General description

Vision is a face, object, process recognition technology based on machine learning and artificial neural networks. Vision will automate and improve the accuracy of complex visual inspections of varying complexity.

• 98% accuracy of face detection among a million.
• TensorRT on inference, <10ms on photo on GPU.
• 314 scene recognition classes, 25,000 object classes.

Vision technologies are available through APIs that are constantly being expanded. A list of them is available in this help center. Using the API, you can solve such cases as:

• Recognition of persons;
• Determination of scenes and objects;
• Classification of documents;
• Recognition of the fields of documents;
• Распознавание знаменитостей;
• Text recognition on images;
• Detection of cars and their numbers;
• Determination of car numbers;
• Increased resolution;
• Identification of defects in production.