Paquetes ML con capacidades OCR

Optimize your results and ease your work when using Document Understanding^TM by incorporating into your workflow one of the ML packages that have OCR capabilities.

UiPathDocumentOCR (local y en la nube)

This is a non-retrainable model which can be used with the UiPath Document OCR engine activity as part of the Digitize Document activity. To be used, the ML Skill must first be made public so that a URL can be copy-pasted into the UiPath® Document OCR engine activity.

Puede ejecutar UiPathDocumentOCR en la GPU o en la CPU, siendo la precisión la misma en ambos casos y las predicciones en la GPU son más rápidas que las de la CPU.

UiPathDocumentOCR requires access to the Document Understanding metering server at https://du.uipath.com/metering if the ML skill is running on an AI Center on-premises regular deployment. No internet access is needed on AI Center on-premises air-gapped deployments.

UiPathDocumentOCR_CPU (solo local)

Este paquete ML se puede implementar de la misma manera que el paquete ML de UiPathDocumentOCR, con las siguientes diferencias:

• it is optimized to run on CPU, so you should observe a 3-4x speedup when running in workflow, and 5-10x speedup when using it to import documents into Document Manager
• accuracy is slightly lower than the UiPathDocumentOCR ML Package, and it is similar to the UiPath.DocumentUnderstanding.OCR.LocalServer Studio package
• Debido a que es más rápida, la CPU también se recomienda cuando los documentos son grandes (más de 20 páginas por documento) en ausencia de una GPU, que es lo ideal.

UiPath Extended Languages OCR

UiPath Extended Languages OCR is capable of processing documents in over 200 languages, especially in Chinese, Korean, Vietnamese, Thai, major Indian languages, and languages that use the Cyrilic or Greek alphabets.

You can use the URL of this endpoint into the UiPath Extended Languages OCR activity, or directly in a Document Understanding project at configuration time.