Unknown-Box Approximation to Improve Optical Character Recognition Performance

Randika, Ayantha; Ray, Nilanjan; Xiao, Xiao; Latimer, Allegra

doi:10.1007/978-3-030-86549-8_31

Cited by 6 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For training the proposed model, three datasets containing noisy document images -the Kaggle Denoising Dirty Documents dataset [5], the Point-of-Sale (POS) Receipts dataset [34], and the Noisy OCR Dataset (NOD) [12] are used. The Kaggle Denoising dataset comprises noisy document images with various synthetically added noise types, such as wrinkles, stains, and faded spots.…”

Section: Datasetsmentioning

confidence: 99%

Unpaired Document Image Denoising for OCR using BiLSTM enhanced CycleGAN

Singh

Tata

Oeveren

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The recognition performance of optical character recognition (OCR) models can be sub-optimal when document images suffer from various degradations. Supervised deep learning methods for image enhancement can generate high-quality enhanced images. However, these methods demand the availability of corresponding clean images or ground truth text. Sometimes this requirement is difficult to fulfill for real-world noisy documents. For instance, it can be challenging to create paired noisy/clean training datasets or obtain ground truth text for noisy point-of-sale receipts and invoices. Unsupervised methods have been explored in recent years to enhance images in the absence of ground truth images or text. However, these methods focus on enhancing natural scene images. In the case of document images, preserving the readability of text in the enhanced images is of utmost importance for improved OCR performance. In this work, we propose a modified architecture to the CycleGAN model to improve its performance in enhancing document images with better text preservation. Inspired by the success of CNN-BiLSTM combination networks in text recognition models, we propose modifying the discriminator network in the CycleGAN model to a combined CNN-BiLSTM network for better feature extraction from document images during classification by the discriminator network. Results indicate that our proposed model not only leads to better preservation of text and improved OCR performance over the CycleGAN model but also achieves better performance than the classical unsupervised image pre-processing techniques like Sauvola and Otsu.

show abstract

Section: Datasetsmentioning

confidence: 99%