A Method and System for Regional Feature Description Based on Binary Segmentation Tree

A regional feature and binary segmentation technology, applied in the field of computer vision and image processing, can solve the problems of poor feature robustness and insufficient information, achieve high recognition, overcome poor robustness, and strong robustness

CN105574532BActive Publication Date: 2019-03-08SHENZHEN UNIV
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2019-03-08

Smart Images

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

Abstract

The present invention is applicable to image feature extraction, and provides a region feature description method based on a binary segmentation tree. The steps include: A, dividing the original image into several segmentation regions; B, calculating the similarity between adjacent segmentation regions Combine the two adjacent regions with the highest similarity into a super region; C, repeat B until the complete original image is merged; D, construct a binary segmentation tree according to the segmented region and super region; E, extract the binary segmentation tree respectively The characteristics of the target area and the super area corresponding to the target area are used to construct the area feature, and then the feature description of the target area is performed according to the area feature. The present invention combines the basic regional characteristics of the target region, the same-level super region, and the adjacent superior region and super region to describe the characteristics of the target region, which includes not only local region features but also global situation information, so it will have situational awareness, The advantages of high recognition and robustness.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the fields of computer vision and image processing, and in particular relates to a method and system for describing region features based on a binary segmentation tree. Background technique

[0002] Feature description is a basic module in computer vision and image processing. In applications such as image salient object detection, object segmentation, object recognition, and semantic image retrieval, the robustness and richness of features largely determine its performance. Most of the feature extraction methods currently used are: the original image is divided into image sub-blocks or image regions by image segmentation algorithm or pixel clustering method, and then image features are extracted according to these image sub-blocks or image regions.

[0003] Although the existing feature extraction methods are efficient, natural images often contain a lot of complex backgrounds, and the most advanced image segmentation methods ...

Examples

Embodiment Construction

[0055] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0056] In the present invention, a method and system for regional feature description based on binary segmentation tree is proposed, which includes local and global context information of the segmented area, and has the advantages of context awareness, high recognition and strong robustness.

[0057] The present invention is realized like this, as figure 1 A method of regional feature description based on a binary segmentation tree is shown, and the steps include:

[0058] S1, segment the original image into several segmented regions. In this step, the original image is segmented using one of any...