US 12,223,681 B2
Object oriented image normalization
Aviad Zlotnick, Mitzpeh Netofah (IL)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Feb. 1, 2023, as Appl. No. 18/162,994.
Application 18/162,994 is a continuation of application No. 17/104,630, filed on Nov. 25, 2020, granted, now 11,615,554.
Application 17/104,630 is a continuation of application No. 16/204,407, filed on Nov. 29, 2018, granted, now 10,878,596, issued on Dec. 29, 2020.
Prior Publication US 2023/0177729 A1, Jun. 8, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); G06T 7/136 (2017.01); G06T 7/90 (2017.01); G09G 5/02 (2006.01)
CPC G06T 7/90 (2017.01) [G06T 7/136 (2017.01); G09G 5/028 (2013.01); G06T 2207/10024 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer readable storage medium having computer readable instructions, that when executed by at least one computer cause the at least one computer to perform a method for reducing a first number of colors per pixel in an image, comprising instructions to:
receive the image, the image having a plurality of pixels, the plurality of pixels having a plurality of colors;
determine a final number of colors per pixel to reduce the image to, wherein the final number of colors is a number of colors less than the plurality of colors;
identify a corresponding threshold value for each of the final number of colors, such that the corresponding threshold values optimize an arithmetic combination of a separation score function applied to the plurality of pixels and the threshold values, the separation score function based on a number of transitions between pixels across a given threshold value, wherein a transition is when a pixel from one side of the given threshold value is a neighbor of a pixel from an other side of the given threshold value; and
reduce the image from the first number of colors per pixel to the final number of colors per pixel, by creating an output image where a value of each output pixel is determined based on the threshold values and the value of a corresponding input pixel.