Image scene labeling method based on deep learning

Abstract

The invention discloses an image scene labeling method based on deep learning. The method comprises the steps of establishing a scene image data set, constructing a convolutional neural network, training a model, and labeling an image. The scene image data set is used for training and testing a deep learning scene recognition model. According to the construction of the convolutional neural network, the model of the convolutional neural network for scene recognition is constructed. According to the training of the model, the scene recognition model is obtained by training the convolutional neural network. According to the labeling of the image, a scene labeling word of the image is obtained through the identification of the image in the model. The shortage of image scene labeling is solved,and the accuracy of image scene labeling is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and pattern recognition, in particular to an image scene recognition method based on deep learning. Background technique [0002] Image scene recognition is an important research topic in the field of machine vision. Its research goal is to use computers to automatically recognize and understand scene information in images. With the dissemination of image data on the Internet, various websites need to process massive image data, and use computers to automatically understand and classify images, and scene recognition technology plays a very important role in this application. [0003] Due to the wide application prospect of scene recognition technology, this topic has been studied by many researchers. In foreign countries, Li Fei-Fei et al. proposed a middle-level semantic method combining the visual bag-of-words model and the latent Dirichlet distribution model for scene recogniti...

AI Technical Summary

Problems solved by technology

But when the data to be processed reaches a certain scale and the scene classification reaches a certain number, the traditional low-level features and high-level features cannot represent so much scene information.

Therefore, using traditional methods to solve this problem gradually faces bottlenecks, especially on large-scale data sets.

[0005] The method based on deep learning is very suitable for dealing with such problems. The rapid development of deep learning methods is due to the surge in data volume, because deep networks generally require a large amount of data to be trained to form a complex and powerful network architecture.

The existing image scene recognition technology based on deep learning has achieved good accuracy, but the recognition accuracy needs to be improved

Images