Image processing method, apparatus, device, and medium

By combining the generated object feature vectors and category encoding vectors, the problem of insufficient recognition of diverse objects in existing image segmentation models is solved, achieving higher accuracy and flexibility.

CN120807922BActive Publication Date: 2026-08-25SHUXING TECH (BEIJING) CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510894579.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-03-17
Publication Date
2026-08-25
Estimated Expiration
2043-03-17

AI Technical Summary

Technical Problem

Existing image segmentation models can only segment objects that have learned corresponding image features, resulting in low accuracy in object segmentation and an inability to effectively identify diverse image objects.

Method used

By acquiring the image feature vector and object query vector of the target image, an object feature vector is generated. Combined with the category encoding vector of the object category set, the object category to which the target object belongs is determined, thus achieving decoupled recognition of object location and category.

Benefits of technology

It improves the accuracy and flexibility of object segmentation in images, enabling the identification of multiple object categories and enhancing the robustness and usability of image segmentation models.

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

Abstract

Embodiments of the present application disclose an image processing method, device and equipment and medium, which are applied to the technical field of image processing. The method comprises: obtaining a target image containing a target object, an image feature vector and an object query vector; generating an object feature vector based on the object query vector and the image feature vector; obtaining a class code vector corresponding to each object class in an object class set; determining the similarity between the object feature vector and the class code vector corresponding to each object class, so as to determine the belonging object class of the target object from the object class set. The embodiments of the present application can improve the accuracy of object segmentation in an image.
Need to check novelty before this filing date? Find Prior Art