DeepAI AI Chat
Log In Sign Up

Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models

by   Sahar Siddiqui, et al.

Scene text recognition models have advanced greatly in recent years. Inspired by human reading we characterize two important scene text recognition models by measuring their domains i.e. the range of stimulus images that they can read. The domain specifies the ability of readers to generalize to different word lengths, fonts, and amounts of occlusion. These metrics identify strengths and weaknesses of existing models. Relative to the attention-based (Attn) model, we discover that the connectionist temporal classification (CTC) model is more robust to noise and occlusion, and better at generalizing to different word lengths. Further, we show that in both models, adding noise to training images yields better generalization to occlusion. These results demonstrate the value of testing models till they break, complementing the traditional data science focus on optimizing performance.


page 2

page 6


Scene Text Recognition with Semantics

Scene Text Recognition (STR) models have achieved high performance in re...

Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

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

ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition

In recent years, scene text recognition is always regarded as a sequence...

Visual attention models for scene text recognition

In this paper we propose an approach to lexicon-free recognition of text...

Learning to Read by Spelling: Towards Unsupervised Text Recognition

This work presents a method for visual text recognition without using an...

On Pitfalls of Measuring Occlusion Robustness through Data Distortion

Over the past years, the crucial role of data has largely been shadowed ...