A film and television animation production method based on voice drive and image recognition
An image recognition and animation production technology, applied in motion capture and three-dimensional fields, can solve the problems of shallow technical level, small application area, no application, etc., to achieve the effect of improving the technical level
Inactive Publication Date: 2019-08-30
SHANGHAI HIPPO ANIMATION DESIGN INC
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] 1. At present, the application area is very small, occasionally seen in simple interactive games, and has not yet been applied in industry, commerce, film and television animation industries
[0004] 2. The technical level of the application is very shallow, and it still stays at the level of obtaining simple expression words. The data is static data, and there is no precedent for further applying this technology to the film and television animation production system
[0005] 3. In terms of the material format of image recognition, at present it simply calculates from the static image in the network address and local disk
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] The present invention will be described in detail below in conjunction with the accompanying drawings. The following examples do not limit the invention. Without departing from the spirit and scope of the inventive concept, changes and advantages that can be imagined by those skilled in the art are all included in the present invention.
[0025] figure 1 is a flowchart of the method according to the invention. Such as figure 1 Shown, the inventive method comprises the steps:
[0026] Step a: use the software of the present invention to call the computer camera to take screenshots of files in three formats: network pictures, local pictures, or video dynamic images, and save them as source material sequences. and get the sound as the source material.
[0027] In the present invention, files in three formats, network pictures, local pictures or video dynamic images, can be screenshotted to obtain images as source material sequences. The dynamic image of the video is ...
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
Login to View More Abstract
The invention provides a television animation manufacturing method based on speech driving and image recognition, and the method comprises the following steps: step a, images serving as a source material sequence and sounds serving as source materials are acquired; step b, facial emotion data is calculated according to the images acquired in the step a; step c, the facial emotion data obtained in the step b is sent to a three-dimensional software; step d, in the three-dimensional software, the source material sounds acquired in the step a are taken to associate with defined corresponding shapes of mouth of a three-dimensional character model, so that the three-dimensional character model can show the shapes of mouth corresponding to the sounds; and the emotion data in the step c is associated with the defined corresponding facial expressions of the three-dimensional character model, so that the three-dimensional character model can show the facial expressions corresponding to the emotion data. According to the invention, dynamic analysis and optimization are performed on the obtained original static data, and the data is transmitted to the three-dimensional software in real time, so as to prepare for manufacturing character facial expressions in an animation software.
Description
technical field [0001] The invention relates to the field of motion capture and three-dimensional technology, in particular to a method and system for making video and animation based on voice drive and image recognition. Background technique [0002] At present, among the existing expression recognition technologies in the industry, there is the expression cloud computing provided by the Microsoft Oxford project, but it simply obtains a set of expression description vocabulary, including anger, contempt, disgust, fear, fear, joy, sadness and neutrality. Sexual expressions, specifically a set of English descriptions. Problems with this technique include: [0003] 1. At present, the application area is very small, occasionally seen in simple interactive games, and has not been applied in industry, commerce, film and television animation industry. [0004] 2. The technical level of the application is very shallow, and it still stays at the level of obtaining simple expressio...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T13/40
Inventor 徐克
Owner SHANGHAI HIPPO ANIMATION DESIGN INC