A Form Understanding Approach to Printed and Structured Engineering Documentation

Santos, Gabriel León de los; Silva, Vanessa T.; Dalmolin, Laura A.; Rodrigues, Ricardo; Drews, Paul; Filho, Nelson L. Duarte

doi:10.1109/sibgrapi54419.2021.00052

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second one is a private dataset [13] called ENAVAL consisting of scanned technical engineering documents related to normative, construction, and assembly processes of the naval and offshore industry. This dataset consists of 5720 pages with two types of documents, one related to a technical normative of an engineering project and the other type related to materials used during the execution of these projects.…”

Section: A Datasetmentioning

confidence: 99%

An Optical Character Recognition Post-processing Method for technical documents

Silva,

Drews Junior,

Botelho

2023

Anais Estendidos Da XXXVI Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2023)

View full text Add to dashboard Cite

Methods for correcting errors generated by Optical Character Recognition (OCR) system are being developed for a long time, with interesting results in their applications. However, these methods tend to work only on data with words that are part of an existing language and with a large semantic relationship between each word in the text. In this work, an error correction method is proposed that focuses on types of documents without these large semantic relationships inside their text. Instead, we focus on sparse text that tends to have little semantic relationship between the words found within itself. The proposed method uses machine learning to train classifiers capable of finding errors in the OCR output and run an isolated execution of the OCR system to fix the error. The final results indicate a good accuracy of 88.24% for error detection and an improvement of the character error rate (CER) of 14.2%.

show abstract

Section: A Datasetmentioning

confidence: 99%