Methods, systems, articles of manufacture and apparatus to categorize image text

Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed to categorize image text. An example apparatus includes region detection model training circuitry to identify candidate regions in an input image that include text, and generate bounding boxes around respective ones of the identified candidate regions. The example apparatus also includes mask application circuitry to improve optical character recognition (OCR) by applying a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes, and OCR circuitry to perform OCR on the masked input image to obtain text data within the bounding boxes.

What is claimed is: 
     
         1 . An apparatus comprising:
 at least one of a central processing unit, a graphic processing unit or a digital signal processor, the at least one of the central processing unit, the graphic processing unit or the digital signal processor having control circuitry to control data movement within the processor circuitry, arithmetic and logic circuitry to perform one or more first operations corresponding to instructions, and one or more registers to store a result of the one or more first operations, the instructions in the apparatus;   a Field Programmable Gate Array (FPGA), the FPGA including logic gate circuitry, a plurality of configurable interconnections, and storage circuitry, the logic gate circuitry and interconnections to perform one or more second operations, the storage circuitry to store a result of the one or more second operations; or   Application Specific Integrate Circuitry including logic gate circuitry to perform one or more third operations;   the processor circuitry to at least one of perform at least one of the first operations, the second operations or the third operations to:   identify candidate regions in an input image that includes text;   generate bounding boxes around respective ones of the identified candidate regions;   improve optical character recognition (OCR) by applying a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes; and   perform OCR on the masked input image to obtain text data within the boundary boxes.   
     
     
         2 . The apparatus as defined in  claim 1 , wherein the input image is a banner. 
     
     
         3 . The apparatus as defined in  claim 2 , wherein the banner includes a plurality of banner images. 
     
     
         4 . The apparatus as defined in  claim 1 , wherein the processor circuitry is to classify the obtained text data. 
     
     
         5 . The apparatus as defined in  claim 1 , wherein the processor circuitry is to categorize the obtained text data based on coded images corresponding to respective ones of the candidate regions. 
     
     
         6 . The apparatus as defined in  claim 1 , wherein the processor circuitry is to distinguish banner text from product label text. 
     
     
         7 . At least one non-transitory computer readable storage medium comprising instructions that, when executed, cause at least one processor to at least:
 identify candidate regions in an input image that includes text;   generate bounding boxes around respective ones of the identified candidate regions;   improve optical character recognition (OCR) by applying a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes; and   perform OCR on the masked input image to obtain text data within the boundary boxes.   
     
     
         8 . The at least one computer readable storage medium as defined in  claim 7 , wherein the instructions, when executed, cause the at least one processor to identify the input image as a banner. 
     
     
         9 . The at least one computer readable storage medium as defined in  claim 8 , wherein the instructions, when executed, cause the at least one processor to identify a plurality of banner images in the banner. 
     
     
         10 . The at least one computer readable storage medium as defined in  claim 7 , wherein the instructions, when executed, cause the at least one processor to classify the obtained text data. 
     
     
         11 . The at least one computer readable storage medium as defined in  claim 7 , wherein the instructions, when executed, cause the at least one processor to categorize the obtained text data based on coded images corresponding to respective ones of the candidate regions. 
     
     
         12 . The at least one computer readable storage medium as defined in  claim 7 , wherein the instructions, when executed, cause the at least one processor to distinguish banner text from product label text. 
     
     
         13 . A method comprising:
 identifying, by executing an instruction with at least one processor, candidate regions in an input image that includes text;   generating, by executing an instruction with the at least one processor, bounding boxes around respective ones of the identified candidate regions;   improving optical character recognition (OCR) by applying, by executing an instruction with the at least one processor, a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes; and   performing, by executing an instruction with the at least one processor, OCR on the masked input image to obtain text data within the boundary boxes.   
     
     
         14 . The method as defined in  claim 13 , wherein the input image is a banner. 
     
     
         15 . The method as defined in  claim 14 , wherein the banner includes a plurality of banner images. 
     
     
         16 . The method as defined in  claim 13 , further including classifying the obtained text data. 
     
     
         17 . An apparatus to identify text comprising:
 region detection model training circuitry to:
 identify candidate regions in an input image that include text; and 
 generate bounding boxes around respective ones of the identified candidate regions; 
   mask application circuitry to improve optical character recognition (OCR) by applying a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes; and   OCR circuitry to perform OCR on the masked input image to obtain text data within the bounding boxes.   
     
     
         18 . The apparatus as defined in  claim 17 , further including category identification circuitry to classify the obtained text data. 
     
     
         19 . The apparatus as defined in  claim 17 , further including text classification circuitry to categorize the obtained text data based on coded images corresponding to respective ones of the candidate regions. 
     
     
         20 . The apparatus as defined in  claim 17 , wherein the region model training circuitry is to distinguish banner text from product label text.