Image-text impression positive and negative convolutional neural network deep processing method
A neural network and deep processing technology, applied in the field of deep processing of image and text impression positive and negative convolutional neural network, can solve the problems of large processing requirements, troublesome electronic seal method, inconvenient for staff to use, etc. Improve accuracy and ease of use
Pending Publication Date: 2022-01-04
财悠悠科技(深圳)有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] With the continuous development of electronic seals and electronic contracts, the processing requirements for seal pictures (300dpi) are getting bigger and bigger; the current common processing method is to process artificial ps software into transparent bottom pictures, but the existing manual ps software processing Method When processing electronic seals, it is necessary to manually operate the pictures continuously, and the processing method of electronic seals is cumbersome and inconvenient for staff to use
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
[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. 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.
[0036] see figure 1 , the present invention provides a technical solution: a method for in-depth processing of the front and back convolutional neural networks of graphic and text impressions, including:
[0037] S1, data preparation process: prepare the required data,
[0038] S11: Establish a convolutional neural network through a large number of positive and negative data of seals to obtain training result data;
[0039] S12: Obtain the training result of...
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 an image-text impression positive and negative convolutional neural network deep processing method. The method comprises the steps of S1, preparing data, specifically, S11, establishing a convolutional neural network through a lot of positive and negative data of a seal, and obtaining training result data; S12, obtaining a training result of Chinese fonts of the seal by using the method in S11; and S13, constructing a CNN model by referring to a network structure of LeNet, and obtaining a training result; S2, conducting data acquisition, specifically, S21, enabling multiple terminals to simultaneously obtain white background photographing impression picture files for synchronous identification; and S22, sending the picture files and the impression type parameters to a server, and stamping and filing; and S3, pre-processing the image. According to the invention, the seal picture is directly processed into the seal, the operation is relatively simple, a worker does not need to use ps to continuously operate the picture, and the use of the worker is facilitated.
Description
technical field [0001] The invention relates to the technical field of graphic and text impressions, in particular to a deep processing method of front and back convolutional neural networks of graphic and text impressions. Background technique [0002] Adobe Photoshop, referred to as "PS", is an image processing software developed and distributed by Adobe Systems. Photoshop mainly processes digital images composed of pixels. With its numerous editing and drawing tools, you can effectively edit pictures. ps has many functions, involving in image, graphics, text, video, publishing and other aspects [0003] With the continuous development of electronic seals and electronic contracts, the processing requirements for seal pictures (300dpi) are getting bigger and bigger; the current common processing method is to process artificial ps software into transparent bottom pictures, but the existing manual ps software processing Methods When processing electronic seals, it is necess...
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
CPCG06N3/045Y02T10/40
Inventor 田野
Owner 财悠悠科技(深圳)有限公司