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

An adaptive image toning method, system, storage medium and electronic device

An adaptive, image-based technology, applied in the field of image processing, can solve problems such as RGB three-channel incoordination, convergence difficulties, and the inability to promote batch operations based on algorithm rules

Active Publication Date: 2022-07-05
此刻启动北京智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For the GUI interface provided by the app, users can only manually test the image color, and need to try a combination of various indicators (brightness, contrast, etc.) transformations. If there is no relevant experience and knowledge, it may be difficult to achieve the expected results
In addition, manual color grading can only be used for a small number of pictures, and the algorithm cannot be extended to batch operations
And there is more redundancy in the degree of freedom in the prior art
In addition, the parameter learning process of the BP neural network tends to fall into local extremums, resulting in difficulty in convergence; because the parameter optimization of the three channels is independent to a certain extent, the RGB three channels of the output result may be inconsistent, resulting in a warmer overall tone of the image or cold

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
  • An adaptive image toning method, system, storage medium and electronic device
  • An adaptive image toning method, system, storage medium and electronic device
  • An adaptive image toning method, system, storage medium and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Example 1, use opencv-python to read the source image and the target image to preprocess the image, and convert the multi-dimensional array data structure ndarray used for mathematical operations in numpy into torch.tensor through the torch.from_numpy() method, where torch. .tensor is a tensor data structure used for mathematical operations in torch, similar to the previous ndarray, but tensor can build a computational graph, which is mostly used for transmission in neural networks. Convert the HWC format to CHW format by rearranging channels 2, 0, and 1 through the tensor.transpose() method, and then add the batch dimension, which should be understood as: the original tensor dimension is C×H×W , and add the batch dimension to the first position to become N×C×H×W. In the Pytorch deep learning framework, the tensor input to the network must have a batch dimension. This operation is to adapt to it and prepare for the input network. Build a convolutional layer with 3 inpu...

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 present invention relates to the field of image processing, in particular to an adaptive image toning method, system, storage medium and electronic device. The method includes: step 1, acquiring an image to be processed, a source image and a target image; step 2, preprocessing the source image and the target image to obtain the source image and the target image after the format conversion; step 3, by The BP neural network model is trained on the converted source image and the target image; step 4, the to-be-processed image is input into the BP neural network model to obtain an output result; step 5, white balance processing is performed on the output result , to get the final image. Through this method, the effect of making the RGB channels coordinated can be achieved.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an adaptive image toning method, system, storage medium and electronic device. Background technique [0002] The storage and presentation form of a general color image in a computer can be expressed as a tensor of dimension H×W×3. H and W are the height and width of the image respectively, and 3 represents the three channels of RGB (red, green and blue). The RGB three values ​​of each pixel point determine the color that the point presents. To realize the color adjustment algorithm of the image, it is essentially to transform the pixel values ​​of the whole image. The adjustment of brightness, contrast, saturation, etc. has corresponding rules for processing image pixel values. As for various filters, the same is true but the rules are more complicated. Therefore, image toning is logically achievable and also operational. [0003] For the GUI interface provided by the ...

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): G06T3/00G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06T3/04
Inventor 黄江勇刘成城王鹏霄李子实陈静李希贤李甡
Owner 此刻启动北京智能科技有限公司