US 12,141,938 B2
Image processing system, image processing method, and program
Yeongnam Chae, Tokyo (JP)
Assigned to RAKUTEN GROUP, INC., Tokyo (JP)
Appl. No. 17/055,999
Filed by RAKUTEN GROUP, INC., Tokyo (JP)
PCT Filed Jul. 6, 2018, PCT No. PCT/JP2018/025719
§ 371(c)(1), (2) Date Nov. 17, 2020,
PCT Pub. No. WO2020/008628, PCT Pub. Date Jan. 9, 2020.
Prior Publication US 2021/0209393 A1, Jul. 8, 2021
Int. Cl. G06K 9/34 (2006.01); G06T 3/18 (2024.01); G06V 10/24 (2022.01); G06V 10/44 (2022.01); G06V 30/14 (2022.01); G06V 30/146 (2022.01); G06V 30/18 (2022.01); G06V 30/414 (2022.01); G06V 30/418 (2022.01); G06V 30/10 (2022.01); G06V 30/16 (2022.01)
CPC G06T 3/18 (2024.01) [G06V 10/24 (2022.01); G06V 10/245 (2022.01); G06V 10/44 (2022.01); G06V 30/1448 (2022.01); G06V 30/1463 (2022.01); G06V 30/1475 (2022.01); G06V 30/18143 (2022.01); G06V 30/414 (2022.01); G06V 30/418 (2022.01); G06V 30/10 (2022.01); G06V 30/1607 (2022.01)] 18 Claims
OG exemplary drawing
 
1. An image processing system comprising at least one processor configured to:
obtain a captured image of a document that includes a fixed part and an un-fixed part, the document being captured by an image reader or an image capture device;
detect a plurality of first feature points of the captured image;
obtain a plurality of second feature points of a sample image;
shape the captured image based on the first feature points and the second feature points so as to obtain a first shaped image;
detect third feature parts of the fixed part from the first shaped image by executing template matching in the first shaped image by detecting feature parts in the first shaped image based on a plurality of locations of fourth feature parts;
shape the first shaped image such that positions of the third feature parts are aligned with corresponding predetermined positions so as to obtain a second shaped image;
wherein the fourth feature parts indicate feature parts of the fixed part of the sample image;
wherein the system detects the third feature parts by scanning a window having a same size as one of the fourth feature parts and detects the third feature part based on a pixel value of each pixel in the window and a pixel value of each pixel in the fourth feature parts;
wherein the image processing system executes the template matching to four areas of the first shaped image and detects the third feature parts from the four areas, the four areas being a lower right area, an upper left area, an upper right area, and a lower left area of the document in the first shaped image; and
wherein the image processing system shapes the first shaped image such that the positions of the third feature parts of the four areas are aligned with the corresponding predetermined positions so as to obtain a second shaped image.