Method and system for detecting font type in font image based on convolution neural network
A convolutional neural network and detection method technology, applied in the field of font information retrieval, can solve problems such as slow efficiency and low recognition accuracy, and achieve the effects of no need for manual intervention, significant work efficiency, and labor cost savings
Pending Publication Date: 2019-03-22
广州企图腾科技有限公司
View PDF5 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to overcome the deficiencies in the prior art, one of the purposes of the present invention is to provide a font type detection method in font images based on convolutional neural networks, which can solve the current font type recognition methods basically through manual comparison and recognition. The efficiency of this recognition method is slow, and the recognition accuracy is relatively low
[0005] The second object of the present invention is to provide a font type detection system in font images based on convolutional neural network, which can solve the current font type recognition methods basically through manual comparison and recognition, which is relatively slow in efficiency and Problems with relatively low recognition accuracy
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
[0034] Below, the present invention will be further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of not conflicting, the various embodiments described below or the technical features can be combined arbitrarily to form new embodiments. .
[0035] like figure 1 As shown, the font type detection method in the font image based on the convolutional neural network of the present invention comprises the following steps:
[0036]Establish a background image database, capture several background images through the background image material website, store the background image, and obtain the background image database; and perform grayscale processing on the background image; the background images captured in this embodiment are all color images , because the color image is composed of multiple pixels, and each pixel is represented by three RGB values; the background image is grayscale processed a...
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 font type detection method in a font image based on a convolution neural network, which comprises the following steps: capturing a plurality of background images through a background image material website; Captureing several types of copyrighted fonts through intellectual property websites; organically combinding Each background image and each font type in the font type database to obtain a font image, the font image, the font type and inputting the preset font coordinate size information into the training model, and training the training model and acquiring the fonttype detection model by using a convolution neural network algorithm. Inputting The font image to be tested to the font type detection model, and outputting the corresponding font type by the font type detection model. The invention provides a font type detection method in a font image based on a convolution neural network, which can quickly process a large number of font images to be tested by establishing a font type detection model for identifying the font type of the font image to be tested, thereby saving labor cost and remarkable work efficiency.
Description
technical field [0001] The invention relates to the field of font information retrieval, in particular to a method and system for detecting font types in font images based on convolutional neural networks. Background technique [0002] Chinese character fonts are a set of fonts designed according to certain rules and styles. The font is not mysterious, and it appears in human life everywhere in the form of various carriers, such as copybooks, newspapers, books and periodicals, etc. With the continuous development of society and technology, since well-known companies such as Apple and Google have launched their own custom fonts, more and more well-known brands have begun to obtain authorization or customize and develop their own exclusive fonts. The font industry has also received unprecedented attention in the design circle. Whether it is web design or e-book design, text typography is always the most important part, and font is the core part of typography. It is a basic so...
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): G06K9/00G06K9/62
CPCG06V30/333G06V30/36G06V30/287G06F18/2431G06F18/214
Inventor 邓立邦
Owner 广州企图腾科技有限公司