ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
This competition tackles the problem of scaling training data cost-effectively for street view text reading, benefiting researchers and practitioners in computer vision, but it is incremental as it builds on existing benchmarks.
The paper introduces the ICDAR 2019 competition on Large-scale Street View Text with Partial Labeling (LSVT), which provides 50,000 fully annotated and 400,000 weakly annotated images to address the high cost of data labeling for street view text reading, aiming to improve text detection and recognition methods for real-world applications.
Robust text reading from street view images provides valuable information for various applications. Performance improvement of existing methods in such a challenging scenario heavily relies on the amount of fully annotated training data, which is costly and in-efficient to obtain. To scale up the amount of training data while keeping the labeling procedure cost-effective, this competition introduces a new challenge on Large-scale Street View Text with Partial Labeling (LSVT), providing 50, 000 and 400, 000 images in full and weak annotations, respectively. This competition aims to explore the abilities of state-of-the-art methods to detect and recognize text instances from large-scale street view images, closing the gap between research benchmarks and real applications. During the competition period, a total of 41 teams participated in the two proposed tasks with 132 valid submissions, i.e., text detection and end-to-end text spotting. This paper includes dataset descriptions, task definitions, evaluation protocols and results summaries of the ICDAR 2019-LSVT challenge.