요 결과

• 라이선스 플레이트 검출 재현율(USA 99.09%, Europe 99.64% (Sighthound) vs OpenALPR variants).
• 라이선스 플레이트 인식 정확도: USA 93.44% (Sighthound) vs OpenALPR Open Source 78.36% and Cloud 84.64%; Europe 94.55% (Sighthound) vs OpenALPR Open Source 84.80% and Cloud 86.75%.
• 시스템은 미국과 유럽 벤치마크에서 높은 정확도를 제공하고 검출 및 인식 작업 모두에서 OpenALPR보다 우수합니다.
• USA vs Europe에 대한 플레이트 타입 명시가 필요 없는 통합 모델을 사용합니다.
• 조명, 크기, 흐림, 각도 및 템플릿 변화에 대한 강건성을 보여주는 정성적 결과를 제공합니다.