What is a one sentence summary of your feature request?
Improve and fully support Korean OCR recognition in Netwrix Data Classification to ensure reliable and consistent classification of Korean-language documents and scanned images.
Please describe your idea in detail. What is your problem, why do you feel this idea is the best solution, etc.
We are currently testing Netwrix Data Classification in a Korean-language environment and found that Korean text recognition through OCR is not consistently supported.
We understand that Korean text itself is supported, but the OCR detection system does not currently provide reliable Korean-language recognition. As a result, Korean text contained in scanned documents or image-based PDFs may not be detected correctly in some cases.
This is a significant limitation for environments where a large amount of business information is stored as scanned documents or image-based PDFs. If Korean text cannot be reliably extracted through OCR, the classification engine may not be able to identify relevant keywords, phrases, or sensitive information contained in those documents.
We would therefore like to request improved and full Korean OCR support, including reliable recognition of Korean characters and text in scanned documents and image-based files.
We believe this enhancement would significantly improve the accuracy and usability of Data Classification for Korean customers and organizations that manage Korean-language data.
How do you currently solve the challenges you have by not having this feature?
Currently, we have to rely on documents where the text is already available in a machine-readable format.
For scanned documents or image-based PDFs where Korean OCR recognition does not work correctly, we need to manually review the documents or use separate OCR tools to extract the text before classification.
This creates additional manual work and makes it difficult to consistently classify all Korean-language documents.
We would appreciate it if Netwrix could consider improving Korean OCR support and provide information on whether this enhancement is planned and, if possible, its expected development timeline.
