Object identification and segmentation in images, photos, and video streams
Contextual Image Classification
Classification, filtering, augmentation, restoration of images using semantics of image content and domain knowledge in various industries.
Segmentation of photos into multiple homogeneous regions using similarity parameters, with applications to medicine, self-driving, robotics and other fields.
Semantic and instance object detection classification, identification and tracking in real-time video and images.
Face Detection and Recognition
Face detection and identification in photos and videos, with application to attention monitoring, emotion recognition, etc
Text extraction (OCR)
Extraction of printed and handwritten text from images and documents with mixed languages, unstructured formatting and diverse writing styles.
Image caption generation
Feature extraction and generation of human-readable text description to photos with deep natural language models.