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

A non-transitory computer readable medium storing instructions that, when executed by a computing device having one or more processors, causes the one or more processors to perform operations comprising:

• receiving, by a computing device, an image;
• identifying, by the computing device, multiple physical objects represented in the image based on attributes of the multiple physical objects;
• determining, by the computing device, an object type of a first object of the multiple physical objects;
• determining, by the computing device, an object type of a second object of the multiple physical objects;
• identifying, by the computing device, one or more specific regions of the first object for recognition based on the object type of the first object;
• identifying, by the computing device, one or more specific regions of the second object for recognition based on the object type of the second object;
• responsive to identifying the one or more specific regions, recognizing, by the computing device, text in the one or more specific regions of the first object;
• recognizing, by the computing device, text in the one or more specific regions of the second object;
• providing, by the computing device, the text recognized in the one or more specific regions of the first object to a security engine, the security engine configured to evaluate whether the text comprises sensitive information;
• and
• providing, by the computing device, the text in the one or more specific regions of the second object to the security engine.

A computer system comprising:

• a receiving module programmed to receive an image, at least one processor configured to execute the receiving module;
• an object identification module programmed to identify multiple physical objects represented in the image based on attributes of the multiple physical objects, the at least one processor configured to execute the object identification module, the object identification module communicatively coupled to the receiving module;
• an object analysis module programmed to determine an object type of a first object of the multiple physical objects, determine an object type of a second object of the multiple physical objects, identify one or more specific regions of the first object for recognition based on the object type of the first object, and identify one or more specific regions of the second object for recognition based on the object type of the second object, the at least one processor configured to execute the object analysis module, the object analysis module communicatively coupled to the object identification module;
• and
• a text recognition module programmed to, responsive to identifying the one or more specific regions, recognize text in the one or more specific regions of the first object, recognize text in the one or more specific regions of the second object, tag the text recognized in each specific region of the one or more specific regions of the first object with metadata based on a location of the specific region on the first object, provide the text recognized in the one or more specific regions of the first object to a security engine, and provide the text in the one or more specific regions of the second object to the security engine, the metadata indicating a data type expected to be found at the location of the specific region on an object having the object type of the first object, the security engine configured to evaluate whether the text of the first object or the second object comprises sensitive information, the at least one processor configured to execute the text recognition module, the text recognition module communicatively coupled to the object analysis module.