Image segmentation using template prediction

A template, image technology, applied in the field of image segmentation using template prediction, which can solve the problems of complexity, not well suited to image and video material, image heavy and over-segmentation, etc.

Inactive Publication Date: 2005-12-21
KONINKLIJKE PHILIPS ELECTRONICS NV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this is heavy over-segmentation within the image
[0018] As mentioned above, the disadvantage of the current method is excessive segmentation or computational complexity
These methods are not yet well suited for image and video material

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image segmentation using template prediction
  • Image segmentation using template prediction
  • Image segmentation using template prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] figure 1 denotes the method according to the invention. In the first step 2, image feature properties are extracted. In step 4, these features are compared with the feature properties of the segment template of adjacent groups of pixels.

[0043] If the characteristics of the current group deviate from the characteristics of the segment templates of the adjacent group, then in step 6, a new segment template is generated according to the characteristics of the current group. In step 8, this new segment template is stored together with the already stored segment templates. These fragment templates represent groups of pixels that have been segmented.

[0044] In step 10, the template of the current group is predicted using the fragment templates of adjacent groups of pixels according to the stored fragment templates. This means that, from the stored fragment templates, templates related to groups of pixels adjacent to the current group of pixels are extracted. Preferabl...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention relates to image segmentation using templates and spatial prediction. Use the templates of neighboring pixels to predict the features of the current pixel. Pixels are assigned to segments of adjacent pixels according to deviations from the features of the template.

Description

technical field [0001] The invention relates to a method of segmenting an image into groups of segments, said segments being based on image characteristics, said method having the steps of determining groups of pixels for segmentation and determining characteristic properties for said groups. [0002] The invention also relates to a device for computing image segmentation, said device comprising grouping means for grouping image pixels into pixel groups and extraction means for extracting characteristic properties from said pixel groups. [0003] Finally, the invention relates to the use of such a method and such a device. Background technique [0004] Image segmentation is very important for many image and video processing processes, such as object recognition, classification, and video compression, such as MPEG video streaming. [0005] For the result of image segmentation, it is important which features or characteristics are used for segmentation. An image segment can ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T5/00
CPCG06T2207/10016G06T2207/20021G06T7/11G06T5/00
Inventor R·B·维特鲁德G·德哈安
Owner KONINKLIJKE PHILIPS ELECTRONICS NV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap