TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition

• URL: http://arxiv.org/abs/2507.17335v1
• Date: Wed, 23 Jul 2025 09:03:01 GMT
• Title: TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
• Authors: Guangzhu Xu, Zhi Ke, Pengcheng Zuo, Bangjun Lei,
• Abstract summary: This paper proposes a unified solution that integrates a lightweight visual encoder with a text decoder.<n>To mitigate the scarcity of double-line license plate datasets, we constructed a single/double-line license plate dataset.<n>The proposed algorithm achieves an average recognition accuracy of 99.34% on the corrected CCPD test set under coarse localization disturbance.
• Score: 1.1499574149885023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: License plate recognition in open environments is widely applicable across various domains; however, the diversity of license plate types and imaging conditions presents significant challenges. To address the limitations encountered by CNN and CRNN-based approaches in license plate recognition, this paper proposes a unified solution that integrates a lightweight visual encoder with a text decoder, within a pre-training framework tailored for single and double-line Chinese license plates. To mitigate the scarcity of double-line license plate datasets, we constructed a single/double-line license plate dataset by synthesizing images, applying texture mapping onto real scenes, and blending them with authentic license plate images. Furthermore, to enhance the system's recognition accuracy, we introduce a perspective correction network (PTN) that employs license plate corner coordinate regression as an implicit variable, supervised by license plate view classification information. This network offers improved stability, interpretability, and low annotation costs. The proposed algorithm achieves an average recognition accuracy of 99.34% on the corrected CCPD test set under coarse localization disturbance. When evaluated under fine localization disturbance, the accuracy further improves to 99.58%. On the double-line license plate test set, it achieves an average recognition accuracy of 98.70%, with processing speeds reaching up to 167 frames per second, indicating strong practical applicability.

Related papers

• LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network [1.1499574149885023]
  We propose a lightweight, unified network named LPTR-AFLNet for correcting and recognizing Chinese license plates.<n>It combines a perspective transformation correction module (PTR) with an optimized license plate recognition network, AFLNet.<n>We demonstrate exceptional performance of LPTR-AFLNet in rectifying perspective distortion and recognizing double-line license plate images.
  arXiv  Detail & Related papers  (2025-07-22T08:54:32Z)
• Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning [69.33115351856785]
  We present a novel method, called T2I-PAL, to tackle the modality gap issue when using only text captions for PEFT.<n>The core design of T2I-PAL is to leverage pre-trained text-to-image generation models to generate photo-realistic and diverse images from text captions.<n>Extensive experiments on multiple benchmarks, including MS-COCO, VOC2007, and NUS-WIDE, show that our T2I-PAL can boost recognition performance by 3.47% in average.
  arXiv  Detail & Related papers  (2025-06-12T11:09:49Z)
• Learning for Transductive Threshold Calibration in Open-World Recognition [83.35320675679122]
  We introduce OpenGCN, a Graph Neural Network-based transductive threshold calibration method with enhanced robustness and adaptability. Experiments across open-world visual recognition benchmarks validate OpenGCN's superiority over existing posthoc calibration methods for open-world threshold calibration.
  arXiv  Detail & Related papers  (2023-05-19T23:52:48Z)
• Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration [66.33746403815283]
  We propose a scene-adaptive infrared and visible image registration. We employ homography to simulate the deformation between different planes. We propose the first ground truth available misaligned infrared and visible image dataset.
  arXiv  Detail & Related papers  (2023-04-12T06:49:56Z)
• Benchmarking Algorithms for Automatic License Plate Recognition [0.0]
  We evaluate a lightweight Convolutional Neural Network (CNN) called LPRNet for automatic License Plate Recognition (LPR) LPRNet is an end-to-end framework and demonstrated robust performance on both datasets. Once properly trained, LPRNet can be used to recognize characters from a specific region and dataset.
  arXiv  Detail & Related papers  (2022-03-27T13:21:29Z)
• End-to-End High Accuracy License Plate Recognition Based on Depthwise Separable Convolution Networks [0.0]
  We propose a novel segmentation-free framework for license plate recognition and introduce NP-ALPR dataset. The proposed network model consists of the latest deep learning methods and state-of-the-art ideas, and benefits from a novel network architecture. We evaluate the effectiveness of the proposed method on three different datasets and show a recognition accuracy of over 99% and over 70 fps.
  arXiv  Detail & Related papers  (2022-02-21T14:45:03Z)
• DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis [78.78181964748144]
  We present a novel weakly-supervised framework for classifying whole slide images (WSIs) WSIs are commonly processed by patch-wise classification with patch-level labels. With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.
  arXiv  Detail & Related papers  (2021-09-13T09:10:43Z)
• End-to-End License Plate Recognition Pipeline for Real-time Low Resource Video Based Applications [0.43012765978447565]
  We propose a novel two-stage detection pipeline paired with Vision API to provide real-time inference speed. We trained our models on an image dataset and a video dataset containing license plates in the wild. We observed reasonable detection and recognition performance with real-time processing speed (27.2 frames per second)
  arXiv  Detail & Related papers  (2021-08-18T18:31:01Z)
• Rethinking and Designing a High-performing Automatic License Plate Recognition Approach [16.66787965777127]
  We propose a novel automatic license plate recognition (ALPR) approach, termed VSNet. VSNet includes two CNNs, i.e., VertexNet for license plate detection and SCR-Net for license plate recognition, which is integrated in a resampling-based cascaded manner. Experimental results show that the proposed VSNet outperforms state-of-the-art methods by more than 50% relative improvement on error rate.
  arXiv  Detail & Related papers  (2020-11-30T16:03:57Z)
• Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning [70.84106972725917]
  The proposed solution is cost-effective and can easily replace solutions based on radiofrequency identification (RFID) The system is able to automatically reject some of the train wagons successfully counted, as they have damaged identification codes.
  arXiv  Detail & Related papers  (2020-10-30T14:56:54Z)
• A Robust Attentional Framework for License Plate Recognition in the Wild [95.7296788722492]
  We propose a robust framework for license plate recognition in the wild. It is composed of a tailored CycleGAN model for license plate image generation and an elaborate designed image-to-sequence network for plate recognition. We release a new license plate dataset, named "CLPD", with 1200 images from all 31 provinces in mainland China.
  arXiv  Detail & Related papers  (2020-06-06T17:11:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.