Image object retrieval

Abstract

Subject matter disclosed herein relates to image object recognition or retrieval.

1 .- 10 . (canceled) 
     
     
         11 . An apparatus comprising:
 a computing platform to discriminate two or more candidate interest points of an image based, at least in part, on quantization identifications (IDs) of respective neighboring points of the two or more candidate interest points.   
     
     
         12 . The apparatus of  claim 11 , wherein the computing platform to rank the two more candidate interest points based at least in part on the quantization IDs. 
     
     
         13 . The apparatus of  claim 11 , wherein the two or more candidate interest points comprise quantized image descriptors. 
     
     
         14 . The apparatus of  claim 13 , wherein the quantized image descriptors comprise speeded-up-robust-features (SURF) descriptors. 
     
     
         15 . The apparatus of  claim 11 , wherein the computing platform to identify neighboring points based, at least in part, on geometric distance from a particular candidate interest point of the two or more candidate interest points of the image. 
     
     
         16 . An apparatus comprising:
 a special purpose computing system, the special purpose computing system to:
 transform a geometric arrangement of points of an object in an image; 
 quantize groups of the points; and 
 store the quantized groups of the points in an index. 
   
     
     
         17 . The apparatus of  claim 16 , wherein the special purpose computing system to transform a geometric arrangement of points of an object in an image comprises:
 a special purpose computing system to transform a geometric arrangement of points of an object in a reference image.   
     
     
         18 . The apparatus of  claim 16 , wherein the index comprises an edge index. 
     
     
         19 . The apparatus of  claim 16 , wherein the geometric arrangement of points comprises a polygon. 
     
     
         20 . The apparatus of  claim 11 , wherein the computing platform is additionally to test a neighborhood similarity of two interest points of the two or more candidate interest points. 
     
     
         21 . The apparatus of  claim 13 , wherein the quantized image descriptors comprise Scale-Invariant Feature Transform (SIFT) descriptors. 
     
     
         22 . The apparatus of  claim 21 , wherein the quantized image descriptors comprise color SIFT descriptors. 
     
     
         23 . The apparatus of  claim 13 , wherein the quantized image descriptors comprise a histogram of oriented gradients (HoG) descriptors. 
     
     
         24 . The apparatus of  claim 13 , wherein the quantized image descriptors comprise gradient location orientation histogram (GLOH) descriptors. 
     
     
         25 . The apparatus of  claim 11 , wherein the computing platform is additionally to form a geometrical shape to enclose a portion of a sample image. 
     
     
         26 . The apparatus of  claim 25 , wherein the computing platform is received input signals from a pointing device to enclose the portion of the sample image. 
     
     
         27 . The apparatus of  claim 14 , wherein the quantized image descriptors are computed utilizing a sign of a Laplacian of a signal sampled value representing an edge signature. 
     
     
         28 . The apparatus of  claim 18 , wherein the edge index comprises local feature parameters describing quantization of neighboring point-pairs encoded in an edge signature.