Text detection using global geometry estimators

A non-transitory computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

• receive an image including a plurality of pixels;
• determine, based on the image, one or more pixels of the plurality of pixels included in the image that contain text;
• identify, based on the one or more pixels that contain text, a plurality of components in the image, wherein each component of the plurality of components represents a grouping of pixels that contain text;
• determine a subset of components based on the plurality of components, wherein the subset of components includes one or more components of the plurality of components that include a predetermined minimum number of pixels that contain text;
• determine, based on the pixels that contain text of the subset of components, one or more candidate text angles, wherein each candidate text angle of the one or more candidate text angles is associated with a plurality of pixels that contain text;
• determine a global text angle based on the one or more candidate text angles;
• and
• determine a first plurality of bounding boxes based on the global text angle, wherein each bounding box of the first plurality of bounding boxes encloses a component of the plurality of components.

A method, comprising:

• receiving an image including a plurality of pixels;
• determining, based on the image, one or more pixels of the plurality of pixels included in the image that contain text;
• identifying, based on the one or more pixels that contain text, a plurality of components in the image, wherein each component of the plurality of components represents a grouping of pixels that contain text;
• determining a subset of components based on the plurality of components, wherein the subset of components includes one or more components of the plurality of components that include a predetermined minimum number of pixels that contain text;
• determining, based on the pixels that contain text of the subset of components, one or more candidate text angles, wherein each candidate text angle of the one or more candidate text angles is associated with a plurality of pixels that contain text;
• determining a global text angle based on the determined one or more candidate text angles;
• and
• determining a first plurality of bounding boxes based on the global text angle, wherein each bounding box of the first plurality of bounding boxes encloses a component of the plurality of components.

An electronic device, comprising:

• one or more processors;
• a memory;
• and
• one or more programs wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, wherein the one or more programs include instructions for:
• receiving an image including a plurality of pixels;
• determining, based on the image, one or more pixels of the plurality of pixels included in the image that contain text;
• identifying, based on the one or more pixels that contain text, a plurality of components in the image, wherein each component of the plurality of components represents a grouping of pixels that contain text;
• determining a subset of components based on the plurality of components, wherein the subset of components includes one or more components of the plurality of components that include a predetermined minimum number of pixels that contain text;
• determining, based on the pixels that contain text of the subset of components, one or more candidate text angles, wherein each candidate text angle of the one or more candidate text angles is associated with a plurality of pixels that contain text;
• determining a global text angle based on the determined one or more candidate text angles;
• and
• determining a first plurality of bounding boxes based on the global text angle, wherein each bounding box of the first plurality of bounding boxes encloses a component of the plurality of components.