An intelligent image annotation method based on YOLOv3 depth learning network

Abstract

The invention discloses an intelligent image annotation method based on YOLOv3 depth learning network, belonging to the technical field of image retrieval. Firstly, the image data set to be labeled bythe image recognition item is divided into M groups, one group is manually labelled, and it is used to train YOLOv3 deep learning network, then, the obtained network model is automatically labeled with another set of unlabeled image data, and added into the training set of YOLOv3 to continue training, and the labeling and training process is repeated until all sets of image data are labeled successfully, and the updated model of the whole data set corresponding to the image recognition item is obtained. The invention realizes intelligent labeling of picture data sets of image recognition items, not only effectively reduces the complex workload of image labeling, but also gradually improves the performance of YOLOv3 model detection and recognition target through several cyclic iterative training.

Description

technical field [0001] The invention relates to the technical field of image intelligent labeling and retrieval, in particular to an image intelligent labeling method based on a YOLOv3 deep learning network. Background technique [0002] In recent years, artificial intelligence and big data have become the focus of attention in various fields at home and abroad. Faced with more and more image data, how to efficiently manage and organize these image data has become a hot issue in the field of image retrieval. By adding text information related to its content to the image, that is, image annotation has become the most important solution at present. In view of the problems of manual annotation, such as heavy annotation workload and strong subjectivity, intelligent image annotation has attracted attention under the wave of artificial intelligence. popular among researchers. [0003] At present, the automatic labeling of images based on computer vision technology has achieved g...

AI Technical Summary

Problems solved by technology

The above method proposes a method of automatically labeling images through the shallow features of image data and the high-level features of the Boltzmann model, but the classifier trained by shallow image features is only effective for some target labels, but not for other targets. To obtain higher labeling accuracy, the training of the Boltzmann model needs to use a large number of training samples to obtain shallow visual features. Since the feature descriptions of different visual objects are different, it is often necessary to select a better visual feature description in a targeted manner. , leading to poor portability of the method

Images