Photographing posture recommendation method fusing image content and feature extraction

Abstract

The invention discloses a photographing posture recommendation method fusing image content and geometric feature extraction. The method comprises the steps that scene semantic features, scene features and view angle features are extracted from an image input by a user; fusing the extracted scene semantic features, scene features and view angle features according to a set rule; and calculating the similarity between the fused features and the features in the feature database, and returning the posture pictures corresponding to m features with the highest similarity to the user. According to the method, posture preferences of users with different body types, skin colors, genders and ages can be met, and scene category information, texture information and view angle information are introduced in the feature extraction step, so that posture photos with similar scenes in a posture picture library can be retrieved more accurately; semantic information and a strong label system are introduced, so that an object which can be interactively photographed by a user in a picture can be identified more intelligently, and the instantaneity requirement of the user on posture recommendation can be met.

Description

technical field [0001] The invention belongs to the fields of deep learning and image retrieval, and in particular relates to a method for recommending photographing poses that integrates image content and geometric feature extraction. Background technique [0002] At present, the camera function of smartphones is developing rapidly, and its camera pixels and image quality are getting higher and higher. Many smartphones are even capable of taking pictures that are comparable to professional cameras. In this context, coupled with the convenience of mobile phones, people are more willing to use mobile phones to complete personal photography. Whether professionals or hobbyists, digital photography is fun for many people. It is estimated that more than 1 billion photos are taken by smartphones every year. People on social networks often share their photos with friends. The ever-increasing computing power of smartphones and their ability to connect to more powerful computing ...

AI Technical Summary

Problems solved by technology

[0006] None of the above technologies mine the semantic information, scene category information and texture information in the scene.

Images