Open Access

ARTICLE

YOLOv5ST: A Lightweight and Fast Scene Text Detector

Yiwei Liu¹, Yingnan Zhao^1,*, Yi Chen¹, Zheng Hu¹, Min Xia²

1 School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2 School of Automation, Nanjing University of Information Science and Technology, Nanjing, 210044, China

* Corresponding Author: Yingnan Zhao. Email:

(This article belongs to the Special Issue: Deep Learning based Object Detection and Tracking in Videos)

Computers, Materials & Continua 2024, 79(1), 909-926. https://doi.org/10.32604/cmc.2024.047901

Received 21 November 2023; Accepted 20 February 2024; Issue published 25 April 2024

Abstract

Scene text detection is an important task in computer vision. In this paper, we present YOLOv5 Scene Text (YOLOv5ST), an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection. Our primary goal is to enhance inference speed without sacrificing significant detection accuracy, thereby enabling robust performance on resource-constrained devices like drones, closed-circuit television cameras, and other embedded systems. To achieve this, we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation, including replacing standard convolution with depth-wise convolution, adopting the C2 sequence module in place of C3, employing Spatial Pyramid Pooling Global (SPPG) instead of Spatial Pyramid Pooling Fast (SPPF) and integrating Bi-directional Feature Pyramid Network (BiFPN) into the neck. Experimental results demonstrate a remarkable 26% improvement in inference speed compared to the baseline, with only marginal reductions of 1.6% and 4.2% in mean average precision (mAP) at the intersection over union (IoU) thresholds of 0.5 and 0.5:0.95, respectively. Our work represents a significant advancement in scene text detection, striking a balance between speed and accuracy, making it well-suited for performance-constrained environments.

---

Keywords

---