Content retrieval method for chrysanthemum image based on deep hash learning

Abstract

The invention discloses a content retrieval method for a chrysanthemum image based on deep hash learning. A deep neural network algorithm and Hash coding are used to recognize and retrieve images. Themethod comprises: firstly, establishing a training set and a test set to perform pre-data-processing on a to-be-identified image, to enhance generalization ability and recognition degree of the image; secondly, establishing a chrysanthemum image feature extraction model through a convolution neural network, and realizing query calculation by hash coding in a hash layer of the convolution neural network. The method is based on the deep hash learning, so that when high-dimensional data is mapped to a low-dimensional space, similarity of the data in high-dimensional space can be maintained in aHamming space, a coding balance criterion is maintained when the high-dimensional data is mapped to the low-dimensional space. The method processes a chrysanthemum data set, enhances the data set to enhance model generalization ability, and improves image retrieval quality and retrieval efficiency.

Description

technical field [0001] The invention belongs to technical fields such as computer, artificial intelligence, be specifically related to a kind of chrysanthemum image content retrieval method based on deep hash learning. Background technique [0002] At present, for the recognition of plants and flowers, machine learning technology is mainly used. There is a lack of in-depth research on the identification of different chrysanthemum flower types. Although most of the flowers can be identified by the existing technology, the accuracy and efficiency of the query and retrieval of chrysanthemum image content need to be improved. [0003] The existing flower type identification technologies mainly include: (1) Microsoft Flower Recognition is an App application for intelligently identifying flower varieties launched by Microsoft Asia Research Institute and the Institute of Botany, Chinese Academy of Sciences. Knowledge; (2) Xingse is a plant recognition APP application, which can re...

AI Technical Summary

Problems solved by technology

There is a lack of in-depth research on the identification of different chrysanthemum flower types. Although most of the flowers can be identified by the existing technology, the accuracy and efficiency of the query and retrieval of chrysanthemum image content need to be improved.

Images