Self-paced learning to improve text row detection in historical documents with missing labels

01/28/2022
by   Mihaela Gaman, et al.
0

An important preliminary step of optical character recognition systems is the detection of text rows. To address this task in the context of historical data with missing labels, we propose a self-paced learning algorithm capable of improving the row detection performance. We conjecture that pages with more ground-truth bounding boxes are less likely to have missing annotations. Based on this hypothesis, we sort the training examples in descending order with respect to the number of ground-truth bounding boxes, and organize them into k batches. Using our self-paced learning method, we train a row detector over k iterations, progressively adding batches with less ground-truth annotations. At each iteration, we combine the ground-truth bounding boxes with pseudo-bounding boxes (bounding boxes predicted by the model itself) using non-maximum suppression, and we include the resulting annotations at the next training iteration. We demonstrate that our self-paced learning strategy brings significant performance gains on two data sets of historical documents, improving the average precision of YOLOv4 with more than 12 and 39

READ FULL TEXT

page 2

page 4

research
07/17/2022

Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection

Exploiting pseudo labels (e.g., categories and bounding boxes) of unanno...
research
12/25/2019

DDI-100: Dataset for Text Detection and Recognition

Nowadays document analysis and recognition remain challenging tasks. How...
research
06/15/2022

LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

The popular object detection metric 3D Average Precision (3D AP) relies ...
research
06/27/2022

Learning with Weak Annotations for Robust Maritime Obstacle Detection

Robust maritime obstacle detection is crucial for safe navigation of aut...
research
09/10/2020

OCR Graph Features for Manipulation Detection in Documents

Detecting manipulations in digital documents is becoming increasingly im...
research
08/09/2017

Extreme clicking for efficient object annotation

Manually annotating object bounding boxes is central to building compute...
research
07/06/2022

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation

The inherent ambiguity in ground-truth annotations of 3D bounding boxes ...

Please sign up or login with your details

Forgot password? Click here to reset