An improved Retinex-based infrared image detail enhancement method
An infrared image and detail technology, applied in image enhancement, image analysis, image data processing, etc., to achieve the effects of eliminating local uneven brightness, solving halo problems, and optimizing computing efficiency
Pending Publication Date: 2019-04-05
BEIJING INST OF REMOTE SENSING EQUIP
View PDF3 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide an improved infrared image detail enhancement algorithm based on Retinex, which solves the halo problem that occurs when using the Retinex algorithm to enhance the details of the image in the case of uneven imaging brightness of the infrared image, and effectively improves algorithm processing rate
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
[0016] The following combination figure 1 Specific descriptions are given for specific implementations of the present invention.
[0017] An improved Retinex infrared image detail enhancement method proposed by the present invention is characterized in that the specific steps of the method are:
[0018] The first step is to process the brightness of the infrared image with the limited contrast adaptive histogram equalization (CLAHE) algorithm
[0019] Contrast-limited adaptive histogram equalization processing includes: image block processing (1), block histogram statistics (2), and histogram clipping and mapping processing (3).
[0020] The image block processing (1) is: the original infrared image source src is divided into 8 blocks by row, and then divided into 8 blocks by column, and is divided into 64 blocks in total;
[0021] The block histogram statistics (2) is: according to the infrared image is divided into 64 images in the image block processing step, each image i...
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 improved Retinex-based infrared image detail enhancement method, and the method comprises the steps: 1, carrying out the contrast-limited adaptive histogram equalization processing of an original infrared image, and enabling the number of pixels of the image in a certain gray scale range to be roughly the same; 2, transforming the equalized infrared image from a real number domain to a logarithmic domain so as to remove multiplicative noise in the image; Step 3, performing low-pass filtering processing on the infrared image on the logarithm domain by using a mean filter; And 4, converting the infrared image with enhanced details from the logarithm domain to the real number domain, and linearly stretching and converting the infrared image into corresponding pixelprecision. Compared with a traditional Retinex method, the method disclosed by the invention has the advantages that the operation is simple; The infrared image is subjected to self-adaptive equalization processing firstly, so that the brightness of the original image is equalized, the problem of halo generated at the edge of an area with large brightness difference in a traditional Retinex methodis solved, a Gaussian filter with complex calculated amount is replaced by a mean filter, and the operation efficiency is improved.
Description
technical field [0001] The invention relates to the technical field of infrared image enhancement. The invention designs an improved method for enhancing details of infrared images based on Retinex. Background technique [0002] Infrared thermal imaging technology is an image information detection technology based on receiving radiation energy. It reflects the specific content and detailed texture information of the scene image by observing the radiation difference between the target and the background in the field of view. In essence, it is also a wavelength conversion technology, which first converts the received infrared wavelength radiation into a voltage or current signal, and then expresses the electrical signal in the form of grayscale, and then converts it into a visible image in the visible wavelength range. This technical process completes the conversion of invisible light signals to electrical signals and then to visible light signals. [0003] As a modern high-t...
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 IPC IPC(8): G06T5/00
CPCG06T2207/10048G06T5/94G06T5/70
Inventor 李欣致刘志哲马承光修于杰余牧溪
Owner BEIJING INST OF REMOTE SENSING EQUIP