Next integrated result modelling for stopping the text field recognition process in a video using a result model with per-character alternatives

TL;DR

This paper introduces an advanced stopping method for video text recognition that models next integrated recognition results with per-character alternatives, improving accuracy over previous clustering-based methods.

Contribution

It extends the next integrated result modelling approach to handle string recognition with per-character alternatives, demonstrating superior accuracy in stopping decisions.

Findings

Achieves higher accuracy than previous clustering-based methods.

Effective in determining optimal stopping time for recognition.

Validated on the MIDV-500 dataset.

Abstract

In the field of document analysis and recognition using mobile devices for capturing, and the field of object recognition in a video stream, an important problem is determining the time when the capturing process should be stopped. Efficient stopping influences not only the total time spent for performing recognition and data entry, but the expected accuracy of the result as well. This paper is directed on extending the stopping method based on next integrated recognition result modelling, in order for it to be used within a string result recognition model with per-character alternatives. The stopping method and notes on its extension are described, and experimental evaluation is performed on an open dataset MIDV-500. The method was compares with previously published methods based on input observations clustering. The obtained results indicate that the stopping method based on the next integrated result modelling allows to achieve higher accuracy, even when compared with the best achievable configuration of the competing methods.