Improving OCR using internal document redundancy
This work addresses the challenge of improving OCR accuracy for degraded historical documents, which is an incremental advancement in document processing.
The paper tackles the problem of OCR systems struggling with low-quality printed documents by proposing an unsupervised method that leverages internal document redundancy to correct OCR outputs and improve clustering, demonstrating improvements on degraded documents like Uruguayan military archives and historical European newspapers.
Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect outputs of a given OCR system and suggest better clustering. To this aim, we introduce an extended Gaussian Mixture Model (GMM) by alternating an Expectation-Maximization (EM) algorithm with an intra-cluster realignment process and normality statistical testing. We demonstrate improvements in documents with various levels of degradation, including recovered Uruguayan military archives and 17th to mid-20th century European newspapers.