Automatic Stacking Based on Time Proximity and Visual Similarity

Abstract

Automatic stacking based on time proximity and visual similarity is described, including a method, comprising analyzing a time proximity of a plurality of electronic images, performing a visual similarity analysis on the plurality of electronic images, and stacking the plurality of electronic images based on a result of the time proximity analysis and the visual similarity analysis.

What is claimed is: 
     
         1 . A method, comprising:
 analyzing a time proximity of a plurality of electronic images;   performing a visual similarity analysis on the plurality of electronic images; and   stacking the plurality of electronic images based on a result of the time proximity analysis and the visual similarity analysis.   
     
     
         2 . The method of  claim 1 , wherein the stacking of the plurality of electronic images further comprises automatically sorting the plurality of electronic images into stacks having images with a time proximity within a time proximity range and a visual similarity greater than or equal to a first visual similarity threshold. 
     
     
         3 . The method of  claim 2 , wherein the stacking of the plurality of electronic images further comprises automatically sorting the plurality of electronic images into stacks having electronic images with the time proximity outside the time proximity range and the visual similarity greater than a second visual similarity threshold, the second visual similarity threshold being greater than the first visual similarity threshold. 
     
     
         4 . The method of  claim 1 , wherein the analyzing of the time proximity and the performing of the visual similarity analysis are triggered by a download of images from an image capturing device. 
     
     
         5 . The method of  claim 1 , wherein the stacking of the plurality of electronic images further comprises selecting a stack representative image from one of the stacked images. 
     
     
         6 . The method of  claim 1 , wherein the selecting of the stack representative image is based on image quality. 
     
     
         7 . A computer readable memory comprising instructions that, responsive to execution by one or more processors, cause the one or more processors to perform operations comprising:
 analyzing a time proximity on a plurality of electronic images to generate a first result;   performing a visual similarity analysis on the plurality of electronic images to generate a second result; and   stacking the plurality of electronic images into at least one stack based on both the first result and the second result, the at least one stack being usable to represent a subset of the electronic images via a user interface.   
     
     
         8 . The computer readable memory of  claim 7 , wherein the operations further comprise displaying the at least one stack with an image that represents the at least one stack and which is selected from the at least one stack. 
     
     
         9 . The computer readable memory of  claim 7 , wherein the at least one stack is selectable to open the at least one stack and view the subset of the electronic images. 
     
     
         10 . The computer readable memory of  claim 7 , wherein the stacking of the plurality of electronic images further comprises dividing the plurality of electronic images into stacks having images with a first time proximity within a time proximity range and a first visual similarity greater than or equal to a first visual similarity threshold. 
     
     
         11 . The computer readable memory of  claim 10 , wherein the stacking of the plurality of electronic images further comprises dividing the plurality of electronic images into stacks having images with a second time proximity outside a time proximity range and a second visual similarity greater than or equal to a second visual similarity threshold, the second similarity threshold being stricter than the first similarity threshold. 
     
     
         12 . The computer readable memory of  claim 7 , wherein the analyzing of the time proximity and the performing of the visual similarity analysis are triggered by a download of electronic images from an image capturing device. 
     
     
         13 . A computing device comprising:
 a memory;   one or more processors configured to utilize instructions in the memory to cause the computing device to perform operations comprising:
 analyzing a time proximity of a plurality of images; 
 performing a visual similarity analysis on the plurality of images; and 
 stacking the plurality of images based on a result of the time proximity analysis and a result of the visual similarity analysis by at least using a visual similarity threshold that is selected based on the time proximity. 
   
     
     
         14 . The computing device of  claim 13 , wherein the plurality of images are stacked based on whether the result of the visual similarity analysis satisfies the visual similarity threshold. 
     
     
         15 . The computing device of  claim 13 , wherein the operations include automatically sorting the plurality of images into stacks having two or more images with an associated time proximity within a range of time and an associated visual similarity greater than or equal to the visual similarity threshold. 
     
     
         16 . The computing device of  claim 13 , wherein the visual similarity threshold is selected from a plurality of thresholds including a first visual similarity threshold and a second visual similarity threshold, wherein a first visual similarity threshold is selected based on the time proximity being within a range of time, and wherein the second visual similarity threshold is selected based on the time proximity being outside the range of time. 
     
     
         17 . The computing device of  claim 16 , wherein the second visual similarity threshold is relatively higher than the first visual similarity threshold. 
     
     
         18 . The computing device of  claim 13 , wherein stacking the plurality of images includes:
 stacking the plurality of images into one or more stacks that each include a subset of the plurality of images; and   selecting, for each stack, an image from the stack to represent the stack.   
     
     
         19 . The computing device of  claim 18 , wherein the image that is selected to represent the stack is selected based on one or more of image quality or image histogram. 
     
     
         20 . The computing device of  claim 13 , wherein the visual similarity threshold comprises a user-adjustable threshold that is adjustable via a user interface.