Quantitative Image Analysis
AssigneeDetectsystem Lab A/S
InventorsJan LOVMAND, Lars TORP, Rasmus Bækgård HOLM
Life of this patent
Estimating the term…
Abstract
The present invention provides a method for quantitatively rating the degree of similarity of images by using orientation, resizing of the digital image, pixilation of the digital image, creation of an image string suitable for generating a hit-score. In the generation of the image string color codes e.g. by the RGB system is used. The hit-score can be a percentage identity or homology between the image strings of the two digital images, said hit-score being the rating of the similarity between the two digital images. The invention also related to the use of the method in process of assessing insurance claims. Further the invention to the use of said method and for a computer program with instruction for carrying out the method.
Claims20
A method for quantitatively rating the degree of similarity between two digital images, comprising the following steps for each of the digital images:
- check whether image width is less than image height, if image width is less than image height rotate image 90 degrees to obtain a horizontal orientated digital image,
- resize the horizontal orientated digital image to a resized digital image having a certain fixed size and number of pixels,
- pixelate the digital image to pixels of a fixed size to obtain a pixilated image with an average color of each pixelated area,
- calculate total pixel values of the pixelated image top row and calculate total pixel values of the pixelated image bottom row,
- compare the total pixel value of the top row with the total pixel value of the pixilated image bottom row, if the total pixel value of pixilated image the top row is less than the total pixel value of the pixilated image bottom row, then rotate the pixilated image 180 degrees;
- If the total pixel value of the pixilated image top row is equal to total pixel value of the pixilated image bottom row, then proceed calculating the next row from top row and compare to next row from bottom row, if the total pixel value of the next row from top are equal to the total pixel value of the next row from bottom proceed with next rows until the centre row is reached,
- calculate total pixel values of the pixelated image first column and calculate total pixel values of the pixelated image last column and compare the total pixel values;
- if the total pixel value of the pixilated image first-column is less than the total pixel value of the pixilated image last column value, then flip the pixilated image over its vertical axis;
- if the total pixel value of the pixilated image first-column value is equal to the total pixel value of the pixilated image last column value, then proceed calculating the total pixel value of the pixilated image next column from first column and compare to the total pixel value of the pixilated image next column from last column;
- if the total pixel value of the pixilated image next column from first column are equal to total pixel value of the pixilated image of the next column from last column proceed with next columns until centre column is reached,
- read a pixel from each of the pixelated area in the pixilated image and calculate closest predefined color of each of the pixels read to obtain a pixel RGB,
- convert each pixel RGB color to HEX value,
- add each pixel HEX value to an image string representing the image pixel value, and
- then calculate a hit-score as a percentage identity or homology between the image strings of the two digital images, said hit-score being the rating of the similarity between the two digital images.
A method for quantitatively rating the degree of similarity between two digital images, comprising the following steps for each of the digital images:
- resize the digital image to a digital image having a certain fixed size and number of pixels,
- divide the resized digital image into a number of sections having X rows and Y columns so that each section has the same number of pixels,
- divide each section into a number of pixels by rows and columns so that each section has the same number of pixels,
- for each pixel, determine the color code value set, e.g. RGB, and assign a score being an integer or a letter for each of the primary colors (e.g. R, G and B), then assemble these scores into a pixel string,
- for each section assemble all the pixel strings into a section string by appending the pixel strings in a fixed order through all the pixels in the section, and
- assemble all the section strings into an image string by appending the section strings in a fixed order through all the sections of said resized digital image,
- then calculate a hit-score as a percentage identity or homology between the image strings of the two digital images, said hit-score being the rating of the similarity between the two digital images.
Dependencies are inferred from the claim text.