Character image writing track recovery method based on double-flow coding
A writing track and recovery method technology, applied in neural learning methods, character recognition, digital ink recognition and other directions, can solve the problems of poor feature representation, weak generalization performance, and low recovery accuracy of writing tracks, and achieves improved recovery performance, The effect of reducing the amount of parameters
Active Publication Date: 2022-05-10
SOUTH CHINA UNIV OF TECH +1
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, the object of the present invention is to provide a method for recovering writing traces of text images based on dual-stream coding, so as to solve the problems of poor feature representation ability, weak generalization performance, The problem of low accuracy of writing trace recovery
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
[0039]In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments . Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0040] For the sake of reference and clarity, the technical terms, abbreviations or abbreviations used in the following text are summarized as follows:
[0041] CNN: Convolutional Neural Network, convolutional neural network;
[0042] RNN: Recurrent Neural Network, recurrent neural network...
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 character image writing track recovery method based on double-flow coding. The method comprises the following steps: adjusting a character image to a preset size and carrying out binarization processing; a double-flow coding network is constructed, the input of the double-flow coding network is character images, and the output of the double-flow coding network is double-flow fusion coding features; a decoding network is constructed, the input of the decoding network is a double-flow fusion coding feature, and the output of the decoding network is a predicted character writing track sequence; jointly training a double-flow coding network and a decoding network to obtain a character image writing track recovery network model; and carrying out writing track recovery by utilizing the trained character image writing track recovery network model. According to the method, in the encoding process, the features of the characters in the vertical direction and the horizontal direction are extracted respectively, downsampling is carried out on the features, the parameter quantity is reduced, meanwhile, necessary character font information is reserved, subsequent decoding is helped to accurately reflect character fonts, and the recovery performance of character image writing tracks is effectively improved.
Description
technical field [0001] The invention relates to the field of character image pattern recognition, in particular to a method for recovering a writing track of a character image based on dual-stream encoding. Background technique [0002] Text data can be roughly divided into two categories: image modal data and writing trajectory modal data according to the modality type. Text generation technology mainly revolves around these two modal forms. Text images are often obtained by image acquisition devices such as scanners or cameras, and stored in the form of dot matrix images. This kind of data can intuitively display the shape of text, and is often used for text display and reading. The writing track is collected by interactive devices such as a digital pen that can record the track, a tablet or a touch screen, and is usually stored in the form of a track sequence of pen tip coordinate points, and auxiliary information such as pen tip pressure and speed during the writing proc...
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 Applications(China)
IPC IPC(8): G06V30/32G06V20/62G06V30/10G06V10/28G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/241
Inventor 黄双萍陈洲楠杨代辉梁景麟彭政华
Owner SOUTH CHINA UNIV OF TECH