Digital Worker

Image
and voice recognition

Robotic Process Automation

Our digital robots can process and comprehend data in images or videos by utilizing their Computer Vision capabilities. Using Computer Vision and state-of-the-art deep learning architectures, our robots can extract meaningful information that is hidden inside images or videos.

Computer Vision Technology

Our computer vision technology includes Optical Character Recognition (OCR) for scanned documents extracting useful information, such as data from invoices. Tumors can be detected in medical images, and objects of interest – people or cars, for example - can be tracked by surveillance cameras. Equipment inspection is possible utilizing image enhancement, distortion correction, abnormal pattern recognition, camera calibration, video stabilization and Automatic License Plate Recognition (ALPR).

Lower-level computer vision techniques include edge detection, feature extraction, image segmentation, object detection, instance segmentation, and semantic segmentation, In short, robots can identify object outlines down to the pixel level and extract the most essential features previously learnt by the digital worker for processing.