Image automatic marking method based on Monte Carlo data balance

An image automatic labeling and image technology, applied in the field of computer vision and image processing, can solve the problems of high cost, not considering the corresponding relationship between image areas and keywords, and enlargement

CN105701502AActive Publication Date: 2016-06-22FUZHOU UNIV
5 Cites 33 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2016-06-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention relates to an image automatic marking method based on Monte Carlo data balance. The method comprises the steps of carrying out the region segmentation on the training sample images in a public image library, enabling the segmented regions possessing different characteristic description to correspond to one marking word, then carrying out the Monte Carlo data balance on the different types of image sets, extracting the multiscale characteristics of the balanced images, and finally inputting the extracted characteristic vectors in a robustness least squares increment limit learning machine to carry out the classification training to obtain a classification model in the image automatic marking; for the to-be-marked images, carrying out the region segmentation on the to-be-marked images, adopting the same multiscale characteristic fusion extraction method and inputting the extracted characteristic vectors in the least squares increment limit learning machine to obtain a final image marking result. Compared with a conventional image automatic marking method, the method of the present invention enables the images to be marked more effectively, is strong in timeliness, can be used for the automatic marking of the large-scale images, and possesses the actual application meaning.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the fields of computer vision and image processing, in particular to an image automatic labeling method based on Monte Carlo data equalization. Background technique

[0002] Image understanding is the semantic understanding of images. It regards images as objects and knowledge as its core, and focuses on the research on the objects in images, the relationship between objects, and the scenes depicted in images based on people's cognition. The ultimate goal of image semantic understanding is to meet people's different needs for images. Fully understanding the hidden semantic content in images is an important step in image management. Earlier, the construction of image semantic databases was often done manually. However, with the explosive growth of the number of images, if the semantics of images is still marked manually, it will consume huge manpower and material resources, and it is not feasible. In addition, due to certain d...

Examples

Embodiment Construction

[0075] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0076] This embodiment provides an image automatic labeling method based on Monte Carlo data equalization, such as figure 1 shown, including the following steps:

[0077] Step S1: Automatically segment the training set images in the public image database;

[0078] Step S2: Use the comprehensive distance image feature matching method (CDIFM) to automatically match the segmented images, classify images with the same features and similar features into one category, and paste corresponding tag words; different categories of image sets have Tags for different descriptions;

[0079] Step S3: performing Monte Carlo data set equalization (MC-BDS) on image sets of various categories with different tag words, images of each category have the same tag word, and image sets of different categories have different descriptors;

[0080] Step S4: Extract the multi-sc...