Visual attention location system

A technique of visual attention, relation, applied in the field of systems used by image compression systems, to achieve the effect of avoiding the use of processing correlation

Inactive Publication Date: 2003-07-16
BRITISH TELECOMM PLC
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, automatic identification of regions of interest remains a problem

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
  • Visual attention location system
  • Visual attention location system
  • Visual attention location system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The components illustrated in Fig. 4 include: an input device 41, such as a scanner; a central processing unit (CPU) 42; an output unit, such as a visual display unit (VDU) or printer 43; a memory 44; computing processor 45 . The memory includes memories 440,444-446, registers 441,447-449 and counters 442,443. Data and programs for controlling the computer are stored in the memory 44 . The CPU 42 uses this information to control the functions of the computer.

[0057] now consider figure 1 and 4, the image 40 to be analyzed is accessed by the input device 41 and stored digitally in an image memory 440 as an array A of pixels x, where each pixel has the color intensity (r x , g x , b x ), in the case of a grayscale image, a single grayscale intensity value t x .

[0058] Then select a pixel x from array A (step 1) and assign its intensity value (r x , g x , b x ) or t x stored in a test pixel register 441. Several test pixels can be processed in parallel, but...

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

This invention identifies the most significant features in visual scenes, without prior training, by measuring the difficulty in finding similarities between neighbourhoods in the scene. Pixels in an area that is similar to much of the rest of the scene score low measures of visual attention. On the other hand a region that possesses many dissimilarities with other parts of the image will attract a high measure of visual attention. The invention makes use of a trial and error process to find dissimilarities between parts of the image and does not require prior knowledge of the nature of the anomalies that may be present. The method avoids the use of processing dependencies between pixels and is capable of a straightforward parallel implementation for each pixel. The invention is of wide application in searching for anomalous patterns in health screening, quality control processes and in analysis of visual ergonomics for assessing the visibility of signs and advertisements. The invention provides a measure of significant features to an image processor in order to provide variable rate image compression.

Description

technical field [0001] The present invention relates to a system for locating salient objects contained within a still image or a video sequence, especially, but not exclusively, for use by image compression systems. Background technique [0002] The human visual eye-brain perception system is good at recognizing the most important features in a presented scene, or objects that differ in some way from background or surrounding objects in general, without the need for the most automated systems. pre-trained. However, there are certain applications where automation is desired, such as those in which the work is highly repetitive and the amount of data is large. A specific example is the examination of medical smear samples to identify cancer cells. In this case, where a large number of samples need to be examined and with few exceptions, the human observer can become inattentive and fail to notice the particular feature sought. [0003] It is also desirable for many other p...

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
Patent Type & Authority Applications(China)
IPC IPC(8): H04N11/04G06T7/00G06T7/60H04N7/26
CPCG06K9/4671G06V10/462G06T7/00
Inventor 弗雷德里克·沃里克·迈克·斯腾蒂福特
Owner BRITISH TELECOMM PLC
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