Scoring and Adjusting Pixels Based on Neighborhood Relationships for Revealing Data in Images

Abstract

A machine/computer implemented system, method, and computer program product for scored pixel intensity value adjustment of a digital image is disclosed. The system is configured to obtain a digital image from data storage and perform pixel-by-pixel comparisons to generate per pixel scores. The types of comparisons include discovering minima and maxima per pixel scores by comparing to neighboring non-adjacent pixel pairs, delta pair scores by comparing to neighboring pixels, and multiple vector score types by comparing to vectors made up of individual pixels. This new information is applied to adjust each pixel's value. The system is further configured to generate a collection of such scores for a plurality of pixels in a digital image and to generate a multi-dimensional scored pixel adjusted image. The scored pixel adjustment yields a new digital image, wherein the value of a given pixel is adjusted based on one or more of the score types.

What is claimed is: 
     
         1 . A machine-implemented method, comprising:
 receiving a digit image having a collection of pixels each with a corresponding value;   processing each pixel as a centroid pixel surrounded by neighboring pixels;   forming at least one of the following operations for each of a plurality of centroid pixels:
 determining a minima score, 
 determining a maxima score, 
 determining a delta pair score, and 
 determining a vector score; 
   adjusting the value of each of the plurality of centroid pixels based on the performed operations to generate corresponding adjusted centroid pixel values;   generating an adjusted digital image based on the adjusted centroid pixel values; and   outputting the adjusted digital image,
 wherein the receiving, the performing, the adjusting, the generating, and the outputting are performed by one or more machines.