Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition

by   Andreas Spruck, et al.

An insufficient number of training samples is a common problem in neural network applications. While data augmentation methods require at least a minimum number of samples, we propose a novel, rendering-based pipeline for synthesizing annotated data sets. Our method does not modify existing samples but synthesizes entirely new samples. The proposed rendering-based pipeline is capable of generating and annotating synthetic and partly-real image and video data in a fully automatic procedure. Moreover, the pipeline can aid the acquisition of real data. The proposed pipeline is based on a rendering process. This process generates synthetic data. Partly-real data bring the synthetic sequences closer to reality by incorporating real cameras during the acquisition process. The benefits of the proposed data generation pipeline, especially for machine learning scenarios with limited available training data, are demonstrated by an extensive experimental validation in the context of automatic license plate recognition. The experiments demonstrate a significant reduction of the character error rate and miss rate from 73.74 14.11 data set solely. These improvements are achieved by training the algorithm on synthesized data solely. When additionally incorporating real data, the error rates can be decreased further. Thereby, the character error rate and miss rate can be reduced to 11.90 experiments as well as the proposed rendering-based pipeline for the automated data generation is made publicly available under (URL will be revealed upon publication).


page 1

page 2

page 6

page 7

page 8

page 9

page 14


3D Rendering Framework for Data Augmentation in Optical Character Recognition

In this paper, we propose a data augmentation framework for Optical Char...

Data Incubation – Synthesizing Missing Data for Handwriting Recognition

In this paper, we demonstrate how a generative model can be used to buil...

Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

In this work we present a framework for the recognition of natural scene...

Pallet Detection from Synthetic Data Using Game Engines

This research sets out to assess the viability of using game engines to ...

SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose Estimation

Animal pose estimation has become a crucial area of research, but the sc...

On Rendering Synthetic Images for Training an Object Detector

We propose a novel approach to synthesizing images that are effective fo...

Please sign up or login with your details

Forgot password? Click here to reset