A powerful yet smart AI based SDK to extract meaningful information from images, from the abstract level to the fundamental level. This SDK also provides an intuitive and extendable API for different use-cases, such as object-detection, object-segmentation, automatic tagging, low-level image processing, etc.
Identify, classify and group objects in an image including its location, relative size and other object properties
Our state-of-the-art text recognition technology can translate visible words in video or image streams into searchable text. Combined with word database, this technology can help to translate and interpret subtitles, identify brands and even index name tags.
…
Classify each pixel of an image into an instance, each instance (or category) corresponding to an object or a part of the image.
Multipurpose content-based automatic tagging with a large number of category classes
Analyze and classify accurately the scene
…
Image enhancement, image relighting, intrinsic image decomposition