US 12,260,510 B2
Image processing apparatus for weight-based image transformation and operating method thereof
Dubok Park, Suwon-si (KR); Woongil Choi, Suwon-si (KR); Jaehee Kwak, Suwon-si (KR); Jaehyeon Bae, Suwon-si (KR); Youngho Oh, Suwon-si (KR); Sungho Lee, Suwon-si (KR); Seungsoo Jeong, Suwon-si (KR); and Narae Choi, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on May 24, 2022, as Appl. No. 17/752,603.
Application 17/752,603 is a continuation of application No. PCT/KR2022/007304, filed on May 23, 2022.
Claims priority of application No. 10-2021-0066492 (KR), filed on May 24, 2021.
Prior Publication US 2022/0383450 A1, Dec. 1, 2022
Int. Cl. G06T 3/40 (2024.01); G06T 3/10 (2024.01); G06T 7/11 (2017.01)
CPC G06T 3/40 (2013.01) [G06T 3/10 (2024.01); G06T 7/11 (2017.01); G06T 2207/20021 (2013.01); G06T 2207/20212 (2013.01)] 15 Claims
OG exemplary drawing
 
1. An image processing apparatus comprising:
a memory configured to store one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory to:
determine a scale weight for each pixel of original pixels in an entire original image comprising an object region and a peripheral region based on first attribute-related information about the original image, the first attribute-related information comprising pixel value for distinguishing the object region and the peripheral region in the original image;
determine an additional weight for at least one pixel of the original pixels in the peripheral region, based on the first attribute-related information and second attribute-related information about the original image, the second attribute-related information being based on an amount of a change between pixel values of adjacent pixels; and
obtain a transformed image of which a size is changed from the original image, by applying at least one of the scale weight and the additional weight to corresponding pixels of the original pixels in the original image to obtain a pixel value of a transformed pixel in the transformed image.