On-Device Language Identification of Text in Images using Diacritic Characters

TL;DR

This paper presents a method for on-device language identification from images using diacritic characters, enhancing OCR accuracy for Latin languages while considering mobile constraints.

Contribution

The work introduces a lightweight on-device approach for language detection based on diacritics, improving OCR performance across 13 Latin languages.

Findings

Achieved high accuracy in language identification using diacritics.

Improved OCR results when integrating language detection.

Designed a model suitable for mobile devices with low latency.

Abstract

Diacritic characters can be considered as a unique set of characters providing us with adequate and significant clue in identifying a given language with considerably high accuracy. Diacritics, though associated with phonetics often serve as a distinguishing feature for many languages especially the ones with a Latin script. In this proposed work, we aim to identify language of text in images using the presence of diacritic characters in order to improve Optical Character Recognition (OCR) performance in any given automated environment. We showcase our work across 13 Latin languages encompassing 85 diacritic characters. We use an architecture similar to Squeezedet for object detection of diacritic characters followed by a shallow network to finally identify the language. OCR systems when accompanied with identified language parameter tends to produce better results than sole deployment of OCR systems. The discussed work apart from guaranteeing an improvement in OCR results also takes on-device (mobile phone) constraints into consideration in terms of model size and inference time.