1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit

TL;DR

This paper introduces a comprehensive approach for text spotting and aesthetic assessment on integrated circuits, achieving top performance through advanced detection, classification, semi-supervised learning, and optimized deployment.

Contribution

The paper presents a novel end-to-end system combining character detection, classification, semi-supervised learning, and deployment optimization for circuit text analysis.

Findings

Achieved 59.1 mAP on text spotting with 31 FPS.

Achieved 78.7% F2 score on aesthetic assessment with 30 FPS.

Ranked 1st in both tasks at ICDAR 2021 RRC-ICTEXT challenge.

Abstract

This paper presents our proposed methods to ICDAR 2021 Robust Reading Challenge - Integrated Circuit Text Spotting and Aesthetic Assessment (ICDAR RRC-ICTEXT 2021). For the text spotting task, we detect the characters on integrated circuit and classify them based on yolov5 detection model. We balance the lowercase and non-lowercase by using SynthText, generated data and data sampler. We adopt semi-supervised algorithm and distillation to furtherly improve the model's accuracy. For the aesthetic assessment task, we add a classification branch of 3 classes to differentiate the aesthetic classes of each character. Finally, we make model deployment to accelerate inference speed and reduce memory consumption based on NVIDIA Tensorrt. Our methods achieve 59.1 mAP on task 3.1 with 31 FPS and 306M memory (rank 1), 78.7\% F2 score on task 3.2 with 30 FPS and 306M memory (rank 1).