A mobile visual retrieval method for digital humanities

Abstract

The invention discloses a digital humanities-oriented mobile visual retrieval method, comprising: first constructing an image semantic extraction model based on deep hash; initializing parameters of each processing layer of the model through pre-training; constructing a loss function suitable for the field of digital humanities ;Collect digital humanities image samples, and build model training data sets and verification sets; preprocess image samples; use the built loss function and digital humanities training set to train the model, optimize model parameters; use the trained model to extract images The semantic feature vector completes the image retrieval process. Aiming at the two major challenges of image depth semantic feature extraction and data transmission scale limitation in digital humanities mobile visual retrieval, the present invention combines deep learning and hashing methods to propose a digital humanities mobile visual search method based on deep hashing. This method is in the field of digital humanities Excellent performance on the dataset.

Description

technical field [0001] The invention relates to the fields of digital humanities, mobile visual retrieval, etc., and in particular to a digital humanities-oriented mobile visual retrieval method. Background technique [0002] With the popularization of mobile smart terminal equipment and the rapid development of big data and cloud computing technology, massive pictures, videos, 3D models and other visual content have been generated on the Internet; the portability of mobile devices and the ubiquity of wireless networks make information retrieval more difficult. The method tends to be mobile and multimedia. Mobile Visual Search (MVS) technology, that is, an information retrieval model that uses visual data such as images, videos or maps collected by mobile smart terminals as retrieval objects to obtain relevant information, is gradually developing. rise, and have generated huge market and application demands. The application of MVS to the field of digital humanities has emer...

AI Technical Summary

Problems solved by technology

[0004] In the above methods, most of them do not fully consider the extraction of deep semantic features of images and the limitation of data transmission scale, and the digital humanities mobile visual retrieval method still has a large room for optimization.

Images