Image annotation method

Abstract

The invention relates to an image annotation method comprising the following steps: 1, defining a target function of an image annotation model; 2, inputting an image into a CNN model so as to obtain original image characteristics; 3, weighting the original image characteristics; 4, inputting information into a LSTM model; 5, making reversed propagations for errors caused by prediction result. Theimage annotation method firstly uses a convolution nerve network to extract image bottom layer characteristics, then uses a focusing mechanism to extract image characteristics related to image annotation words in an image specific position area, inputting the information into the LSTM network model, forming corresponding prediction annotation words, and finally realizing image annotations; the image annotation method is excellent in annotation performance, high in annotation precision, thus well satisfying real application demands.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image labeling method. Background technique [0002] In recent years, researchers have been working on computers' semantic understanding of images. Automatic image annotation is to let the computer automatically label keywords for entities in the image, which is a key technology in the field of image retrieval. With the rapid development of multimedia information technology and Internet information technology, hundreds of millions of new images are presented on the Internet every day. Compared with text, images can describe information more intuitively and accurately. Therefore, in today's era of information explosion, images can enable users to obtain the required information more conveniently, faster, and more accurately. Image information has gradually become one of the most important ways of information dissemination in the current era. Therefore, h...

AI Technical Summary

Problems solved by technology

Being able to quickly and accurately retrieve the images required by users in such a huge image library is an urgent need in the era of big data. However, most current automatic image annotation techniques generally have poor results in such a huge image library. New automatic image annotation technique under the data has great significance

Images