System and method for identifying feature of interest in hyperspectral data

Abstract

A system and method for identifying objects of interest in image data is provided. The present invention utilizes principles of Iterative Transformational Divergence in which objects in images, when subjected to special transformations, will exhibit radically different responses based on the physical, chemical, or numerical properties of the object or its representation (such as images), combined with machine learning capabilities. Using the system and methods of the present invention, certain objects that appear indistinguishable from other objects to the eye or computer recognition systems, or are otherwise almost identical, generate radically different and statistically significant differences in the image describers (metrics) that can be easily measured.

1 . A method of identifying a feature of interest in hyperspectral data, comprising: 
 receiving the hyperspectral data; and    applying at least one divergence transform to the hyperspectral data to effect divergence of the feature of interest from other features.    
   
   
       2 . The method of  claim 1 , wherein the at least one divergence transform comprises a series of divergence transforms.  
   
   
       3 . The method of  claim 1 , wherein the at least one divergence transform comprises at least one point operation.  
   
   
       4 . The method of  claim 5 , wherein the at least one point operation comprises at least one nodal point that is adjusted so as to effect the divergence of the feature of interest from other features.  
   
   
       5 . The method of  claim 1 , further comprising generating an output image containing the feature of interest.  
   
   
       6 . The method of  claim 5 , wherein the feature of interest is distinguished from other features in the output image by adjusting a visual parameter of the feature of interest and other features based on the results of the at least one divergence transform.  
   
   
       7 . The method of  claim 6 , wherein the visual parameter comprises color.  
   
   
       8 . The method of  claim 6 , wherein the visual parameter comprises luminance.  
   
   
       9 . The method of  claim 1 , wherein the hyperspectral data comprises nonparametric hyperspectral data.  
   
   
       10 . The method of  claim 1 , wherein the hyperspectral data comprises two-dimensional hyperspectral data.  
   
   
       11 . The method of  claim 1 , wherein the hyperspectral data comprises three-dimensional hyperspectral data.  
   
   
       12 . The method of  claim 1 , wherein the hyperspectral data comprises x-ray hyperspectral data.  
   
   
       13 . A method of identifying a feature of interest in hyperspectral data, comprising: 
 receiving the hyperspectral data;    segmenting the hyperspectral data to identify feature candidates;    applying at least one divergence transform to original image pixels that correspond to the feature candidates to effect divergence of the feature of interest from other features; and    identifying the feature of interest based on its response to the at least one divergence transform.    
   
   
       14 . The method of  claim 13 , wherein the hyperspectral data is segmented based on color, density and/or atomic weight characteristics.  
   
   
       15 . The method of  claim 13 , wherein the at least one divergence transform comprises at least one point operation.  
   
   
       16 . The method of  claim 15 , wherein the at least one point operation comprises at least one nodal point that is adjusted so as to effect the divergence of the feature of interest from other features.  
   
   
       17 . A system for identifying a feature of interest in hyperspectral data, comprising: 
 an input device for receiving the hyperspectral data;    an image analysis system for applying at least one divergence transform to the received hyperspectral data to yield transformed hyperspectral data in which the feature of interest diverges from other features; and    a display for displaying an output image from the transformed hyperspectral data.    
   
   
       18 . The system of  claim 17 , wherein the at least one divergence transform comprises at least one point operation.  
   
   
       19 . The system of  claim 18 , wherein the at least one point operation comprises at least one nodal point that is positioned so as to effect the divergence of the feature of interest from other features in the transformed hyperspectral data.  
   
   
       20 . A method of identifying a feature of interest in hyperspectral data, comprising: 
 receiving the hyperspectral data; and    applying a series of divergence transforms to the hyperspectral data to effect divergence of the feature of interest from other features.    
   
   
       21 . The method of  claim 20 , wherein each divergence transform in the series of divergence transforms comprises at least one point operation.  
   
   
       22 . The method of  claim 21 , wherein the at least one point operation comprises at least one nodal point that is adjusted so as to effect the divergence of the feature of interest from other features.  
   
   
       23 . A system for identifying a feature of interest in hyperspectral data, comprising: 
 an input device for receiving the hyperspectral data;    an image analysis system for applying a series of divergence transforms to the received hyperspectral data to yield transformed hyperspectral data in which the feature of interest diverges from other features; and    a display for displaying an output image from the transformed hyperspectral data.    
   
   
       24 . The system of  claim 23 , wherein each bifurcation transform in the series of bifurcation transforms comprises at least one point operation.  
   
   
       25 . The system of  claim 24 , wherein the at least one point operation comprises at least one nodal point that is adjusted so as to effect the divergence of the feature of interest from other features.