Unlock instant, AI-driven research and patent intelligence for your innovation.

A halftone image classification method

A classification method and halftone technology, applied in the field of printing, can solve the problems of low accuracy rate and achieve the effect of improving accuracy rate, overcoming poor adaptability, and reducing time

Active Publication Date: 2018-07-06
SHANGHAI ADD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a halftone image classification method, which solves the problem of low correct rate of existing halftone image classification methods

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A halftone image classification method
  • A halftone image classification method
  • A halftone image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0031] A kind of halftone image classification method of the present invention, flow process is as follows figure 1 As shown, the specific steps are as follows:

[0032] Step 1, using the sparse self-encoding deep neural network as the feature extraction model of the halftone image, and the sparse self-encoding deep neural network is connected to the Softmax classifier;

[0033] Among them, the sparse self-encoding deep neural network includes 4 layers, the first layer is the input layer, and the number of neurons in the first layer is the number of pixels in the image block, such as the image block size is 16×16pixel, that is, the input layer The number of neurons is 256; the second and third layers are hidden layers, the number of neurons in the second and third layers are 200 and 100 respectively, the fourth layer is the output layer, and...

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

No PUM Login to View More

Abstract

The invention discloses a method for classifying halftone images, which is specifically implemented according to the following steps: using a sparse self-encoded deep neural network to connect a Softmax classifier as a classification model for halftone images; dividing halftone images for training into blocks, and using these Train the model in blocks; extract the effective blocks of the halftone image to be classified and classify these effective blocks; count the number of categories of each effective block of the halftone image to be classified, and take the category with the largest number of categories as the halftone to be classified The category of the image. The method for classifying halftone images of the present invention solves the problem of manual selection and extraction of halftone image features in the prior art, can adapt to various halftone images, and improves the accuracy of classification.

Description

technical field [0001] The invention belongs to the technical field of printing, and in particular relates to a halftone image classification method. Background technique [0002] Halftone image is a kind of image that contains only two tones, but can show continuous tone visual effect when observed by human eyes. It is widely used in traditional printing industry, digital publishing system, various binarization display and printout equipment and other fields. For halftone images generated by various halftone methods, if they are to be reused, visual noise such as textures generated during the halftone process must be removed. This technique is called inverse halftone technology. At present, various high-quality inverse halftone methods require first to know the corresponding halftone image category, that is, which halftone method produces the halftone image. Classifying halftone images according to the method by which they were produced is therefore a key step in the vari...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/24147
Inventor 张二虎张燕
Owner SHANGHAI ADD