Object Recognition System and Method Using a Search Engine Matching of Index-Mapped Training Feature Description and Input Image Signature

Abstract

The present invention discloses methods and systems for recognizing an object in an input image based on stored training images. An object recognition system the input image, computes a signature of the input image, compares the signature with one or more stored signatures and retrieves one or more matching images from the set of training images. The matching images are then displayed to the user for further action.

What is claimed is: 
     
         1 . An object recognition system using a search engine matching of index-mapped training feature description and input image signature, said system comprising:
 a processor, a non-transitory storage element coupled to the processor, encoded instructions stored in the non-transitory storage element, wherein the encoded instructions when implemented by the processor, configure the object recognition system to:
 generate a signature for an input image of an object by an image signature generation unit, whereby the signature of the input image comprises description corresponding to each of one or more feature points in the input image; 
 an index mapping unit configured to create an index mapping based on training feature descriptors and identify a matching image of the set training images by a search engine comparing the signature of the input image with the training feature descriptors using the index mapping; and 
 an option to take at least one of an action on the matching image such as performing a purchase activity, sharing with other users over an online platform or reviewing additional information associated with the matching image. 
   
     
     
         2 . The object recognition system of  claim 1 , wherein the object recognition system is a part of at least one of the group comprising a mobile phone, a computer and a server. 
     
     
         3 . The object recognition system of  claim 1  further comprising of a compactor unit configured to compact a size associated with the description of the feature point, wherein the size corresponds to memory required to store the description of the feature point. 
     
     
         4 . The object recognition system of  claim 1 , wherein the index mapping is at least one data structure of the group comprising an array, a hash table, a lookup table and k-dimensional (k-d) tree. 
     
     
         5 . The object recognition system of  claim 4 , wherein the index mapping unit is further configured to prune the k-dimensional (k-d) tree. 
     
     
         6 . The object recognition system of  claim 1 , wherein the search engine is further configured to compare the signature of the input image with the one or more training feature descriptors of the training image using spatial consistency. 
     
     
         7 . The object recognition system of  claim 6 , wherein the search engine is further configured to compute a spatial transformation between the input image and the training image. 
     
     
         8 . The object recognition system of  claim 7 , wherein the search engine is further configured to compute a matching score between the input image and the training image. 
     
     
         9 . The object recognition system of  claim 1 , wherein the data storage is further configured to cluster the set of training images into Similar Image Clusters (SICs). 
     
     
         10 . The object recognition system of  claim 1 , the input image is a frame of a video. 
     
     
         11 . The object recognition system of  claim 10 , wherein the search engine is further configured to perform a temporal verification check on the matching image. 
     
     
         12 . The object recognition of  claim 11 , wherein the matching image is sent back to a user and displayed through a user interface of an object recognition application with an action option. 
     
     
         13 . An object recognition system using a search engine matching of index-mapped training feature description and input image signature, said system comprising:
 a processor, a non-transitory storage element coupled to the processor, encoded instructions stored in the non-transitory storage element, wherein the encoded instructions when implemented by the processor, configure the object recognition system to:
 generate a signature for an input image of an object by an image signature generation unit, whereby the signature of the input image comprises description corresponding to each of one or more feature points in the input image; 
 an index mapping unit configured to create an index mapping based on training feature descriptors, wherein the index mapping is at least one data structure of the group comprising an array, a hash table, a lookup table and k-dimensional (k-d) tree; 
 identify a matching image of the set training images by a search engine, wherein the search engine is further configured to compare the signature of the input image with the one or more training feature descriptors of the training image using a spatial consistency by computing a spatial transformation between the input image and the training image; 
 compare the signature of the input image with the training feature descriptors using the index mapping and match the input image with the training image that score above a pre-defined threshold; 
 verify the match by performing a temporal verification check on the matching image; and 
 an option to take at least one of an action on the matching image such as performing a purchase activity, sharing with other users over an online platform or reviewing additional information associated with the matching image. 
   
     
     
         14 . The object recognition system of  claim 13 , wherein the object recognition system is a part of at least one of the group comprising a mobile phone, a computer and a server. 
     
     
         15 . The object recognition system of  claim 13  further comprising of a compactor unit configured to compact a size associated with the description of the feature point, wherein the size corresponds to memory required to store the description of the feature point. 
     
     
         16 . The object recognition system of  claim 13 , wherein the index mapping unit is further configured to prune the k-dimensional (k-d) tree. 
     
     
         17 . The object recognition system of  claim 13 , wherein the data storage is further configured to cluster the set of training images into Similar Image Clusters (SICs). 
     
     
         18 . The object recognition system of  claim 13 , the input image is a frame of a video. 
     
     
         19 . The object recognition of  claim 13 , wherein the matching image is sent back to a user and displayed through a user interface of an object recognition application with an action option 
     
     
         20 . A method for recognizing an object in one or more input images based on one or more training images stored in a data storage, the method comprising:
 generating a signature for an input image of the object comprising:
 detecting one or more feature points in the input image; 
 computing a description for each feature point of the one or more feature points, whereby the signature of the input image comprises description corresponding to each of the one or more feature points in the input image; and 
 identifying a matching image of a set training images by a search engine, wherein the search engine is further configured to compare the signature of the input image with one or more training feature descriptors of the training image using a spatial consistency by computing a spatial transformation between the input image and the training image; 
 comparing the signature of the input image with the training feature descriptors using the index mapping and match the input image with the training image that score above a pre-defined threshold; 
 verifying the match by performing a temporal verification check on the matching image; and 
 taking at least one of an action on the matching image such as performing a purchase activity, sharing with other users over an online platform or reviewing additional information associated with the matching image. 
   
     
     
         21 . The method of  claim 20 , wherein the index mapping is at least one data structure of the group comprising an array, a hash table, a lookup table and k-dimensional (k-d) tree. 
     
     
         22 . The method of  claim 20  further comprising pruning the k-dimensional (k-d) tree. 
     
     
         23 . The method of  claim 20  further comprising clustering the set of training images into Similar Image Clusters (SICs). 
     
     
         24 . The method of  claim 20 , wherein the input image is a frame of a video. 
     
     
         25 . The method of  claim 20 , wherein the matching image is sent back to a user and displayed through a user interface of an object recognition application with an action option