Image retrieval method and system based on large model

By extracting textual and visual features from images using a multimodal large model and repartitioning the index structure using an automatic edge-cutting set optimizer, the efficiency and accuracy issues of image retrieval methods under large-scale data are solved, achieving more efficient and accurate retrieval results.

CN121479007APending Publication Date: 2026-02-06AIKESHENG INFORMATION TECH SHANGHAI
6 Cites 0 Cited by

Patent Information

Application Number
CN202610018213.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-08
Publication Date
2026-02-06

AI Technical Summary

Technical Problem

Existing image retrieval methods incur high computational and storage costs with large-scale data, are prone to missegmentation during image partitioning, leading to decreased retrieval efficiency and accuracy, and fail to fully utilize the textual information in images, further reducing retrieval accuracy.

Method used

By leveraging a multimodal large model to extract textual information and visual features from images, a similarity fusion of visual and textual features is constructed. The initial edge cut set is re-partitioned using an automatic edge cut set optimizer to construct a retrieval graph driven by both semantic and visual features, thereby optimizing the index structure.

Benefits of technology

While maintaining retrieval efficiency, it improves retrieval accuracy, with recall and queries per second outperforming existing methods.

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

Abstract

The invention provides an image retrieval method and system based on a large model. The method comprises the following steps: extracting text information of an original picture; converting the original picture into a visual feature vector, and converting the text information into a character feature vector; respectively calculating the similarity of the two feature vectors in each set to obtain a visual feature fusion similarity and a character feature fusion similarity; determining similarity measurement of visual feature and character feature fusion; constructing data corresponding to the original picture into an initial picture structure; allocating a weight for each edge of the initial graph structure by using the metric to obtain a simplified coarsened graph structure; performing hierarchical segmentation on the coarsened image structure to obtain a plurality of initial cut edge sets; training the automatic edge cutting set optimizer by using the training data; re-dividing the initial cut edge set by using the trained automatic cut edge set optimizer; and taking the nearest partition as a retrieval result. According to the method, the retrieval accuracy can be improved while the retrieval efficiency is ensured.
Need to check novelty before this filing date? Find Prior Art