Text Detection performs Optical Character Recognition (OCR) to detect visible text from frames in a video, or video segments, and returns the detected text along with information about the frame-level location and timestamp in the video for that text.
Text Detection is particularly useful for media & entertainment use cases, including, detecting and extracting cast lists at the end of shows and movies, or detecting the presence of burnt-in subtitles.
Text detection is available for the languages supported by the Cloud Vision API.
To detect visible text from a video or video segments, call the
annotate
method and specify
TEXT_DETECTION
in the features field.
For examples of requesting text detection and getting the annotated results, see Text Detection.