Image-to-sound method

An image and sound technology, applied in the field of image processing and audio processing, can solve the problem of not mining image information in depth

Active Publication Date: 2018-04-27
BEIJING UNIV OF TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] It can be seen that the above methods are simple mappings from image to sound, without deep mining of image information, color semantics, and the way music affects people's emotions
None of the current image-to-sound algorithms can truly achieve emotional resonance and create so-called music

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-to-sound method
  • Image-to-sound method
  • Image-to-sound method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Such as Figure 7 As shown, the present invention provides an image-to-sound method including the following steps:

[0036] Step 1. Extract the spatial distribution of the image color based on the salient features;

[0037] Step 2. Extract the overall and partial emotional semantics of the color of the image;

[0038] Step 3. Determine the emotional tone of the music;

[0039] Step 4. Generate specific music fragments on the spatial information extracted from the image;

[0040] Step 5. Processing the initial music.

[0041] Step 1 is specifically: screening information according to the human visual attention mechanism to achieve the purpose of more consistent extraction of information with human extraction, and it is also the material for subsequent music creation "inspiration". Starting from the anomaly of the color between regions, the thorn weight function of each pixel can be given by using the HSV color space:

[0042] f(p)=C h g h (p·H)+C s g s (p·S)+C v g v (p·V) (1)

[004...

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 discloses a image-to-sound method. The method comprises: S1, extracting space distribution of image colors according to saliency features; S2, global and local emotional semantic extraction on the image colors; S3, determining a music emotion keynote; step four, carrying out specific music segment generation on extracted space information of the image; and step five, processing initial music. According to the invention, any image can be transformed into unique music to realize emotion and artistic conception unification of a given image and generated music; and the human sound and image connection process is simulated.

Description

Technical field [0001] The present invention belongs to the technical field of image processing and audio processing, and particularly relates to a method for converting images into sound, which can convert music through any given picture. Background technique [0002] Painting, calligraphy and music have been twin sisters since ancient times. When people are fascinated by the ink paintings of art and photography works by world masters, a piece of beautiful music based on this work seems to linger in their ears. For example, when admiring the picture scroll of the "Penteng Yellow River", people seem to hear the roar of the Yellow River; when admiring the picture scroll of the "Morning Forest", people seem to hear the gurgling water of the mountain stream and the birds in the forest. Euphemistic singing. This sound-color synesthesia exists in everyone, and this mechanism is not only at the level of philosophy and psychology, but can be tracked by a large number of audiovisual exp...

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): G06K9/46G10L25/63
CPCG10L25/63G10H2220/441G10H2210/101G06V10/56
Inventor 王波涛李珺
Owner BEIJING UNIV OF TECH
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