A neural network-based handwriting recognition system, device and mobile terminal
A handwriting recognition and recognition device technology, applied in the field of neural networks, can solve the problems of relying on network bandwidth for processing big data, remote servers, and fixed mathematical processing models, so as to reduce complexity, increase possibilities, and reduce dependence.
Active Publication Date: 2019-05-28
SPREADTRUM COMM (SHANGHAI) CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] According to the problems existing in the prior art, a technical solution of a neural network-based handwriting recognition system, device, and mobile terminal is now provided, aiming at solving the problem that the mathematical processing model applied to devices such as mobile terminals is relatively fixed, and processing large data Depends on network bandwidth and remote server issues
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
[0066] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.
[0067] In the prior art, there are usually two implementation methods for traditional mathematical models applied to mobile terminals and other handheld devices to realize intelligent recognition:
[0068] 1) One of the implementation methods is limited by the hardware computing capability of the mobile terminal, and needs to be calculated by the remote server, that is, cloud computing to train the mathematical processing model inside the mobile terminal. Since the amount of data transmitted between the mobile terminal and the remote server may be relatively large, such as image recognition or video recognition, the realization of this method is limited by the limitation of network bandwidth, which is a relatively unreliable realization method ;
[0069] 2) Another implementation method may pre...
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 discloses a neural network-based handwriting recognition system, device and mobile terminal, belonging to the technical field of neural networks; the system includes a collection device, a recognition device and a result feedback device; wherein the recognition devices are arranged in multiple rows and columns and mutually The neural network model formed by the block processing of multiple associated neural units recognizes the image of the externally input handwritten character; the image of the externally input handwritten character is converted into a corresponding time pulse sequence and sent to the recognition device. The neural network model is updated and learned through feedback results, so as to train and form a neural network model adapted to the user's personal writing habits. The beneficial effects of the above technical solution are: reducing the complexity of the mathematical processing model to process data; reducing the amount of data transmitted to the remote server, reducing the dependence of the mobile terminal on the network bandwidth of the mathematical processing model; improving the application of the mathematical processing model to the mobile terminal on possibility.
Description
technical field [0001] The invention relates to the technical field of neural networks, in particular to a neural network-based handwriting recognition system, device and mobile terminal. Background technique [0002] In the prior art, a handwriting recognition system for a mobile terminal is usually realized by using some data processing models set inside the mobile terminal. These mathematical processing models need to be adjusted accordingly according to changes in the user's personal habits. [0003] However, in the prior art, the function of realizing automatic handwriting recognition inside the mobile terminal is usually limited by the relatively small computing power of the mobile terminal and the relatively fixed mathematical processing model inside the mobile terminal, and its data processing depends on the support of the remote server. And the processing method is relatively fixed and not flexible. Contents of the invention [0004] According to the problems ex...
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): G06K9/68
Inventor 郑介誌林福辉
Owner SPREADTRUM COMM (SHANGHAI) CO LTD