CN-122023202-A - Image stripe correction method and device, electronic equipment and storage medium

CN122023202ACN 122023202 ACN122023202 ACN 122023202ACN-122023202-A

Abstract

The invention relates to an image stripe correction method, an image stripe correction device, an electronic device and a storage medium, wherein the method comprises the steps of responding to a correction instruction, acquiring a brightness channel image and a stripe direction; the brightness channel image is subjected to bright stripe detection along the stripe direction, a bright stripe area corresponding to the brightness channel image is determined, the current average gray level corresponding to the bright stripe area is calculated, an adjustment proportion coefficient is determined based on the current average gray level, the recorded average gray level and the area of the stripe area, a gain adjustment coefficient is determined based on the adjustment proportion coefficient, the current average gray level and the recorded average gray level, a gain adjustment coefficient is utilized to adjust a current gain value to obtain a target gain value, the pixel gray level corresponding to the bright stripe area is corrected based on the target gain value to obtain a target channel image, and the target channel image is used for replacing the brightness channel image. By adopting the technical scheme provided by the invention, the accuracy and timeliness of image streak correction are improved, and the accuracy and safety of operation are ensured.

Inventors

XIN LILI
XING QINGFENG
WANG JIWEI
CHEN DONG

Assignees

新光维医疗科技(苏州)股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251210

Claims (10)

1. A method of image streak correction, the method comprising: Responding to a correction instruction, and acquiring a brightness channel image and a stripe direction corresponding to the brightness channel image; Adopting a brightness change detection algorithm or an edge detection algorithm to detect bright stripes of the brightness channel image along the stripe direction corresponding to the brightness channel image, and determining a bright stripe region corresponding to the brightness channel image; calculating the current average gray level corresponding to the bright stripe region, and determining an adjustment proportion coefficient based on the current average gray level, the recorded average gray level and the area of the stripe region corresponding to the bright stripe region, wherein the recorded average gray level is the average gray level value recorded by the bright stripe region in an undisturbed state; determining a gain adjustment coefficient based on the adjustment proportion coefficient, the current average gray level and the recorded average gray level through a preset control algorithm, and adjusting a current gain value by utilizing the gain adjustment coefficient to obtain a target gain value; And correcting the pixel gray value corresponding to the bright stripe region based on the target gain value to obtain a target channel image, and replacing the brightness channel image by using the target channel image.
2. The method of claim 1, wherein the employing a brightness change detection algorithm to detect bright stripes of the brightness channel image along the stripe direction corresponding to the brightness channel image, and determining the bright stripe region corresponding to the brightness channel image comprises: Image blocking is carried out on the brightness channel image along the stripe direction corresponding to the brightness channel image, so that a plurality of brightness image blocks are obtained; Calculating a block gray average value and a block gray standard deviation of each brightness image block; Comparing the block gray average value with a preset gray average value, and taking a brightness image block corresponding to the block gray average value larger than the preset gray average value as a first target image block; Comparing the block gray standard deviation corresponding to the first target image block with a preset gray standard deviation, taking the first target image block with the block gray standard deviation smaller than the preset gray standard deviation as a second target image block, and combining the second target image block to form the bright stripe region.
3. The method of claim 1, wherein the employing an edge detection algorithm to detect bright stripes of the luminance channel image along a stripe direction corresponding to the luminance channel image, and determining a bright stripe region corresponding to the luminance channel image comprises: Performing edge detection on the brightness channel image along the stripe direction corresponding to the brightness channel image to obtain a plurality of edge image blocks; Calculating the characteristic values of the plurality of edge image blocks to obtain edge characteristic values corresponding to each edge image block; Comparing the edge characteristic value with a preset characteristic value, and determining an edge image block with the edge characteristic value smaller than the preset characteristic value as an interference image block; And calculating the gradient change quantity of the interference image blocks, determining the interference image blocks with the gradient change quantity larger than the preset gradient change quantity as target image blocks, and combining the target image blocks to form the bright stripe region.
4. The method of claim 1, wherein the determining an adjustment scaling factor based on the current average gray level, a recorded average gray level, and a stripe area corresponding to the bright stripe area comprises: Acquiring the current image area of the brightness channel image; determining an area ratio corresponding to the bright stripe area based on the current image area and the stripe area; determining an average gray level difference based on the current average gray level and the recorded average gray level; dividing calculation is carried out based on the average gray level difference value and the recorded average gray level, and gray level change is determined; the adjustment scaling factor is determined based on the area duty cycle, the gray level variation, and the current average gray level.
5. The method of claim 4, wherein the determining the adjustment scaling factor based on the area duty cycle, the gray level variation, and the current average gray level comprises: Acquiring a sensitivity adjustment constant, a preset area occupation ratio and a gray scale influence coefficient; Adjusting the influence sensitivity based on the sensitivity adjustment constant, the preset area occupation ratio and the area occupation ratio to obtain the current influence area occupation ratio; based on the gray scale influence coefficient and the gray scale change, gray scale influence adjustment is carried out, and the current influence gray scale is determined; And determining the adjustment scaling factor based on the current impact area occupation ratio and the current impact gray scale.
6. The method of claim 1, wherein said adjusting the current gain value using the gain adjustment factor comprises: gain conversion coefficients are obtained; determining a conversion gain value based on the gain adjustment coefficient and the gain conversion coefficient; The target gain value is determined based on the current gain value and the conversion gain value.
7. The method of claim 1, wherein prior to acquiring the luminance channel image, the method further comprises: Acquiring user operation information, and determining a mode entry path based on the user operation information; And entering an operation mode based on the mode entering path, and acquiring an endoscope image corresponding to the operation mode to extract the brightness channel image.
8. An image streak correction apparatus, the apparatus comprising: the acquisition module is used for responding to the correction instruction and acquiring a brightness channel image and a stripe direction corresponding to the brightness channel image; The detection module is used for detecting bright stripes of the brightness channel image along the stripe direction corresponding to the brightness channel image by adopting a brightness change detection algorithm or an edge detection algorithm, and determining a bright stripe area corresponding to the brightness channel image; The system comprises a determination module, a control module and a display module, wherein the determination module is used for calculating the current average gray level corresponding to the bright stripe region, determining an adjustment proportion coefficient based on the current average gray level, the recorded average gray level and the stripe region area corresponding to the bright stripe region, wherein the recorded average gray level is the average gray level value recorded by the bright stripe region in an undisturbed state; The gain module is used for determining a gain adjustment coefficient through a preset control algorithm based on the adjustment proportion coefficient, the current average gray level and the recorded average gray level, and adjusting a current gain value by utilizing the gain adjustment coefficient to obtain a target gain value; And the correction module is used for correcting the pixel gray value corresponding to the bright stripe region based on the target gain value to obtain a target channel image, and replacing the brightness channel image by using the target channel image.
9. An electronic device, comprising: A processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the image streak correction method of any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the image streak correction method according to any one of claims 1 to 7.

Description

Image stripe correction method and device, electronic equipment and storage medium Technical Field The present invention relates to the field of image streak correction technology, and in particular, to an image streak correction method, an image streak correction device, an electronic apparatus, and a storage medium. Background In minimally invasive surgery such as laser/electrohydraulic lithotripsy, an endoscope imaging system is a core vision support for a doctor to observe an in-vivo surgery area and perform accurate operation, and the stability and definition of imaging quality are directly related to the efficiency and safety of the surgery. However, energy devices used in surgical procedures, such as holmium lasers, produce extremely strong, instantaneous flashes of light at the moment of firing. The sudden strong light is extremely easy to exceed the dynamic range of an endoscope image sensor, so that local overexposure occurs in the acquired image, and obvious bright white stripes are formed. The existing endoscope system generally has Automatic Exposure Control (AEC) and Automatic Gain Control (AGC) functions, but the control strategy is mainly designed for the slow change of the overall brightness of a scene, and has two inherent defects that firstly, the response speed is relatively slow, the instantaneous light intensity change of millisecond level such as laser pulse is difficult to follow, and secondly, the adjustment mode is generally overall unified adjustment, namely, when bright stripes appear locally, the system can reduce the gain or exposure of the whole picture, thereby reducing the overall brightness of an image non-interference area and losing details, darkening the operation visual field and influencing the observation of normal tissues and stones by doctors. Therefore, the prior art cannot effectively eliminate bright streak interference caused by instantaneous strong light, and ensure the normal display quality of a non-interference area of an image, so that the problem needs to be solved. Therefore, there is an urgent need in the art for a new image streak correction method. Disclosure of Invention In view of this, the embodiment of the invention provides an image streak correction method, an image streak correction device, an electronic device and a storage medium, which can quickly and accurately inhibit local bright streak interference caused by instantaneous strong light (such as laser) in an endoscopic operation, and simultaneously avoid negative influence on brightness and details of a non-interference area of an image, thereby providing a clear and stable whole-course operation field for doctors and guaranteeing the accuracy and safety of the operation. One aspect of the present invention provides an image streak correction method including the steps of: Responding to a correction instruction, and acquiring a brightness channel image and a stripe direction corresponding to the brightness channel image; Adopting a brightness change detection algorithm or an edge detection algorithm to detect bright stripes of the brightness channel image along the stripe direction corresponding to the brightness channel image, and determining a bright stripe region corresponding to the brightness channel image; calculating the current average gray level corresponding to the bright stripe region, and determining an adjustment proportion coefficient based on the current average gray level, the recorded average gray level and the area of the stripe region corresponding to the bright stripe region, wherein the recorded average gray level is the average gray level value recorded by the bright stripe region in an undisturbed state; determining a gain adjustment coefficient based on the adjustment proportion coefficient, the current average gray level and the recorded average gray level through a preset control algorithm, and adjusting a current gain value by utilizing the gain adjustment coefficient to obtain a target gain value; And correcting the pixel gray value corresponding to the bright stripe region based on the target gain value to obtain a target channel image, and replacing the brightness channel image by using the target channel image. Another aspect of the present invention provides an image streak correction apparatus, the apparatus including: the acquisition module is used for responding to the correction instruction and acquiring a brightness channel image and a stripe direction corresponding to the brightness channel image; The detection module is used for detecting bright stripes of the brightness channel image along the stripe direction corresponding to the brightness channel image by adopting a brightness change detection algorithm or an edge detection algorithm, and determining a bright stripe area corresponding to the brightness channel image; The system comprises a determination module, a control module and a display module, wherein the determination module is used for calc