A Method for Automatic Image Annotation and Translation Based on Decision Tree Learning

Abstract

The invention discloses a method for automatic image labeling and translation based on decision tree learning, which automatically labels new images, and realizes machine retrieval of image data by using machine translation text vocabulary with visual content, including training and labeling image sets and images are automatically annotated. The training labeled image set uses the image segmentation algorithm to divide the training image set into sub-block areas, extracts the underlying visual features of each sub-block area; discretizes these feature data, and then uses the clustering algorithm to train the labeled image set based on the discrete values ​​of the underlying features Carry out classification and construct a semantic dictionary; use the discrete value of the underlying feature as the input attribute of the decision tree learning; use the decision tree machine learning method to carry out self-training and learning on the constructed dictionary corresponding to the preset semantic concept, and generate a decision tree and obtain the corresponding decision rules. The training marked image set of the present invention has expansibility and robustness, and can improve the retrieval recall rate and precision rate when it is applied to semantic image retrieval.

Description

technical field [0001] The invention relates to the fields of digital image retrieval technology and machine learning technology, in particular to a method for automatic image labeling and translation based on decision tree learning. Background technique [0002] In the early days, people realized image retrieval through manual annotation, but this work was time-consuming and laborious, especially when faced with large-scale network images, it was obviously not competent. Therefore, how to quickly and effectively realize the automatic semantic annotation of images has become very necessary. [0003] Automatic image annotation is a process of automatically assigning metadata to a digital image in the form of captions or keywords by a computer system. This computer vision application technique is used in image retrieval to organize and find images of interest to the user in the database. This method is called a multi-class image classification method, which contains a large ...

AI Technical Summary

Problems solved by technology

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to study a method for automatic image labeling and translation based on decision tree learning, so that the training set after labeling has scalability and robustness, to solve the problem of training image database Problems with not fitting to another untrained image database and problems with incomplete and noisy data

Images