Structured text and pattern matching for data loss prevention in object-specific image domains

摘要

Structured text and pattern matching can be performed to prevent data loss in the object-specific image domain. According to some embodiments, a method comprises receiving, by a computing device, an image; identifying one or more objects in the image based on attributes of the one or more objects; Determining the object type of a first object of the above objects. The method includes identifying, by a computing device, one or more specific regions of the first object for recognition based on an object type of the first object; Recognizing text in the region. In some embodiments, the method may then include, by the computing device, providing text recognized within the one or more specific areas of the first object to a security engine. May be configured to evaluate whether the text contains sensitive information.