Building method for character type detection model, and computing equipment
A text type, detection model technology, applied in computing, computer parts, character and pattern recognition, etc., can solve problems such as handwriting immersion, limited detection effect, and rotation images cannot be well detected, so as to improve fine-grained and Accuracy, avoid the effect of result roughness
Active Publication Date: 2018-07-20
BEIJING YUNJIANG TECH CO LTD
View PDF8 Cites 20 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method requires very high image quality. If the image has shadows or handwriting immersion and blurring, it will cause low detection accuracy.
Moreover, this method can only be segmented and detected based on horizontal lines of text, and it cannot detect rotated images very well.
In addition, the text itself has a variety of features, and the detection and distinction of handwritten text based only on color features cannot fully exploit the characteristics of handwritten text, which limits its detection effect to a certain extent.
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
[0030] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0031] figure 1 is a block diagram of an example computing device 100 . In a basic configuration 102 , computing device 100 typically includes system memory 106 and one or more processors 104 . A memory bus 108 may be used for communication between the processor 104 and the system memory 106 .
[0032]Depending on the desired configuration, processor 104 may be any type of processing including, but not limited to, a microprocesso...
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 building method for a character type detection model and a character type detection method, and is suitable to be executed in computing equipment. The building method comprises the steps: collecting training images; expanding each training image into a square image; obtaining a result after a print-form character region and a handwriting character region of each square image are marked; training a CNN (convolutional neural network) according to all training images and the marking results of the training images, and obtaining a character type detection model. The detection method comprises the steps: obtaining a to-be-recognized original image, and cutting the original image into a plurality of subimages; detecting the print-form character region and the handwriting character region of each subimage through the character type detection model, and obtaining the coordinate information of each character region and the character type of each character region; merging the character regions of the same type which are adjacent and tangent to each other and belong to different subimages, and obtaining the print-form character region and the handwriting character region of the original image. The invention also discloses corresponding computing equipment.
Description
technical field [0001] The invention relates to the field of image data processing, in particular to a construction method of a character type detection model, a character type detection method and a computing device. Background technique [0002] With the development of computer and Internet technology, people are increasingly using automated equipment to mark student examination papers. During test paper analysis, it is often necessary to identify whether the text in each recognition area is a handwritten font or a printed font. Current text recognition methods are usually based on character color or short-answer text features. This method has very high requirements on the quality of the image. If the image has shadows or handwriting immersion and blurring, etc., it will cause the problem of low detection accuracy. Moreover, this method can usually only perform segmentation detection based on horizontal lines of text, and it cannot detect rotated images well. In additio...
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): G06K9/00G06N3/04
CPCG06V30/40G06N3/045
Inventor 徐行刘辉刘宁张东祥郭龙陈李江李启林
Owner BEIJING YUNJIANG TECH CO LTD