License Plate Recognition Based On Multi-Angle View Model

TL;DR

This paper introduces a multi-angle view model for license plate recognition that combines features from multiple perspectives to improve text detection accuracy, demonstrating superior results on self-collected and public datasets.

Contribution

The paper proposes a novel multi-angle view approach for license plate recognition that integrates features from different viewpoints to enhance detection and recognition accuracy.

Findings

Outperforms existing methods on PTITPlates dataset

Effective in various real-world scenarios

Utilizes multiple perspectives for improved accuracy

Abstract

In the realm of research, the detection/recognition of text within images/videos captured by cameras constitutes a highly challenging problem for researchers. Despite certain advancements achieving high accuracy, current methods still require substantial improvements to be applicable in practical scenarios. Diverging from text detection in images/videos, this paper addresses the issue of text detection within license plates by amalgamating multiple frames of distinct perspectives. For each viewpoint, the proposed method extracts descriptive features characterizing the text components of the license plate, specifically corner points and area. Concretely, we present three viewpoints: view-1, view-2, and view-3, to identify the nearest neighboring components facilitating the restoration of text components from the same license plate line based on estimations of similarity levels and distance metrics. Subsequently, we employ the CnOCR method for text recognition within license plates. Experimental results on the self-collected dataset (PTITPlates), comprising pairs of images in various scenarios, and the publicly available Stanford Cars Dataset, demonstrate the superiority of the proposed method over existing approaches.