Method, device and computer equipment for image enhancement

Abstract

The application provides a method for image enhancement, comprising: when a target image is acquired, acquiring redundant information data contained in target image data, the redundant information data being used for reflecting image data to be denoised in the target image data; performing denoising processing on the target image data according to the redundant information data and the image data to be denoised to obtain denoised image data; performing edge enhancement processing on the denoised image data to obtain edge enhanced image data, so as to obtain an edge enhanced image, the edge enhanced image data containing gray value data, the gray value data being used for reflecting contrast data contained in the edge enhanced image; and performing contrast enhancement processing on the edge enhanced image according to the gray value data to obtain an enhanced image. In addition, the application also provides an image enhancement device and a computer device. The technical scheme of the application realizes the effective reduction of image noise while improving the visible details of an infrared image.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus and computer device for image enhancement. Background Technology

[0002] In infrared image acquisition, the light used by the sensor differs from that of visible light, and the sensor digitizes the radiation. After acquiring the infrared image, the imaging process often requires defining a fixed visible temperature range, such as 100 degrees Celsius. However, this imaging process suffers from low visible contrast. Furthermore, due to the limited imaging conditions, the imaging process generates high image noise, significantly impacting subsequent image processing and the final result. Summary of the Invention

[0003] This application provides an image enhancement method, apparatus, and computer device that improves the visible details of infrared images while effectively reducing image noise.

[0004] In a first aspect, embodiments of this application provide an image enhancement method, the image enhancement method comprising: when a target image is acquired, acquiring redundant information data contained in a target image data packet, the redundant information data being used to reflect image data to be denoised in the target image data; performing denoising processing on the target image data according to the redundant information data and the image data to be denoised to obtain denoised image data; performing edge enhancement processing on the denoised image data to obtain edge-enhanced image data, thereby obtaining an edge-enhanced image, the edge-enhanced image data packet containing grayscale value data, the grayscale value data being used to reflect contrast data contained in the edge-enhanced image; and performing contrast enhancement processing on the edge-enhanced image according to the grayscale value data to obtain an enhanced image.

[0005] Secondly, embodiments of this application provide an image enhancement apparatus. The apparatus for acquiring enhanced image data includes an image data acquisition module, a first image data processing module, a second image data acquisition module, and an image processing module. When a target image is acquired, the image data acquisition module acquires redundant information data contained in the target image data packet. The redundant information data reflects the image data to be denoised in the target image data. The first image data processing module performs denoising processing on the target image data based on the redundant information data and the image data to be denoised to obtain denoised image data. The second image data processing module performs edge enhancement processing on the denoised image data to obtain edge-enhanced image data, thereby obtaining an edge-enhanced image. The edge-enhanced image data packet contains grayscale value data, which reflects the contrast data contained in the edge-enhanced image. The image processing module performs contrast enhancement processing on the edge-enhanced image based on the grayscale value data to obtain an enhanced image.

[0006] Thirdly, embodiments of this application provide a computer device, the computer device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the above-described image enhancement method.

[0007] The aforementioned image enhancement method, apparatus, and computer equipment acquire a target image to obtain target image data, perform noise reduction processing on the target image data to obtain denoised image data, perform edge enhancement processing on the denoised image data to obtain edge-enhanced image data, and then perform contrast enhancement processing on the edge-enhanced image to obtain an enhanced image. This achieves both improved visible details in infrared images and effective reduction of image noise, facilitating subsequent image processing. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0009] Figure 1 This is a first flowchart of an image enhancement method provided in an embodiment of this application.

[0010] Figure 2 A second flowchart of an image enhancement method provided in an embodiment of this application.

[0011] Figure 3A flowchart of step S102 provided in the embodiments of this application.

[0012] Figure 4 A flowchart of step S103 provided in the embodiments of this application.

[0013] Figure 5 A flowchart of step S104 provided in the embodiments of this application.

[0014] Figure 6 A flowchart of sub-step S1043 provided for embodiments of this application.

[0015] Figure 7 A flowchart of sub-step S1044 provided for embodiments of this application.

[0016] Figure 8 This is a schematic diagram of the structure of the image enhancement device provided in the embodiments of this application.

[0017] Figure 9 This is a schematic diagram of the internal structure of a computer device for applying an image enhancement method according to an embodiment of this application.

[0018] Figure 10 A flowchart illustrating the image noise reduction process provided in this application embodiment.

[0019] Figure 11 A flowchart for image contrast enhancement provided in an embodiment of this application.

[0020] Figure 12 A first schematic diagram of an enhanced image provided for an embodiment of this application.

[0021] Figure 13 A second schematic diagram of an enhanced image provided for an embodiment of this application.

[0022] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0024] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar planned objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data are interchangeable where appropriate; in other words, the described embodiments are implemented according to a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, may also include other content; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] It should be noted that the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0026] Please refer to Figure 2 This is a second flowchart of an image enhancement method provided in an embodiment of this application. The image enhancement method includes step S100.

[0027] Step S100: When the image to be enhanced is obtained, the image data to be enhanced is obtained and the image data to be enhanced is converted to obtain the target image data, so as to obtain the target image.

[0028] In step S100, the image to be enhanced is a MIPI format image. Correspondingly, the format of the image data to be enhanced is an uncompressed raw image format (RAW Image Format). RAW is used to store data generated by the camera, such as shutter speed, aperture value, white balance, etc. In this embodiment, the image to be enhanced can be acquired by a shooting device, such as a camera, a sensor for acquiring infrared images, etc. Preferably, the target image data is uncompressed 16-bit RAW image data. 16-bit RAW image data can store more tonal information in the dark areas, thus having a considerable advantage within the image's exposure range. At the same time, the data volume of 16-bit RAW image data is large enough to ensure sufficient depth for subsequent processing. The aforementioned 16-bit RAW image data is only a preferred example of the target image data and is not a limitation on the target image data. The target image data can also be other image data with characteristics such as being uncompressed and having a large data storage capacity, which will not be elaborated here.

[0029] The following will describe the specific steps of image enhancement methods to illustrate how to obtain an enhanced image through image processing after acquiring the target image.

[0030] Please refer to Figure 1 This is a first flowchart of an image enhancement method provided in an embodiment of this application. The image enhancement method further includes steps S101-S104.

[0031] Step S101: When the target image is obtained, the redundant information data contained in the target image data packet is obtained.

[0032] In step S101, redundant information data is used to reflect the image data to be denoised in the target image data, thereby identifying the image data in the target image data that requires denoising processing. In this embodiment, the redundant information data can be the similarity between multiple target image data. Specifically, several reference image data are set in the target image data, such that the similarity of the reference image data is used to measure the similarity between its neighboring target image data, thereby determining that target image data with excessively high or low similarity is the image data to be denoised.

[0033] Step S102: Based on the redundant information data and the image data to be denoised, the target image data is denoised to obtain denoised image data.

[0034] In step S102, a preset denoising algorithm can be used to denoise the target image data. Preferably, this embodiment uses the NL-Means denoising algorithm to denoise the 16-bit Raw image data. The NL-Means denoising algorithm is a non-local mean denoising algorithm that can utilize the redundant information data contained in the 16-bit Raw image data for denoising. Here, the redundant information data is the similarity between the target image data adjacent to the reference image data or between image patches formed by the target image data. Specifically, the NL-Means algorithm can be represented by Equation 1.

[0035]

[0036] In Equation 1, I is the input image, I ′ ω is the output image, N is the neighborhood of a pixel, ω is the weight function used to measure the similarity between two neighborhoods, and C is the normalization constant used to ensure that the sum of the weights is 1.

[0037] Please refer to Figure 3 The flowchart below shows step S102, a sub-step provided in this embodiment. Steps S1021-S1024 involve performing noise reduction processing on the target image data based on redundant information data and the image data to be denoised.

[0038] Step S1021: Based on the redundant information data, the target image data is divided into several sub-target image data.

[0039] In step S1021, the redundant information data is the similarity between sub-target image data. Understandably, when sub-target image data is aggregated into sub-target image patches, the redundant information data is the similarity between alphabet image patches.

[0040] Step S1022: Assign weights to each sub-target image data based on similarity.

[0041] In step S1022, after acquiring multiple sub-target image data, several reference target image data are determined from the multiple sub-target image data, so that the other sub-target image data are assigned weights proportionally according to preset weights based on the similarity between the reference target image data and other sub-target image data.

[0042] Step S1023: Based on the weights, perform noise reduction processing on each sub-target image data to obtain the corresponding noise-reduced image data.

[0043] In step S1023, the weights can be based on similarity to influence the required noise reduction amplitude of the corresponding sub-target image data, thereby being applicable to each sub-target image data, so that the sub-target image data can achieve the effect of being suitable for the reference target image data after noise reduction processing.

[0044] Step S1024: Obtain the denoised image data based on each corresponding denoised image data.

[0045] In step S1024, after acquiring multiple corresponding denoised image data, the multiple corresponding denoised image data are combined to obtain denoised image data, so that the multiple corresponding denoised image data correspond to the target image data. After the combination is completed, the denoised image data is converted into a denoised image for output, so as to facilitate subsequent image processing.

[0046] Please refer to the following: Figure 10 This is a flowchart of the image noise reduction process provided in the embodiments of this application. The following will be combined with... Figure 10 This section will explain the specific steps involved in noise reduction using the NL-Means noise reduction algorithm.

[0047] like Figure 10 As shown, after receiving the input 16-bit Raw image data, the 16-bit Raw image data is first aggregated to form image blocks. After identifying several reference image data, the data is divided according to the reference image data to form several reference image blocks and several image blocks to be denoised. After obtaining several reference image blocks and several image blocks to be denoised, the similarity between the reference image blocks and their neighboring image blocks to be denoised is calculated. Based on the reference image data and the calculated similarity, the similarity is normalized. After assigning weights to the normalized image blocks, the corresponding denoised image is output according to Equation 1. The above NL-Means denoising algorithm is only a preferred example of a denoising algorithm and is not a limitation on denoising algorithms. Other denoising algorithms that at least have the characteristics of aggregating and dividing image blocks, calculating image block similarity, normalizing, and assigning corresponding weights to image blocks can also be used to denoise the input image, which will not be elaborated here.

[0048] Step S103: Perform edge enhancement processing on the denoised image data to obtain edge-enhanced image data, thereby obtaining an edge-enhanced image.

[0049] In step S103, the edge enhancement process involves performing a Laplacian transform on the denoised image data. The edge enhancement image data packet contains grayscale value data. The grayscale value data reflects the contrast data contained in the edge enhancement image.

[0050] Please refer to Figure 4 This is a flowchart of step S103 provided in the embodiments of this application. Steps S1031-S1032 involve performing edge enhancement processing on the denoised image data to obtain edge-enhanced image data, thereby obtaining an edge-enhanced image.

[0051] Step S1031: Construct the convolution kernel for Laplace transform processing.

[0052] In step S1031, the convolution kernel is obtained from the denoised image data.

[0053] Step S1032: Based on the convolution kernel, perform Laplacian transform on the denoised image to obtain edge-enhanced image data.

[0054] While acquiring the edge-enhanced image, the grayscale data corresponding to each image data or image block in the edge-enhanced image are also acquired, i.e., contrast data. Contrast data represents the contrast of different parts of the image, measuring the image quality and the amount of detail displayed. When the image contrast is too low or too high, it affects both the reading of image details and subsequent image processing. Therefore, contrast enhancement algorithms can be used to enhance the image contrast, ensuring image fidelity while revealing more details. Preferably, this embodiment uses the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm to enhance the contrast of the edge-enhanced image data. The CLAHE algorithm is an adaptive histogram equalization algorithm that enhances the contrast of local images by limiting the contrast in the image data, thereby improving the overall visibility of the image. Specifically, in the CLAHE algorithm, the contrast amplification near a given pixel value is given by the slope of the transformation function, which is proportional to the slope of the Cumulative Distribution Function (CDF) of the neighborhood, and therefore proportional to the histogram value of that pixel value. The CLAHE algorithm limits the amplification by cropping the histogram to a predefined value before calculating the CDF, and then equalizes the cropped histogram to obtain a new histogram, thus resulting in an image with enhanced contrast.

[0055] Step S104: Based on the grayscale data, perform contrast enhancement processing on the edge enhancement image to obtain the enhanced image.

[0056] In this embodiment, some steps of the CLAHE algorithm are improved, specifically in histogram equalization. In the traditional CLAHE algorithm, only the height of the histogram is cropped. However, in this embodiment, in addition to cropping the histogram in the height direction, the width direction is also cropped to reduce potential instability near the midpoints of the histogram, resulting in a more balanced histogram. This leads to an overall balanced image while better revealing image details. The specific steps of contrast enhancement will be explained below in conjunction with the specific steps of image enhancement methods.

[0057] Please refer to Figure 5 This is a flowchart of step S104, a sub-step provided in the embodiments of this application. The enhanced image is obtained by performing contrast enhancement processing on the edge enhancement image based on grayscale data, including steps S1041-S1044.

[0058] Step S1041: Divide the edge enhancement image into several sub-edge enhancement images.

[0059] Step S1042: Obtain the grayscale value data contained in each sub-edge enhancement image to obtain several grayscale histograms.

[0060] Step S1043: According to the preset cropping threshold, each grayscale histogram is cropped to obtain several cropped grayscale histograms.

[0061] In step S1043, the cropped grayscale histogram is a histogram of the cropped portion of grayscale data, where the cropped grayscale data consists of grayscale values ​​that do not meet the preset cropping threshold. For the histogram, the cropped grayscale data represents anomalous data compared to other grayscale values, which may be caused by factors such as the image acquisition environment or abnormal segmentation of the sub-edge enhancement image. The cropped grayscale histogram includes a first cropped grayscale histogram representing the cropping direction along the height direction of the grayscale histogram, and a second cropped grayscale histogram representing the cropping direction along the width direction of the grayscale histogram.

[0062] Please refer to Figure 6 This is a flowchart of step S1043 provided in the embodiments of this application. Steps S10431-S10433 involve cropping each grayscale histogram according to a preset cropping threshold to obtain several cropped grayscale histograms.

[0063] Step S10431: Compare the grayscale data contained in each sub-edge enhancement image with the preset cropping threshold to determine whether the corresponding grayscale histogram needs to be cropped.

[0064] In step S10431, the preset cropping threshold includes a preset upper cropping threshold and a preset lower cropping threshold.

[0065] Step S10432: When the grayscale value data is greater than the preset upper limit threshold for cropping or less than the preset lower limit threshold for cropping, the corresponding grayscale histogram needs to be cropped.

[0066] Step S10433: When the grayscale value data is greater than or equal to the preset lower cropping threshold and less than or equal to the preset upper cropping threshold, the corresponding grayscale histogram does not need to be cropped.

[0067] Step S1044: Based on partial grayscale data and several cropped grayscale histograms, several target grayscale histograms are obtained, and the edge enhancement image is converted into an enhancement image based on the several target grayscale histograms.

[0068] In step S1044, after obtaining several cropped grayscale histograms, all cropped grayscale histograms are combined and grayscale value data is combined to enhance the grayscale value to increase the contrast data of the histogram, so as to obtain the target grayscale histogram and the grayscale histogram of the image corresponding to the edge enhancement of the target grayscale histogram.

[0069] Please refer to Figure 7 The flowchart below shows step S1044, which is a sub-step provided in the embodiments of this application. Steps S10441-S10442 involve obtaining several target grayscale histograms based on partial grayscale value data and several cropped grayscale histograms.

[0070] Step S10441: Obtain the cropped grayscale histogram corresponding to each part of the grayscale data.

[0071] Step S10442: Divide each part of grayscale data equally into the corresponding cropped grayscale histogram to obtain several target grayscale histograms.

[0072] In step S10442, after obtaining the number of gray values ​​in the cropped grayscale histogram, the corresponding grayscale value data is evenly distributed to each grayscale value in the cropped grayscale histogram and summed to enhance each grayscale value in the cropped grayscale histogram.

[0073] Please refer to the following: Figure 11 This is a flowchart of image contrast enhancement provided in an embodiment of this application. The following will be combined with… Figure 11 This section will explain the specific steps involved in enhancing image contrast using the CLAHE algorithm.

[0074] like Figure 11 As shown, after acquiring the edge enhancement image, the histograms of each part of the edge enhancement image are first calculated to obtain grayscale histograms. Then, according to a preset cropping threshold, the grayscale histograms are cropped in both the height and width directions to obtain a first cropped grayscale histogram and a second cropped grayscale histogram, respectively, and the corresponding cropped grayscale values ​​are obtained. After acquiring the first and second cropped grayscale histograms, the CDF of the cropped grayscale histograms is calculated to obtain the grayscale distribution of the cropped grayscale histograms. Based on the cropped grayscale histograms and the grayscale distribution, the corresponding cropped grayscale values ​​are evenly distributed in the cropped grayscale histograms for contrast enhancement to obtain the target grayscale histogram. After obtaining the target grayscale histogram, it is combined with the edge enhancement image to obtain the enhanced image with enhanced contrast.

[0075] Specifically, if the number of pixels with a value of i in the grayscale histogram of each part is set to hist[i], then the grayscale histogram can be represented by Equation 2.

[0076]

[0077] In Equation 2, cumulative_hist[i] represents the total number of pixels with pixel number i in the grayscale histogram.

[0078] The preset cropping threshold, the preset upper cropping threshold and the preset lower cropping threshold can be expressed by Equation 3 and Equation 4, respectively.

[0079] lower_threshold = p low *cumulative_hist[max] (Equation 3)

[0080] upper_threshold = p high *cumulative_hist[max] (Equation 4)

[0081] In Equation 3, lower_threshold represents the preset lower threshold for cropping, p low This represents the preset lower cropping limit ratio. The preset lower cropping limit ratio can be set according to the edge enhancement image and the expected enhancement. In Equation 4, upper_threshold represents the preset upper cropping threshold, p high This indicates the preset upper cropping limit ratio. Similarly, the preset lower cropping limit ratio can be set according to the edge enhancement image and the expected enhancement effect.

[0082] After obtaining the preset upper and lower cropping thresholds using Equations 3 and 4, the preset cropping thresholds need to be applied to the cropping of the grayscale histogram. Specifically, for the width direction of the grayscale histogram, starting from both ends, pixel values ​​are gradually subtracted according to the preset cropping thresholds. For example, for the lowest pixel value, starting from i = 0, hist[i] is subtracted from lower_threshold each time until lower_threshold = 0, and then the current i is assigned to lower_threshold to complete the cropping of the lower limit of the grayscale histogram. Similarly, for the highest pixel value, starting from i = 255, hist[i] is subtracted from upper_threshold each time until upper_threshold = 0, and then the current i is assigned to upper_threshold to complete the cropping of the upper limit of the grayscale histogram.

[0083] Please refer to Figure 12 and Figure 13 , Figure 12 This is a first schematic diagram of an enhanced image provided in an embodiment of this application. Figure 13 A second schematic diagram of an enhanced image provided for an embodiment of this application.

[0084] like Figure 12 and Figure 13 As shown, the enhanced images obtained using traditional image processing methods include a first traditional enhanced image 10, a second traditional enhanced image 20, and a third traditional enhanced image 30. The enhanced images obtained after denoising using the NL-Means denoising algorithm and enhancing contrast using the CLAHE algorithm include a first enhanced image 40, a second enhanced image 50, and a third enhanced image 60. (Comparison) Figure 12 and Figure 13 As can be seen, compared with the enhanced images obtained by traditional image processing methods, the enhanced images obtained in this application are significantly superior in terms of image detail and image contrast. For example, in the case of the same photographed object, the details of distant buildings in the third enhanced image 60 are significantly better than the details of distant buildings in the third traditional enhanced image 30, and the details of reflective objects in the second enhanced image 50 are also significantly better than the details of reflective objects in the second traditional enhanced image 20.

[0085] Please refer to Figure 8 This is a schematic diagram of the structure of the image enhancement device provided in the embodiments of this application.

[0086] like Figure 8 As shown, the image enhancement device 11 includes an image data acquisition module 110, a first image data processing module 111, a second image data acquisition module 112, an image processing module 113, and an image data conversion module 114.

[0087] When the target image is acquired, the image data acquisition module 110 is used to acquire the redundant information data contained in the target image data packet. The redundant information data is used to reflect the image data to be denoised in the target image data.

[0088] The first image data processing module 111 is used to perform noise reduction processing on the target image data based on redundant information data and the image data to be denoised to obtain denoised image data.

[0089] The second image data processing module 112 is used to perform edge enhancement processing on the denoised image data to obtain edge enhanced image data, so as to obtain an edge enhanced image. The edge enhanced image data package contains grayscale value data, which is used to reflect the contrast data contained in the edge enhanced image.

[0090] The image processing module 113 is used to perform contrast enhancement processing on the edge enhancement image based on grayscale value data to obtain an enhanced image.

[0091] When the image to be enhanced is acquired, the image data conversion module 114 is used to acquire the image data to be enhanced and perform data conversion on the image data to obtain the target image data, so as to obtain the target image.

[0092] Please refer to Figure 9 This is a schematic diagram of the internal structure of a computer device for applying the image enhancement method provided in the embodiments of this application.

[0093] like Figure 9 As shown, the computer device 100 includes a memory 901 and a processor 902. The processor 902 is used to execute computer program instructions stored in the memory 901 to implement an image enhancement method.

[0094] The memory 901 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 901 can be an internal storage unit of a computer device, such as a hard disk. In other embodiments, the memory 901 can be an external storage device of a computer device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., configured in the computer device. Furthermore, the memory 901 can include both internal and external storage units of the computer device. The memory 901 can be used not only to store application software and various types of data installed on the computer device, such as code for image enhancement methods, but also to temporarily store data that has been output or will be output.

[0095] Furthermore, the computer device 100 also includes a bus 903. The bus 903 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0096] Furthermore, the computer device 100 may also include a display component 904. The display component 904 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display component 904 may also be appropriately referred to as a display device or display unit, used to display information processed in the computer device 100 and to display a visual user interface.

[0097] Furthermore, the computer device 100 may also include a communication component 905. The communication component 905 may optionally include a wired communication component and / or a wireless communication component (such as a Wi-Fi communication component, a Bluetooth communication component, etc.), which is typically used to establish a communication connection between the computer device 100 and other computer devices.

[0098] Figure 9 Only a partial computer device 100 with some components and methods for applying image enhancement is shown; those skilled in the art will understand that... Figure 9 The structure shown does not constitute a limitation on the computer device 100 and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0099] In the above embodiments, target image data is obtained by acquiring a target image, noise reduction processing is performed on the target image data to obtain noise-reduced image data, edge enhancement processing is performed on the noise-reduced image data to obtain edge-enhanced image data, and finally, contrast enhancement processing is performed on the edge-enhanced image to obtain an enhanced image. This achieves the improvement of visible details in the infrared image while effectively reducing image noise for subsequent image processing.

[0100] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0101] The above-listed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A method of image enhancement, characterized by, The method for image enhancement comprises: When the target image is acquired, redundant information data contained in target image data is acquired, the redundant information data being used for reflecting image data to be denoised in the target image data; According to the redundant information data and the image data to be denoised, denoised image data is obtained by performing denoising processing on the target image data; Edge enhancement image data containing gray value data is obtained by performing edge enhancement processing on the denoised image data, the gray value data being used for reflecting contrast data contained in the edge enhancement image; and According to the gray value data, an enhanced image is obtained by performing contrast enhancement processing on the edge enhancement image, comprising: The edge enhancement image is divided into a plurality of sub-edge enhancement images; Gray value data contained in each sub-edge enhancement image is acquired to obtain a plurality of gray histograms; According to a preset cutting threshold, each gray histogram is cut to obtain a plurality of cut gray histograms, the cut gray histogram being a histogram of a cut part of the gray value data; and According to the part of the gray value data and the plurality of cut gray histograms, a plurality of target gray histograms is obtained, so as to convert the edge enhancement image into the enhanced image according to the plurality of target gray histograms; The cut gray histogram comprises a first cut gray histogram representing a cutting direction being a height direction of the gray histogram, and a second cut gray histogram representing a cutting direction being a width direction of the gray histogram; according to a preset cutting threshold, each gray histogram is cut to obtain a plurality of cut gray histograms, comprising: The gray value data contained in each sub-edge enhancement image is compared with the preset cutting threshold to determine whether the corresponding gray histogram needs to be cut, the preset cutting threshold comprising a preset upper cutting threshold and a preset lower cutting threshold; When the gray value data is greater than the preset upper cutting threshold or less than the preset lower cutting threshold, the corresponding gray histogram needs to be cut; and When the gray value data is greater than or equal to the preset lower cutting threshold and less than or equal to the preset upper cutting threshold, the corresponding gray histogram does not need to be cut.

2. The method of image enhancement of claim 1, wherein, The method for image enhancement further comprises: When the image to be enhanced is acquired, the target image data is obtained by performing data conversion on the image data to be enhanced, so as to obtain the target image.

3. The method of image enhancement of claim 1, wherein, According to the redundant information data and the image data to be denoised, the denoised image data is obtained by performing denoising processing on the target image, comprising: According to the redundant information data, the target image data is divided into a plurality of sub-target image data, the redundant information data being a similarity between the sub-target image data; According to the similarity, a weight value is given to each sub-target image data; According to the weight value, the corresponding denoised image data is obtained by performing denoising processing on each sub-target image data; and According to each corresponding denoised image data, the denoised image data is obtained.

4. The method of image enhancement of claim 1, wherein, The edge enhancement processing is Laplace transform processing based on the denoised image data; The edge enhancement processing is Laplace transform processing based on the denoised image data; The edge enhancement processing is Laplace transform processing based on the denoised image data; The edge enhancement processing is Laplace transform processing based on the denoised image data; The edge enhancement processing is Laplace transform processing based on the denoised image data.

5. The method of image enhancement of claim 1, wherein, According to the partial gray value data and the plurality of cut gray histograms, a plurality of target gray histograms is obtained, including: Obtaining a cut gray histogram corresponding to each partial gray value data; and Dividing the each partial gray value data into the corresponding cut gray histogram to obtain the plurality of target gray histograms.

6. An apparatus for image enhancement, characterized by The image enhancement device includes: An image data acquisition module, when obtaining a target image, the image data acquisition module is used to acquire redundant information data contained in target image data, and the redundant information data is used to reflect image data to be denoised in the target image data; A first image data processing module, used to obtain denoised image data by denoising the target image data according to the redundant information data and the image data to be denoised; A second image data processing module, used to obtain edge enhancement image data by edge enhancement processing of the denoised image data, so as to obtain an edge enhancement image, the edge enhancement image data contains gray value data, and the gray value data is used to reflect contrast data contained in the edge enhancement image; and An image processing module, used to obtain an enhanced image by contrast enhancement processing of the edge enhancement image according to the gray value data, including: Dividing the edge enhancement image into a plurality of sub-edge enhancement images; Obtaining gray value data contained in each sub-edge enhancement image to obtain a plurality of gray histograms; According to a preset cut threshold, each gray histogram is cut to obtain a plurality of cut gray histograms, and the cut gray histogram is a histogram of cut partial gray value data; and According to the partial gray value data and the plurality of cut gray histograms, a plurality of target gray histograms is obtained, so as to convert the edge enhancement image into the enhanced image according to the plurality of target gray histograms; The image processing module is also used to cut each gray histogram according to a preset cut threshold to obtain a plurality of cut gray histograms, including: Comparing the gray value data contained in the each sub-edge enhancement image with the preset cut threshold to determine whether the corresponding gray histogram needs to be cut, and the preset cut threshold includes a preset upper cut threshold and a preset lower cut threshold; When the gray value data is greater than the preset upper cut threshold or less than the preset lower cut threshold, the corresponding gray histogram needs to be cut; and When the gray value data is greater than or equal to the preset lower cutting threshold and less than or equal to the preset upper cutting threshold, the corresponding gray histogram does not need to be cut.

7. The apparatus for image enhancement of claim 6, wherein, The device for image enhancement further comprises: An image data conversion module is configured to obtain target image data by obtaining and converting image data of an image to be enhanced when the image to be enhanced is acquired.

8. A computer device, comprising: The computer device comprises a memory for storing a computer program; and A processor is configured to execute the computer program to implement the method for image enhancement according to any one of claims 1-5.

Images