Image cutting method and device, electronic equipment, storage medium and program product

By identifying the subject object and safe area in the target image, determining the cropping box using its center and cropping ratio, and cropping the image, the problems of image cropping inadequacy and low quality in the prior art are solved, and a higher quality image cropping effect is achieved.

CN119648720APending Publication Date: 2025-03-18BEIJING QIYI CENTURY SCI & TECH CO LTD
0 Cites 2 Cited by

Patent Information

Application Number
CN202411704205.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-26
Publication Date
2025-03-18

AI Technical Summary

Technical Problem

The existing image cropping methods are single and poorly adaptable, which can easily lead to inappropriate cropping, causing the main part of the image to be wrongly cropped or segmented, especially in portrait photos, which may lead to the critical parts of the face or body being accidentally cut off, significantly reducing the user's aesthetic needs and experience.

Method used

By obtaining the target image and target image parameters, determine the subject object in the image and its object type, determine the safe area based on the object type, determine the target crop box using the center of the security area and the target crop ratio, and crop the image based on the box to ensure that the cropped image contains the key parts of the subject object.

Benefits of technology

Adaptive cropping is achieved based on the subject objects in the image, improving the image cropping quality, enhancing the user experience, and ensuring that the cropped image contains key parts.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to an image cutting method and device, electronic equipment, a storage medium and a program product, adaptive cutting can be performed based on a main body object in an image, and the image cutting quality is improved. The method comprises the following steps: acquiring a target image and a target image parameter, wherein the target image parameter is used for indicating a target cutting proportion; determining a main body object in the target image and a target object type to which the main body object belongs; based on the target object type, determining a safety area in the target image, the safety area including a key part of the main object; based on the centroid of the safety area and a target cutting ratio, determining a target cutting frame, the target cutting frame including the safety area, the length-width ratio of the target cutting frame being the target cutting ratio, and each edge of the target cutting frame being in the target image; and cutting the target image based on the target cutting frame to obtain a first cut image.
Need to check novelty before this filing date? Find Prior Art