An automatic image enhancement system and method for fusing multi-scale information

An automatic image enhancement system technology, applied in the field of image processing, can solve problems such as inability to fuse context information, achieve the effect of enhancing target contrast and suppressing image noise

CN108492271BActive Publication Date: 2021-08-24CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
7 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-08-24

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an automatic image enhancement system and method for fusing multi-scale information, comprising: a sample calibration module: collecting training set images, marking the training set images at the pixel level, determining the mapping range of labels, and obtaining corresponding reference standard images; Automatically build the network module: input the corresponding reference standard image, specify the image range to be perceived, automatically calculate the size and number of convolution kernels in the multi-scale fusion module, and generate a convolutional neural network model; automatically train the network module: use the stochastic gradient descent method Optimize the pixel weighted loss function, train the convolutional neural network model offline; network application module: input a new image to the trained network, and output an enhanced image of the original image size. The present invention effectively utilizes context information by fusing multi-scale features to automatically enhance images without manual intervention.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of image processing, in particular to an automatic image enhancement system and method for fusing multi-scale information. Background technique

[0002] Image enhancement is one of the basic contents of image processing. According to a specific requirement, the useful information in the image is highlighted, and the useless information is removed or weakened. The purpose is to improve image quality, and the processed results are more suitable for human visual characteristics or machine recognition systems. Image enhancement technology has been widely used in medical diagnosis, aerospace, non-destructive detection, satellite image processing and other fields.

[0003] Common image enhancement technologies are mostly based on image statistical information, using low-pass filtering, median filtering and other methods to remove noise in the image; using high-pass filtering, wavelet transform, etc. to enhance edges to mak...

Examples

Embodiment Construction

[0051] The embodiments of the present invention are described in detail below. This embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following implementation example.

[0052] see image 3 : An automatic image enhancement system that fuses multi-scale information, including the following modules:

[0053] Sample calibration module: collect the training set images, mark the training set images at the pixel level, determine the mapping range of the labels, and obtain the corresponding reference standard images;

[0054] Automatically construct the network module: input the corresponding reference standard image, specify the image range to be perceived, automatically calculate the size and number of convolution kernels in the multi-scale fusion module, and generate a convolutional neu...