Hi Bubblers !
With this plugin, you can detect text, words, line and positions within a MPEG-4 or MOV video, encoded using the H. 264 codec and stored in AWS S3.
This plugin returns a list of words & lines in the video. For each, the operation returns the text, a bounding box of the text, a confidence value, and the polygon coordinates in which the text is contained and the timestamp.
A word is one or more ISO basic Latin script characters that aren’t separated by spaces. It can detect up to 50 words per frame of video. Amazon Rekognition can also detect numbers and common symbols such as @, /, $, %. -, _, +, *, and #.
A line is a string of equally spaced words. A line isn’t necessarily a complete sentence. For example, a driver’s license number is detected as a line. A line ends when there is no aligned text after it. Also, a line ends when there’s a large gap between words, relative to the length of the words. Depending on the gap between words, this means that Amazon Rekognition might detect multiple lines in text that are aligned in the same direction. Periods don’t represent the end of a line. If a sentence spans multiple lines, the operation returns multiple lines.
To interact with AWS S3 and AWS SQS, it is highly recommended to use this plugin in conjunction of our AWS S3 & SQS Utilities Plugin to provide the Put, Get, and Delete a file from AWS S3, and Poll Queue from AWS SQS action.
Made with by wise:able
Discover our other Artificial Intelligence-based Plugins