Image processing system, image processing method, and program
AssigneeRakuten Group, Inc.
InventorYeongnam Chae
Life of this patent
Estimating the term…
Abstract
At least one processor of an image processing system acquires a target object image including a target object. The at least one processor detects, from the target object image, a plurality of line segments located relatively on an outer side based on predetermined line segment detection processing. The at least one processor acquires, based on the plurality of line segments, information about an outline of the target object in the target object image. The at least one processor processes, based on the information, at least a part of the target object image so that the outline matches or approximates a predetermined outline.
Claims15
An image processing system, comprising at least one processor configured to:
- (step S1) acquire a target object image including a target object;
- (step S2) detect, from the target object image, a plurality of outermost line segments in a region of interest of the target object image based on predetermined line segment detection processing;
- (step S3) acquire, based on the plurality of outermost line segments, information about an outline of the target object in the target object image;
- (step S4) process, based on the information, at least a part of the target object image so that the outline matches or approximates a predetermined outline;
- wherein the at least one processor is configured to determine whether at least one of corners of the target object deduced from the information is outside the region of interest,
- wherein the at least one processor is configured to perform the processing of the at least a part of the target object image when it is not determined that the at least one of the corners is outside the region of interest and wherein the at least one processor is configured to repeat steps S1-S4 when it is determined that the at least one of the corners is outside the region of interest;
- and wherein the region of interest is a same or similar shape to the target object with an area that is a multiple of an area of the target object.
An image processing method, comprising:
- (step S1) acquiring a target object image including a target object;
- (step S2) detecting, from the target object image, a plurality of outermost line segments in a region of interest of the target object image based on predetermined line segment detection processing;
- (step S3) acquiring, based on the plurality of outermost line segments, information about an outline of the target object in the target object image;
- and
- (step S4) processing, based on the information, at least a part of the target object image so that the outline matches or approximates a predetermined outline;
- determining whether at least one of corners of the target object deduced from the information is outside the region of interest, perform the processing of the at least a part of the target object image when it is not determined that the at least one of the corners is outside the region of interest, repeat steps S1-S4 when it is determined that the at least one of the corners is outside the region of interest;
- and
- wherein the region of interest is a same or similar shape to the target object with an area that is a multiple of an area of the target object.
A non-transitory computer-readable information storage medium for storing a program for causing a computer to:
- (step S1) acquire a target object image including a target object;
- (step S2) detect, from the target object image, a plurality of outermost line segments in a region of interest of the target object image based on predetermined line segment detection processing;
- (step S3) acquire, based on the plurality of outermost line segments, information about an outline of the target object in the target object image;
- and
- (step S4) process, based on the information, at least a part of the target object image so that the outline matches or approximates a predetermined outline;
- and
- determine whether at least one of corners of the target object deduced from the information is outside the region of interest, perform the processing of the at least a part of the target object image when it is not determined that the at least one of the corners is outside the region of interest, repeat steps S1-S4 when it is determined that the at least one of the corners is outside the region of interest;
- and
- wherein the region of interest is a same or similar shape to the target object with an area that is a multiple of an area of the target object.
Dependencies are inferred from the claim text.