Optical character recognition (OCR) is a technique that locates letters in images, photographs, scanned documents, etc., and converts them into textual data.
Deep learning-based OCR technology allows you to extract characters from unstructured data such as an image and store them as textual data. Digitize hard-to-manage data in printed documents, enabling accurate and rapid data collection, retrieval and utilization.
|Data||Data type||Contents||Use mode|
|Input data||MP4, JPG, PNG, etc.||Image or video data||API|
|Output data||CSV, JSON||Text information
(Coordinates, text strings, labeling images)
||Attached file upon application
|API Setting||$1,800 ~|
|API Predicting||$0.02 / Image|