Methods and systems for performing real time digital content concealment are described herein. A computing device may, in response to detecting a user within view of an image capture device of a client device, perform a first type of text recognition on a first region of digital content and a second type of text recognition on a second region of the digital content, where the first type of text recognition is determined based on a first type of content items contained in the first region and the second type of text recognition is determined based on a second type of content items contained in the second region. Based at least in part on rules corresponding to the user, the computing device may determine content items within the digital content to be concealed, and may modify the digital content to conceal the content items.