Rendering images based on image segmentation

An image segmentation and image technology, applied in image analysis, image enhancement, image data processing and other directions, can solve problems such as filling holes, and achieve the effect of a simple hole filling program

Inactive Publication Date: 2007-10-24
KONINKLIJKE PHILIPS ELECTRONICS NV
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In paint programs, if this blurring is not handled properly, it can lead to phantom edges
[0007] So far, existing techniques have had the problem of filling holes at object boundaries that coincide with image boundaries (such as color boundaries) with a large amount of variation

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
  • Rendering images based on image segmentation
  • Rendering images based on image segmentation
  • Rendering images based on image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Throughout the drawings, the same reference numerals represent similar elements. The inventive method is particularly concerned with rendering images based on displacement, eg for compression algorithms or rendering "image+depth" data on multi-view displays. The invention particularly provides a method for automatically drawing images based on image segmentation.

[0036] FIG. 1 shows an image containing a segment 4 defined by a boundary 2 . Boundary 2 is an edge that can be determined from a discontinuity in the image, for example in color degradation, or, if possible, in a displacement field of a given displacement or in 2,5-D image discontinuity data. It could be others, too, such as brightness, contrast, chroma, or any other discontinuity in value.

[0037] Figure 2a schematically shows a legend for a cross view through the image. The horizontal axis can be regarded as a scan line, and the vertical axis can be regarded as an image brightness value on the correspo...

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 invention relates to a method for providing rendered images based on image segmentation with determining an edge within the image introduced by boundaries of image segments. To allow shift-based rendering, the invention provides determining an edge within the image introduced by boundaries of image segments, determining an edge region around the edge, determining a first displacement field for the segments, determining a second displacement field for the edge region, merging the first and the second displacement field into a third displacement field having a displacement of the first displacement field for the segments and a displacement of the second displacement field for the edge region, such that the edge region is treated as a separate object with a separate displacement, and shifting the image pixels according to the third displacement field.

Description

technical field [0001] The present invention generally relates to a method and system for rendering images based on image segmentation by determining at least one edge within an image introduced by boundaries of image segments. Background technique [0002] For example, shift-based rendering is used in compression applications and in the field of rendering "image+depth" data such as 2,5-dimensional (2,5-D) image data on multi-view displays. Shift-based rendering can be employed when a new image must be generated based on an existing image, for example, when the viewpoint is changed slightly or the viewing time is slightly delayed. For example, when motion estimation is applied to compressed images, image segmentation is also used. Hole filling and edge blurring need to be handled when segmenting images and shifting fragments. For displacement-based rendering, the original image data is available. Additionally, a displacement field or equivalent depth map is provided. The...

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): G06T15/20
CPCG06T7/0022G06T7/0083G06T15/20G06T2207/20228G06T7/97G06T7/12G06T15/10
Inventor F·E·厄恩斯特P·-A·雷德特
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