DLoRA-TrOCR: Mixed Text Mode Optical Character Recognition Based On Transformer

arXiv:2404.12734v1 Announce Type: new
Abstract: With the continuous development of OCR technology and the expansion of application fields, text recognition in complex scenes has become a key challenge. Factors such as multiple fonts, mixed scenes and complex layouts seriously affect the recognition accuracy of traditional OCR models. Although OCR models based on deep learning have performed well in specific fields or similar data sets in recent years, the generalization ability and robustness of the model are still a big challenge …

abstract accuracy application arxiv become challenge character recognition continuous continuous development cs.cv development expansion fields key mixed multiple ocr optical optical character recognition recognition technology text transformer type