Methods and apparatus for identifying objects depicted in a video using extracted video frames in combination with a reverse image search engine

Abstract

Example systems are to capture screenshots corresponding respectively to search results pages returned from a reverse image search engine, the search results pages corresponding respectively to image frames of a video processed by the reverse image search engine, generate base query records corresponding respectively to ones of the screenshots that have respective textual information matching a base search term, the respective ones of the base query records including the base search term and at least portions of the respective textual information from the corresponding screenshots, determine an object search term based on a frequency analysis of the textual information included in the base query records, generate object query records corresponding respectively to ones of the base query records that have respective textual information matching the object search term, and identify an object depicted in the video based on one or more criteria applied to the object query records.

What is claimed is: 
     
         1 . A system to identify objects depicted in videos, the system comprising:
 memory;   computer readable instructions; and   processor circuitry to execute the computer readable instructions to:
 capture a plurality of screenshots corresponding respectively to a plurality of search results pages returned from a reverse image search engine, the plurality of search results pages corresponding respectively to a plurality of image frames of a first video processed by the reverse image search engine; 
 generate a plurality of base query records corresponding respectively to ones of the screenshots that have respective textual information that matches a base search term, the respective ones of the base query records including the base search term and at least portions of the respective textual information from the corresponding screenshots; 
 determine an object search term based on a frequency analysis of the textual information included in the base query records, the frequency analysis to ignore the base search term; 
 generate a plurality of object query records corresponding respectively to ones of the base query records that have respective textual information that matches the object search term; and 
 identify a first object depicted in the first video based on one or more criteria applied to the object query records. 
   
     
     
         2 . The system as defined in  claim 1 , wherein the respective ones of the image frames are accessible from an image repository based on resource locators associated with the image frames. 
     
     
         3 . The system as defined in  claim 1 , wherein the frequency analysis includes at least one of a word count analysis, a phrase count analysis, or a string comparison analysis. 
     
     
         4 . The system as defined in  claim 1 , wherein the base search term is associated with at least one of a word or a phrase included in at least some of the plurality of the search results pages returned by the reverse image search engine. 
     
     
         5 . The system as defined in  claim 1 , wherein the base search term is associated with at least one of a position or a threshold relative to a configuration of a layout associated with the plurality of the search results pages returned by the reverse image search engine. 
     
     
         6 . The system as defined in  claim 1 , wherein the portions of the respective textual information from the corresponding screenshots at least one of follow the base search term in the corresponding screenshots, are on a same line as the base search term in the corresponding screenshots, or are part of a same string as the base search term in the corresponding screenshots. 
     
     
         7 . The system as defined in  claim 1 , wherein the one or more criteria include a threshold based on a first number of the object query records including the object search term. 
     
     
         8 . The system as defined in  claim 1 , wherein the one or more criteria include a threshold based on a first number of the object query records including the object search term within a first time period, the first time period based on a sampling rate at which the image frames were obtained from the first video. 
     
     
         9 . The system as defined in  claim 1 , wherein the one or more criteria include a threshold based on a first consecutive number of the object query records including the object search term. 
     
     
         10 . The system as defined in  claim 1 , wherein the one or more criteria include a threshold based on a first percentage of a number of object query records including the object search term relative to a number of base query records including the base search term. 
     
     
         11 . At least one non-transitory computer readable medium comprising computer readable instructions that, when executed, cause one or more processors to at least:
 capture a plurality of screenshots corresponding respectively to a plurality of search results pages returned from a reverse image search engine, the plurality of search results pages corresponding respectively to a plurality of image frames of a first video processed by the reverse image search engine;   generate a plurality of base query records corresponding respectively to ones of the screenshots that have respective textual information that matches a base search term, the respective ones of the base query records including the base search term and at least portions of the respective textual information from the corresponding screenshots;   determine an object search term based on a frequency analysis of the textual information included in the base query records, the frequency analysis to ignore the base search term;   generate a plurality of object query records corresponding respectively to ones of the base query records that have respective textual information that matches the object search term; and   identify a first object depicted in the first video based on one or more criteria applied to the object query records.   
     
     
         12 . The at least one non-transitory computer readable medium as defined in  claim 11 , wherein the frequency analysis includes at least one of a word count analysis, a phrase count analysis, or a string comparison analysis. 
     
     
         13 . The at least one non-transitory computer readable medium as defined in  claim 11 , wherein the base search term is associated with at least one of a word or a phrase included in at least some of the plurality of the search results pages returned by the reverse image search engine. 
     
     
         14 . The at least one non-transitory computer readable medium as defined in  claim 11 , wherein the base search term is associated with at least one of a position or a threshold relative to a configuration of a layout included in the respective ones of the search results pages returned by the reverse image search engine. 
     
     
         15 . The at least one non-transitory computer readable medium as defined in  claim 11 , wherein the portions of the respective textual information from the corresponding screenshots at least one of follow the base search term in the corresponding screenshots, are on a same line as the base search term in the corresponding screenshots, or are part of a same string as the base search term in the corresponding screenshots. 
     
     
         16 . An apparatus to identify objects depicted in videos, the apparatus comprising:
 means for capturing a plurality of screenshots corresponding respectively to a plurality of search results pages returned from a reverse image search engine, the plurality of search results pages corresponding respectively to a plurality of image frames of a first video processed by the reverse image search engine;   means for generating a plurality of base query records corresponding respectively to ones of the screenshots that have respective textual information that matches a base search term, the respective ones of the base query records including the base search term and at least portions of the respective textual information from the corresponding screenshots;   means for determining an object search term based on a frequency analysis of the textual information included in the base query records, the frequency analysis to ignore the base search term;   means for generating a plurality of object query records corresponding respectively to ones of the base query records that have respective textual information that matches the object search term; and   means for identifying a first object depicted in the first video based on one or more criteria applied to the object query records.   
     
     
         17 . The apparatus as defined in  claim 16 , wherein the frequency analysis includes at least one of a word count analysis, a phrase count analysis, or a string comparison analysis. 
     
     
         18 . The apparatus as defined in  claim 16 , wherein the base search term is associated with at least one of a word or a phrase included in at least some of the plurality of the search results pages returned by the reverse image search engine. 
     
     
         19 . The apparatus as defined in  claim 16 , wherein the base search term is associated with at least one of a position or a threshold relative to a configuration of a layout associated with the plurality of the search results pages returned by the reverse image search engine. 
     
     
         20 . The apparatus as defined in  claim 16 , wherein the portions of the respective textual information from the corresponding screenshots at least one of follow the base search term in the corresponding screenshots, are on a same line as the base search term in the corresponding screenshots, or are part of a same string as the base search term in the corresponding screenshots.