Noise processing method, image forming device, electronic device and storage medium

Abstract

The present application provides a noise processing method, an image forming device, an electronic device and a storage medium, including: if there is an abnormality in any color feature value corresponding to any pixel in the scanned image, then the color abnormality type corresponding to any pixel is determined based on the abnormal color feature value corresponding to any pixel; and the abnormal color feature corresponding to any pixel is adjusted according to the preset processing method corresponding to the color abnormality type. In an embodiment of the present application, according to the color abnormality type of the abnormal pixel, a corresponding color adjustment method is used for the color abnormality type. It can be understood that the abnormal pixel is a noise point, and the reasons for the generation of the noise point are different, so the color abnormality type corresponding to the noise point is also different. Using different image processing methods for different color abnormality types can remove various types of noise points to the greatest extent, thereby ensuring the image quality and the user's perception.

Description

Technical Field

[0001] The present application relates to the field of image forming technology, and in particular to a noise processing method, an image forming device, an electronic device, and a storage medium. Background Art

[0002] An image forming device, such as a printer, copier, fax machine, multi-function image production and copying device, xerographic printing device, or any other similar device, forms an image on an imaging medium using the imaging principle. After a terminal device transmits image data to the image forming device, the device performs a series of complex operations, including signal conversion and laser imaging, before ultimately presenting the image on the imaging medium. However, due to various factors, the image presented on the imaging medium may contain noise, i.e., unwanted spots on the imaging medium.

[0003] In related technologies, in order to achieve better printing results, image forming devices usually use general filtering algorithms, such as mean filtering or median filtering. These methods can reduce the noise that is ultimately presented in the imaging medium to a certain extent.

[0004] However, the filtering algorithms in related technologies use the same processing method for all noise points when removing noise points, which may result in some noise points not being effectively removed. As a result, after a series of complex operations such as signal conversion and laser imaging by the image forming device, some noise points will eventually appear on the printed medium, affecting the image quality and thus affecting the user's perception, and may even cause serious information interference and misinterpretation.

[0005] It should be pointed out that the information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of implication that the information constitutes prior art already known to those skilled in the art. Summary of the Invention

[0006] In view of this, the present application provides a noise processing method, an image forming device, an electronic device and a storage medium, so as to solve the problem that the filtering algorithm in the prior art uses the same processing method for all noise points when removing noise points, which may result in some noise points not being effectively removed, affecting the image quality, thereby affecting the user's perception, and may even cause serious information interference and misinterpretation.

[0007] In a first aspect, an embodiment of the present application provides a noise processing method, comprising:

[0008] Converting the color of the scanned image into a color space for analyzing color features, and acquiring the scanned image converted into the color space for analyzing color features;

[0009] If any color feature value corresponding to any pixel in the scanned image of the color space used to analyze color features is abnormal, determining the color abnormality type corresponding to any pixel according to the abnormal color feature value corresponding to any pixel;

[0010] According to the preset processing method corresponding to the color anomaly type, the abnormal color feature corresponding to any of the pixel points is adjusted.

[0011] In the embodiments of the present application, a corresponding color adjustment method is employed based on the color anomaly type of the abnormal pixel. It is understood that abnormal pixels, or noise, have different causes, and therefore correspond to different color anomaly types. Using different image processing methods for different color anomaly types can maximize the removal of various types of noise, thereby ensuring image quality and user experience.

[0012] In a possible implementation, the color space used to analyze color features is a Lab color space.

[0013] In an embodiment of the present application, the color space used to analyze color features can be a Lab color space. The Lab color space is designed based on human visual perception and can accurately represent all color ranges that humans can perceive. That is to say, the Lab color space can accurately represent the colors of all pixels, thereby ensuring the accuracy of color correction, and ultimately better processing the noise of the image presented on the imaging medium, avoiding the noise affecting the image quality and improving the user experience.

[0014] In a possible implementation, if any color feature value corresponding to any pixel in the scanned image of the color space for analyzing color features is abnormal, before determining the color abnormality type corresponding to any pixel according to the color feature abnormality value corresponding to any pixel, the method further includes:

[0015] Obtain the mean values ​​of multiple color features corresponding to all pixels in the scanned image;

[0016] Determining whether a color feature value corresponding to any pixel point in the scanned image matches a corresponding color feature mean value;

[0017] If the color feature value corresponding to any pixel point in the scanned image does not match the corresponding color feature mean value, then the color feature value corresponding to any pixel point is abnormal.

[0018] In the embodiments of the present application, the color feature value corresponding to each pixel in the scanned image is compared with the corresponding color feature mean to determine whether the color feature value corresponding to each pixel is abnormal. It is understood that by separately verifying the multiple color feature values ​​corresponding to each pixel, a variety of abnormal pixels can be obtained based on different color feature value abnormalities, allowing for different abnormality types to be processed differently, thereby ensuring that different noise points are treated accordingly, and the image quality ultimately presented on the imaging medium is more in line with the user experience.

[0019] In a possible implementation, adjusting the abnormal color feature corresponding to any pixel point according to a preset processing method corresponding to the color anomaly type includes:

[0020] If any of the pixel points is a non-edge pixel point, adjusting the abnormal color feature corresponding to any of the pixel points according to the preset processing method corresponding to the color anomaly type;

[0021] If any of the pixel points is an edge pixel point, the abnormal color feature corresponding to any of the pixel points is adjusted according to the preset processing method and preset adjustment range corresponding to the color anomaly type, and the preset adjustment range represents the adjustment range of the abnormal color feature.

[0022] In the embodiment of the present application, edge pixels and non-edge pixels are processed in different ways. It can be understood that a special processing strategy is adopted for edge pixels to avoid using the same processing strategy as non-edge pixels. The edge pixels can be processed better so that the final edge effect meets the user's expectations of the portrait effect presented on the paper.

[0023] In a possible implementation, the preset adjustment range of brightness adjustment is ±10%, the preset adjustment range of hue adjustment is ±15°, and the preset adjustment range of saturation adjustment is ±20%.

[0024] In an embodiment of the present application, the preset adjustment range of brightness is set to ±10%, the preset adjustment range of hue adjustment is set to ±15°, and the preset adjustment range of saturation adjustment is limited to ±20%. This allows the clarity and sharpness of the edges to be retained to the greatest extent while removing the influence of noise, so that the edge effect of the image finally presented on the imaging medium will not be blurred or distorted, meeting the user's expectations for the image.

[0025] In a possible implementation, the color feature values ​​include brightness, hue, and saturation; and the color anomaly types include at least one of brightness anomaly, hue anomaly, saturation anomaly, brightness anomaly and hue anomaly, brightness anomaly and saturation anomaly, and hue anomaly and saturation anomaly.

[0026] In the embodiment of the present application, the color feature values ​​include brightness, hue and saturation. It can be understood that these three feature values ​​can almost fully describe the characteristics of a pixel point, so that the method provided in the present application can handle a variety of abnormal situations.

[0027] In a possible implementation, adjusting the abnormal color feature corresponding to any pixel point according to a preset processing method corresponding to the color anomaly type includes:

[0028] If the color anomaly type corresponding to any of the pixel points is brightness anomaly, adjusting the brightness corresponding to any of the pixel points according to the weighted average brightness of other pixel points within a first preset range around the pixel point;

[0029] and / or, if the color anomaly type corresponding to any of the pixels is a hue anomaly, converting any of the pixels into an HSL color space, and adjusting the hue corresponding to any of the pixels based on a difference between the hue of any of the pixels and the hues of other pixels within a surrounding second preset range;

[0030] and / or, if the color anomaly type corresponding to any of the pixels is a saturation anomaly, performing equalization processing on a saturation histogram of a target area according to the saturation mean and standard deviation of the scanned image, the target area being an area corresponding to a third preset range where any of the pixels is located;

[0031] And / or, if the color anomaly type corresponding to any of the pixels is brightness anomaly and hue anomaly, first adjusting the brightness corresponding to any of the pixels based on a weighted average of the brightnesses corresponding to other pixels within a first preset range surrounding any of the pixels, then converting any of the pixels to an HSL color space, and adjusting the hue corresponding to any of the pixels based on a difference between the hue of any of the pixels and the hue of other pixels within a second preset range surrounding any of the pixels;

[0032] And / or, if the color abnormality type corresponding to any of the pixels is brightness abnormality and saturation abnormality, first adjusting the brightness corresponding to any of the pixels based on a weighted average of the brightnesses corresponding to other pixels within a first preset range around any of the pixels, and then performing equalization processing on the saturation histogram of a target area based on the saturation mean and standard deviation of the scanned image, where the target area is an area corresponding to a third preset range where any of the pixels is located;

[0033] And / or, if the color abnormality type corresponding to any of the pixel points is hue abnormality and saturation abnormality, any of the pixel points is first converted to the HSL color space, and the hue corresponding to any of the pixel points is adjusted according to the difference between the hue of any of the pixel points and the hue of other pixel points within the surrounding second preset range, and then the saturation histogram of the target area is equalized according to the saturation mean and standard deviation of the scanned image, and the target area is the area corresponding to the third preset range where any of the pixel points is located.

[0034] In an embodiment of the present application, for pixels with abnormal brightness, the brightness corresponding to the abnormal pixel is adjusted based on the weighted average brightness of other pixels within a first preset range around the abnormal pixel. It can be understood that adjusting the brightness of the abnormal pixel using the weighted average brightness of other pixels within a certain range around the abnormal pixel can not only ensure that the brightness of the abnormal pixel is adjusted to be similar to the brightness of other pixels, but also ensure that the brightness of the pixel is adjusted appropriately to avoid step-wise differences in brightness from other surrounding pixels, ultimately improving the effect of removing noise with abnormal brightness of the image presented on the imaging medium. In addition, adjusting the hue of the abnormal pixel using the hue corresponding to other pixels within a certain range around the abnormal pixel can not only ensure that the hue of the abnormal pixel is adjusted to be similar to the hue of other pixels, but also ensure that the hue of the pixel is adjusted appropriately to avoid step-wise differences in hue from other surrounding pixels, ultimately improving the effect of removing noise with abnormal hue of the image presented on the imaging medium. Moreover, equalizing the saturation histogram of the target area can ensure that the saturation of the target area is relatively balanced and has a small difference from the saturation of other areas in the entire scanned image, ultimately improving the effect of removing abnormal saturation noise in the image presented on the imaging medium.

[0035] Furthermore, if a pixel has multiple color anomaly types, for example, a pixel has both brightness anomaly and saturation anomaly, then the multiple abnormal color features corresponding to the abnormal pixel are adjusted in sequence according to the priority of the color anomaly type and the multiple preset processing methods corresponding to the multiple color anomaly types, so that the final noise processing effect meets the user's expectations, thereby avoiding the situation where only one abnormal type is processed when a certain noise point has multiple color anomaly types, resulting in the final presentation effect still failing to meet the user's expectations for the image presented on the imaging medium.

[0036] In a second aspect, an embodiment of the present application provides an image forming device, comprising:

[0037] A color conversion module is used to convert the color of the scanned image into a color space for analyzing color features, and obtain the scanned image converted to the color space for analyzing color features;

[0038] an abnormality determination module, configured to determine, if any color feature value corresponding to any pixel point in the scanned image of the color space used to analyze color features is abnormal, a color abnormality type corresponding to any pixel point based on the abnormality of the color feature value corresponding to any pixel point;

[0039] The color feature value adjustment module is used to adjust the abnormal color feature corresponding to any of the pixel points according to the preset processing method corresponding to the color abnormality type.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0041] processor;

[0042] Memory;

[0043] and a computer program, wherein the computer program is stored in the memory, and the computer program includes instructions, which, when executed by the processor, enable the electronic device to perform any one of the methods described in the first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described in the first aspect.

[0045] It is understood that the image forming apparatus provided in the second aspect, the electronic device provided in the third aspect, and the computer-readable storage medium provided in the fourth aspect are used to perform the methods provided in this application. Therefore, the beneficial effects achievable by these methods can be referenced to the beneficial effects of the corresponding methods and will not be further elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 A schematic diagram of a noise processing method provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of pixel arrangement within a first preset range provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a flow chart of another noise processing method provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a flow chart of another noise processing method provided in an embodiment of the present application;

[0051] Figure 5 A schematic structural diagram of an image forming device provided in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0054] It should be clear that the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] The terms used in the embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "an", "the" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0056] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0057] An image forming device, such as a printer, copier, fax machine, multi-function image production and copying device, xerographic printing device, or any other similar device, forms an image on an imaging medium using the imaging principle. After a terminal device transmits image data to the image forming device, the device performs a series of complex operations, including signal conversion and laser imaging, before ultimately presenting the image on the imaging medium. However, due to various factors, the image presented on the imaging medium may contain noise, i.e., unwanted spots on the imaging medium.

[0058] In related technologies, general filtering algorithms are usually used, such as mean filtering or median filtering, which can reduce noise to a certain extent.

[0059] However, the filtering algorithms in related technologies use the same processing method for all noise points when removing noise points, which may result in some noise points not being effectively removed, affecting the quality of images printed or copied on paper, thereby affecting the user's perception, and may even cause serious information interference and misinterpretation.

[0060] To address the above issues, embodiments of the present application provide a noise processing method that employs a corresponding color adjustment method based on the color anomaly type of the abnormal pixel. It is understood that abnormal pixels, or noise, have different causes, and therefore correspond to different color anomaly types. Using different image processing methods for different color anomaly types can maximize the removal of various types of noise, thereby ensuring the quality of images printed or copied on paper and the user's visual experience. This is described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] See also Figure 1 , is a flow chart of a noise processing method provided in an embodiment of the present application. Figure 1 As shown, it mainly includes the following steps.

[0062] Step S101: converting the color of the scanned image into a color space for analyzing color features, and acquiring the scanned image converted into the color space for analyzing color features.

[0063] Specifically, after receiving the scanned image, the image forming apparatus first performs color space conversion on the image, converting the commonly used RGB color space into a color space for analyzing color features.

[0064] In one possible implementation, the color space used to analyze color features is the Lab color space (i.e., the CIELab color space). The Lab color space is more conducive to analyzing color features. CIELab is a color system and colorimetric system developed by the International Commission on Illumination (CIE). CIELab-based means based on this color system and is essentially used to determine the numerical information of a specific color. The Lab mode, a color model published by the CIE in 1976, is a color model established by the CIE organization that theoretically includes all colors visible to the human eye. The CIELab color space can more evenly represent color differences, facilitating the accurate extraction of color brightness (L), red-green saturation (a), and yellow-blue saturation (b). By analyzing the color features (Lab) of each pixel, a color feature matrix for the image is established.

[0065] Step S102: If any color feature value corresponding to any pixel in the scanned image of the color space used for analyzing color features is abnormal, the color abnormality type corresponding to any pixel is determined according to the abnormal color feature value corresponding to any pixel.

[0066] Specifically, when the image forming apparatus determines that any color feature value corresponding to a pixel in the scanned image is abnormal, the image forming apparatus determines the color abnormality type corresponding to the abnormal pixel based on the abnormal color feature value corresponding to the abnormal pixel.

[0067] In one possible implementation, a statistical analysis method is used to calculate the distribution of each color feature value in the scanned image in the entire color space. By setting a color distribution threshold, pixels whose color feature values ​​deviate from the normal distribution range are screened out. The colors corresponding to these pixels are possible noise colors.

[0068] In one possible implementation, the color distribution threshold is a pre-set fixed value, but pre-setting a fixed value may result in poor flexibility of the solution, so the color distribution threshold in the embodiment of the present application is the mean of the color features corresponding to all pixels in the scanned image.

[0069] Specifically, the mean values ​​of multiple color features corresponding to all pixels in the scanned image are obtained; it is determined whether the color feature value corresponding to any pixel in the scanned image matches the corresponding color feature mean value; if the color feature value corresponding to any pixel in the scanned image does not match the corresponding color feature mean value, then there is an abnormality in the color feature value corresponding to any pixel.

[0070] Exemplarily, the brightness mean corresponding to all pixels in the scanned image is obtained, and it is determined whether there is any pixel in the scanned image whose brightness value does not match the brightness mean. If the brightness value corresponding to any pixel does not match the brightness mean, then the color feature value corresponding to the pixel is abnormal.

[0071] It is understandable that by verifying the multiple color feature values ​​corresponding to each pixel point respectively, a variety of different abnormal pixel points can be obtained according to different color feature value anomalies, so as to perform different processing on different anomaly types.

[0072] In one possible implementation, if the color feature value corresponding to a pixel point differs from the color feature mean by more than a certain threshold, the pixel point is included in the noise color candidate set. In other words, all pixels with abnormal color features are placed in the same set to facilitate subsequent corresponding processing of the abnormal pixel point.

[0073] It is understandable that in the noise color candidate set, the color anomaly type corresponding to each pixel is not necessarily the same. For example, the color anomaly type corresponding to the first pixel may be brightness anomaly, the color anomaly type corresponding to the second pixel may be saturation anomaly, the color anomaly type corresponding to the third pixel may also be saturation anomaly, the color anomaly type corresponding to the fourth pixel may be hue anomaly, the color anomaly type corresponding to the fifth pixel may be brightness anomaly, the color anomaly type corresponding to the sixth pixel may be hue anomaly and saturation anomaly, the color anomaly type corresponding to the seventh pixel may be brightness anomaly and saturation anomaly, and the color anomaly type corresponding to the eighth pixel may be brightness anomaly and hue anomaly. In order to completely remove these pixels with different color anomaly types, it is necessary to classify these pixels with color feature anomalies, so as to adopt different processing methods for different color anomaly types.

[0074] In one possible implementation, convolutional neural networks (CNNs) are used to classify pixels in a set of color candidates. Specifically, the color feature matrix of the scanned image to be processed is fed into a trained model. The model then matches and classifies the features to accurately identify the color anomaly type corresponding to the abnormal pixels, such as brightness anomaly, hue anomaly, saturation anomaly, brightness anomaly and hue anomaly, brightness anomaly and saturation anomaly, or hue anomaly and saturation anomaly.

[0075] In one possible implementation, the CNN training method involves pre-collecting a large number of image samples with color anomalies and manually labeling the colors of the noise in these samples. The machine learning model is then trained using these labeled samples to learn the characteristic patterns of color anomalies.

[0076] Step S103: adjusting the abnormal color feature corresponding to any pixel point according to a preset processing method corresponding to the color abnormality type.

[0077] Specifically, after determining the color anomaly type of the abnormal pixel, the image forming apparatus determines a preset processing method based on the abnormal color feature value of the abnormal pixel, and adjusts the abnormal color feature corresponding to the abnormal pixel according to the preset processing method. The abnormal color feature is a color feature that is abnormal among all color features corresponding to the abnormal pixel, and the preset processing method is a method used to correct the abnormal color feature.

[0078] In a possible implementation, the color feature value includes brightness, hue, and saturation, and the color anomaly type includes at least one of brightness anomaly, hue anomaly, saturation anomaly, brightness anomaly and hue anomaly, brightness anomaly and saturation anomaly, and hue anomaly and saturation anomaly.

[0079] In one possible implementation, if the color anomaly type corresponding to any pixel is a brightness anomaly, the brightness corresponding to the abnormal pixel is adjusted based on the weighted average brightness of the other pixels within a first preset range surrounding the abnormal pixel. Adjusting the brightness corresponding to the abnormal pixel based on the weighted average brightness of the other pixels within the first preset range surrounding the abnormal pixel represents the preset processing method mentioned above, and the brightness corresponding to the abnormal pixel represents the abnormal color feature mentioned above.

[0080] In one possible implementation, the first preset range is a 5×5 neighborhood window centered on the abnormal pixel point. Of course, those skilled in the art can set the first preset range to any range according to actual needs, and the embodiment of the present application does not impose any specific restrictions on this.

[0081] For example, see Figure 2 , is a schematic diagram of pixel arrangement in a first preset range provided in an embodiment of the present application. Figure 2 As shown, the first preset range includes 25 pixels, one of which is an abnormal pixel, and the abnormal pixel is at the center, and the other 24 are normal pixels.

[0082] The weighted average brightness is assigned based on the distance between normal and abnormal pixels, with closer distances giving higher weights. Normal pixels closer to abnormal pixels receive higher weights, ensuring that abnormal pixels match the surrounding normal pixels, thus ensuring a consistent user experience.

[0083] In one possible implementation, if the color anomaly type corresponding to any pixel is a hue anomaly, the hue corresponding to the abnormal pixel is adjusted based on the difference between the hue of the abnormal pixel and the hues of other pixels within a second preset range. Adjusting the hue corresponding to the abnormal pixel based on the difference between the hue of the abnormal pixel and the hues of other pixels within the second preset range is the preset processing method mentioned above, and the hue corresponding to the abnormal pixel is the abnormal color feature mentioned above.

[0084] In the embodiment of the present application, the second preset range may be the same as or different from the first preset range, and those skilled in the art may adjust the range value of the second preset range according to actual needs.

[0085] Furthermore, to better adjust the hue of the abnormal pixel, the color of the abnormal pixel is converted from the CIELab color space to the polar coordinate HSL (Hue, Saturation, Lightness) color space, and the hue is adjusted in the HSL color space. Based on the difference in hue between the abnormal pixel and the surrounding normal pixels, the hue angle required for adjustment is calculated. The hue value of the abnormal pixel is then rotated accordingly to align the hue of the abnormal pixel with the surrounding hue. Once the adjustment is complete, the color is converted back to the CIELab color space to ensure compatibility with subsequent printing processes.

[0086] In one possible implementation, if the color anomaly corresponding to the abnormal pixel is a saturation anomaly, the saturation histogram of the target region is equalized based on the saturation mean and standard deviation of the scanned image. The target region is the region corresponding to the third preset range where the abnormal pixel is located. Equalizing the saturation histogram of the target region based on the saturation mean and standard deviation of the scanned image is the preset processing method mentioned above, and the saturation histogram of the target region where the abnormal pixel is located is the abnormal color feature mentioned above.

[0087] In other words, based on the saturation mean and standard deviation of the entire scanned image, the saturation histogram of the target area is adjusted to a value that is close to the mean and standard deviation of the saturation of the entire scanned image. This also ensures that the saturation of the abnormal pixel is reasonably distributed within the local area. In this way, the saturation of the abnormal pixel matches the surrounding environment while maintaining a natural color transition in the image.

[0088] In the embodiment of the present application, the third preset range may be the same as or different from the second preset range and the first preset range, and those skilled in the art may adjust the range value of the third preset range according to actual needs.

[0089] In summary, using different image processing methods for different types of color anomalies can remove various types of noise to the greatest extent possible, thereby ensuring the quality of images printed or copied on paper and the user's perception.

[0090] Furthermore, as mentioned above, CNN classifies abnormal pixels in the color candidate set, allowing for different adjustments to be made for pixels with different color anomalies. In other words, rather than applying multiple adjustments to every abnormal pixel, adjustments are made based on the anomaly of the pixel.

[0091] In a possible implementation, abnormal pixels are classified through CNN, and the color abnormality types include: brightness abnormality, hue abnormality, saturation abnormality, brightness abnormality and hue abnormality, brightness abnormality and saturation abnormality, and hue abnormality and saturation abnormality.

[0092] For example, if the brightness of the first pixel is abnormal, only the brightness of the first pixel is adjusted; if the saturation of the second pixel is abnormal, the saturation of the second pixel is adjusted; if both the brightness and saturation of the third pixel are abnormal, both the brightness and saturation of the third pixel are adjusted.

[0093] In actual applications, each abnormal pixel may have more than one abnormal color feature value. For these pixels with multiple color feature anomalies, if only one abnormal color feature of these pixels is adjusted while other abnormal feature values ​​of the pixel are ignored, the color of the image printed or copied on paper may still be abnormal, affecting the user's perception.

[0094] Therefore, in an embodiment of the present application, if a pixel point has multiple color anomaly types, for example, a pixel point is a brightness anomaly and a saturation anomaly type, then the multiple abnormal color features corresponding to the abnormal pixel point are adjusted in sequence according to the priority of the color anomaly type and the multiple preset processing methods corresponding to the multiple color anomaly types.

[0095] The priority of color anomaly types is a preset order for processing color anomaly types based on the degree of impact of the color anomaly type on the image printed or copied on paper and the degree of impact of multiple color features on each other. For example, brightness anomaly has a greater impact on the overall image printed or copied on paper than saturation anomaly because brightness affects the contrast and detail controllability of the image printed or copied on paper. Excessive brightness or darkness can also obscure saturation information. In other words, saturation depends on brightness and needs to be adjusted after brightness is adjusted. Therefore, when a pixel corresponds to a color anomaly type of brightness anomaly and saturation anomaly, the brightness anomaly of the pixel is processed first, followed by the saturation anomaly. Specifically, the brightness of the pixel is first adjusted based on the weighted average of the brightness of other pixels within a first preset range surrounding the pixel. Then, the saturation histogram of the target area is equalized based on the saturation mean and standard deviation of the scanned image. The target area is the area corresponding to the third preset range where the pixel is located. Based on the priority of the color anomaly type and the multiple preset processing methods corresponding to the multiple color anomaly types, the multiple abnormal color features corresponding to the abnormal pixel are adjusted sequentially, so that the final noise processing effect meets the user's expectations.

[0096] Similarly, if the color abnormality type corresponding to any pixel point is brightness abnormality and hue abnormality, the brightness abnormality of the pixel point is processed first, and then the hue abnormality is processed. That is, the brightness corresponding to the pixel point is adjusted according to the weighted average brightness corresponding to other pixels within the first preset range around the pixel point, and then the pixel point is converted to the HSL color space, and the hue corresponding to the pixel point is adjusted according to the difference between the hue of the pixel point and the hue of other pixels within the second preset range around it.

[0097] In addition, if the color abnormality type corresponding to any pixel point is hue abnormality and saturation abnormality, the hue abnormality of the pixel point is processed first, and then the saturation abnormality is processed, that is, the pixel point is first converted to the HSL color space, and the hue corresponding to the pixel point is adjusted according to the difference between the hue of the pixel point and the hue of other pixels within the surrounding second preset range, and then the saturation histogram of the target area is equalized according to the saturation mean and standard deviation of the scanned image. The target area is the area corresponding to the third preset range where the pixel point is located.

[0098] In practical applications, the edges of images are usually clearer and sharper. If the same method is used to adjust edge pixels and non-edge pixels, the sharpness of the image edges may be affected.

[0099] Therefore, in the embodiment of the present application, it is determined whether the abnormal pixel point is an edge pixel point. If the abnormal pixel point is a non-edge pixel point, the abnormal color feature corresponding to the abnormal pixel point is adjusted according to the preset processing method corresponding to the color abnormality type; if the abnormal pixel point is an edge pixel point, the abnormal color feature corresponding to the abnormal pixel point is adjusted according to the preset processing method and preset adjustment amplitude corresponding to the color abnormality type.

[0100] The preset adjustment range can be understood as the preset limit range for adjusting brightness, hue, and saturation. It is to avoid excessive adjustment of edge pixels, so as to remove the influence of noise while retaining the clarity and sharpness of the edge to the greatest extent.

[0101] Exemplarily, the preset adjustment range of brightness adjustment is generally ±10%~±30% (relative to the original value) to avoid overexposure or too dark resulting in loss of details. For example, in the adjustment of a certain edge pixel point, if the brightness of the pixel point itself is 50%, and the preset adjustment range is ±30%, then the brightness of the pixel point after adjustment is limited to 20%~80%. That is to say, even if the brightness of the pixel point should be adjusted to 90% based on the weighted average brightness of other pixels within the first preset range around the abnormal edge pixel point, due to the setting of the preset adjustment range, the brightness of the abnormal edge pixel point can only be adjusted to a maximum of 80%; the range limit of hue adjustment is generally controlled at ±15°~±45° (relative to the original value) ("°" refers to the angle of hue) to avoid color distortion. Exemplarily, if the original hue of a certain edge pixel point is 60°, and the preset adjustment range is set to ±15°, then after adjustment, the pixel point The hue range of edge pixels is 45° to 75°. That is, even if the hue of the abnormal pixel is calculated to be 80° based on the difference between the hue of the abnormal pixel and the hue of other pixels within the second preset range, the hue can only be adjusted to 75° due to the preset adjustment range. The saturation adjustment range is generally limited to ±20% to ±50% (relative to the original value) to avoid unnatural images. For example, if the original saturation of an abnormal edge pixel is 50% and the preset adjustment range is set to ±20%, the adjusted saturation range of the abnormal edge pixel is 30% to 70%. That is, even if the saturation histogram of the target area is equalized based on the saturation mean and standard deviation of the scanned image and the saturation of the abnormal edge pixel is calculated to be 80%, due to the limitation of the preset adjustment range, the saturation of the abnormal edge pixel can only be adjusted to 70%. It should be noted that in actual applications, those skilled in the art can set the preset adjustment range to any value according to actual needs, and the embodiments of the present application do not impose specific restrictions on this.

[0102] In one possible implementation, the Sobel edge detection algorithm is introduced to mark and protect image edge information, making it easier to identify edge pixels. The Sobel operator is an important processing method in computer vision. It is primarily used to obtain the first-order gradient of digital images. Its common application and physical significance is edge detection. The Sobel operator calculates the weighted difference in the grayscale values ​​of each pixel in the image, reaching an extreme value at the edge.

[0103] In addition, image enhancement techniques (such as histogram matching algorithms) are used to enhance the details of the processed scanned images. By increasing the weight of high-frequency components, the image details are highlighted, further improving the image clarity and visual quality. After image enhancement, image sharpening algorithms (such as Laplace sharpening algorithms) are used to sharpen the image, enhancing the edges and textures of objects in the image, making the printed image clearer and more vivid, and finally obtaining the output image.

[0104] Histogram matching, also known as histogram normalization, is an image enhancement method that converts the histogram of an image into a histogram of a specified shape. This involves matching the histogram of one image or region to another, maintaining the tonal consistency of the two images. This matching can be performed between single-band image histograms or simultaneously across multiple bands. Laplace sharpening is a commonly used image processing technique, primarily used to enhance image details and edges for greater clarity.

[0105] Finally, according to the concentration of toner in the image forming device and the sensitivity of the photosensitive drum, the brightness and contrast of the image are optimized to improve the layering and clarity of the output image, and image formation is performed on the processed output image.

[0106] Corresponding to the above embodiment, the present application also provides another noise processing method.

[0107] See also Figure 3 , is a flow chart of another noise processing method provided in the embodiment of the present application. Figure 3 As shown, it mainly includes the following steps.

[0108] Step S301: importing a scanned image A to be printed.

[0109] Step S302: Convert the color space from RGB to CIELab.

[0110] Step S303: Color feature mean distribution statistics.

[0111] Specifically, the color feature mean includes but is not limited to the brightness mean, the hue mean, and the saturation mean.

[0112] Step S304: Determine whether the color feature value deviates from the threshold.

[0113] That is, it is determined whether the color feature value corresponding to any pixel in the scanned image matches the corresponding color feature mean value. If so, step S305 is executed; if not, step S306 is executed.

[0114] Step S305: Incorporating a color candidate set.

[0115] Step S306: Default processing.

[0116] Step S307: Convolutional neural network identifies the type of color anomaly.

[0117] Step S308: Targeted processing.

[0118] For details of the embodiments of this application, please refer to the above Figure 1 and Figure 2 For the sake of brevity, the description in the illustrated embodiment will not be repeated here.

[0119] Corresponding to the above-mentioned targeted processing, the embodiment of the present application also provides another noise processing method.

[0120] See also Figure 4 , is a flow chart of another noise processing method provided in the embodiment of the present application. Figure 4 As shown, it mainly includes the following steps.

[0121] Step S307: Convolutional neural network identifies the type of color anomaly.

[0122] Step S401: Determine brightness abnormality.

[0123] Step S4011: Adaptive weighted average algorithm.

[0124] That is, as described above, the weighted average brightness of other pixels within a first preset range around the abnormal pixel is calculated.

[0125] Step S4012: Brightness correction.

[0126] Step S4013: Edge detection and protection.

[0127] Step S402: Determine the hue deviation.

[0128] Step S4021: Convert the color space from CIELab to HSL.

[0129] Step S4022: Hue adjustment.

[0130] Step S4023: Convert the color space from HSL to CIELab.

[0131] Step S4024: edge detection and protection.

[0132] Step S403: Determine whether the saturation is abnormal.

[0133] Step S4031: Saturation correction.

[0134] Step S4032: Edge detection and protection.

[0135] Step S404: Determine whether the brightness is abnormal or the hue is abnormal.

[0136] Step S4041: Process brightness abnormality.

[0137] Step S4042: Processing color tone abnormality.

[0138] Step S4043: Edge detection and protection.

[0139] Step S405: Determine whether the brightness is abnormal or the saturation is abnormal.

[0140] Step S4051: Process brightness abnormality.

[0141] Step S4052: Processing saturation abnormality.

[0142] Step S4053: Edge detection and protection.

[0143] Step S406: Determine whether the hue is abnormal and the saturation is abnormal.

[0144] Step S4061: Processing color tone abnormality.

[0145] Step S4062: Processing saturation abnormality.

[0146] Step S4063: Edge detection and protection.

[0147] Step S407: Image B after removing noise.

[0148] Among them, noise refers to abnormal pixel points.

[0149] Step S408: Image enhancement and sharpening.

[0150] Step S409: Output image C.

[0151] Step S410: Printing imaging.

[0152] For details of the embodiments of this application, please refer to the above Figures 1 to 3 For the sake of brevity, the description in the illustrated embodiment will not be repeated here.

[0153] In one possible implementation, Figure 3 、 Figure 4 The embodiment shown can be executed by the image forming apparatus or by other terminal equipment that is in communication with the image forming apparatus. Figure 3 、 Figure 4 The embodiment shown is executed by a terminal device, so before step S301, it also includes: the terminal device receives the original image scanned and obtained by the image forming device, and the terminal device completes the process of scanning the original image. Figure 3 、 Figure 4 After processing, the terminal device sends the processed image to the image forming device, and then the image forming device performs an image forming job according to the received processed image.

[0154] Corresponding to the above embodiments, the present application also provides an image forming device.

[0155] See also Figure 5 , is a structural diagram of an image forming device provided in an embodiment of the present application, such as Figure 5 As shown, the image forming apparatus may include: a color conversion module 501, an abnormality determination module 502, and a color feature value adjustment module 503. These components communicate via one or more buses. Those skilled in the art will appreciate that the structure of the electronic device shown in the figure does not limit the embodiments of the present application. It may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0156] The color conversion module 501 is used to convert the color of the scanned image into the Lab color space, and obtain the scanned image converted into the Lab color space;

[0157] Anomaly determination module 502 is configured to determine the color anomaly type corresponding to any pixel point in the scanned image based on the abnormal color feature value corresponding to any pixel point if any color feature value corresponding to the pixel point in the scanned image is abnormal;

[0158] The color feature value adjustment module 503 is configured to adjust the abnormal color feature corresponding to any of the pixel points according to a preset processing method corresponding to the color anomaly type.

[0159] Corresponding to the above embodiments, the present application also provides an electronic device.

[0160] See also Figure 6 , is a structural diagram of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 may include: a processor 601, a memory 602, and a communication unit 603. These components communicate via one or more buses. Those skilled in the art will appreciate that the structure of the electronic device shown in the figure does not limit the embodiments of the present application. It may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0161] The communication unit 603 is configured to establish a communication channel so that the electronic device can communicate with other devices, receive user data sent by other devices, or send user data to other devices.

[0162] The processor 601 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It runs or executes software programs, instructions, and / or modules stored in the memory 602, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 601 can include only a central processing unit (CPU). In the embodiment of the present application, the CPU can be a single computing core or multiple computing cores.

[0163] The memory 602 is used to store execution instructions of the processor 601. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0164] When the execution instructions in the memory 602 are executed by the processor 601, the electronic device 600 can execute Figure 1 Some or all of the steps in the illustrated embodiments.

[0165] In a specific implementation, embodiments of the present application further provide a computer storage medium, wherein the computer storage medium may store a program that, when executed, may include some or all of the steps of each embodiment of the simulation scenario generation method provided in embodiments of the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0166] In a specific implementation, an embodiment of the present application also provides a computer program product, wherein the computer program product includes executable instructions, which, when executed on a computer, enable the computer to execute some or all of the steps in each embodiment of the simulation scenario generation method provided in the embodiment of the present application.

[0167] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0168] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0169] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0170] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0171] In this specification, reference can be made to the same or similar parts between the various embodiments. In particular, for the device embodiment and the terminal embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

Claims

1. A noise processing method, characterized in that: include: Converting the color of the scanned image obtained by the image forming device into a color space for analyzing color features, and acquiring the scanned image converted into the color space for analyzing color features; If any color feature value corresponding to any pixel in the scanned image of the color space used to analyze color features is abnormal, determining the color abnormality type corresponding to any pixel according to the abnormal color feature value corresponding to any pixel; adjusting the abnormal color feature corresponding to any of the pixel points according to a preset processing method corresponding to the color abnormality type, and the image forming device performing an image forming operation on the adjusted image; The determining the color anomaly type corresponding to any pixel point according to the color feature value anomaly corresponding to any pixel point includes: Determine the color anomaly type corresponding to any of the pixel points through a convolutional neural network according to the abnormal color feature value corresponding to any of the pixel points; The color feature values ​​include: brightness, hue and saturation; the color anomaly types include: at least one of: brightness anomaly, hue anomaly, saturation anomaly, brightness anomaly and hue anomaly, brightness anomaly and saturation anomaly, hue anomaly and saturation anomaly; The adjusting the abnormal color feature corresponding to any of the pixel points according to the preset processing method corresponding to the color abnormality type includes: If the color anomaly type corresponding to any of the pixel points is brightness anomaly, adjusting the brightness corresponding to any of the pixel points according to the weighted average brightness of other pixel points within a first preset range around the pixel point; and / or, if the color anomaly type corresponding to any of the pixels is a hue anomaly, converting any of the pixels into an HSL color space, and adjusting the hue corresponding to any of the pixels based on a difference between the hue of any of the pixels and the hues of other pixels within a surrounding second preset range; and / or, if the color anomaly type corresponding to any of the pixels is a saturation anomaly, performing equalization processing on a saturation histogram of a target area according to the saturation mean and standard deviation of the scanned image, the target area being an area corresponding to a third preset range where any of the pixels is located; And / or, if the color anomaly type corresponding to any of the pixels is brightness anomaly and hue anomaly, first adjusting the brightness corresponding to any of the pixels based on a weighted average of the brightnesses corresponding to other pixels within a first preset range surrounding any of the pixels, then converting any of the pixels to an HSL color space, and adjusting the hue corresponding to any of the pixels based on a difference between the hue of any of the pixels and the hue of other pixels within a second preset range surrounding any of the pixels; And / or, if the color abnormality type corresponding to any of the pixels is brightness abnormality and saturation abnormality, first adjusting the brightness corresponding to any of the pixels based on a weighted average of the brightnesses corresponding to other pixels within a first preset range around any of the pixels, and then performing equalization processing on the saturation histogram of a target area based on the saturation mean and standard deviation of the scanned image, where the target area is an area corresponding to a third preset range where any of the pixels is located; And / or, if the color abnormality type corresponding to any of the pixel points is hue abnormality and saturation abnormality, any of the pixel points is first converted to the HSL color space, and the hue corresponding to any of the pixel points is adjusted according to the difference between the hue of any of the pixel points and the hue of other pixel points within the surrounding second preset range, and then the saturation histogram of the target area is equalized according to the saturation mean and standard deviation of the scanned image, and the target area is the area corresponding to the third preset range where any of the pixel points is located.

2. The method according to claim 1, characterized in that The color space used to analyze color features is the Lab color space.

3. The method according to claim 2, characterized in that Before determining the color anomaly type corresponding to any pixel point according to the color feature abnormality value corresponding to any pixel point if any color feature value corresponding to any pixel point in the scanned image of the color space for analyzing color features is abnormal, the method further includes: Obtain the mean values ​​of multiple color features corresponding to all pixels in the scanned image; Determining whether a color feature value corresponding to any pixel point in the scanned image matches a corresponding color feature mean value; If the color feature value corresponding to any pixel point in the scanned image does not match the corresponding color feature mean value, then the color feature value corresponding to any pixel point is abnormal.

4. The method according to claim 2, characterized in that The adjusting the abnormal color feature corresponding to any of the pixel points according to the preset processing method corresponding to the color abnormality type includes: If any of the pixel points is a non-edge pixel point, adjusting the abnormal color feature corresponding to any of the pixel points according to the preset processing method corresponding to the color anomaly type; If any of the pixel points is an edge pixel point, the abnormal color feature corresponding to any of the pixel points is adjusted according to the preset processing method and preset adjustment range corresponding to the color anomaly type, and the preset adjustment range represents the adjustment range of the abnormal color feature.

5. The method according to claim 4, characterized in that The preset adjustment range of brightness adjustment is ±10%, the preset adjustment range of hue adjustment is ±15°, and the preset adjustment range of saturation adjustment is ±20%.

6. An image forming apparatus, characterized in that: include: A color conversion module is used to convert the color of the scanned image obtained by the image forming device into a color space for analyzing color features, and obtain the scanned image converted into the color space for analyzing color features; an abnormality determination module, configured to determine, if any color feature value corresponding to any pixel point in the scanned image of the color space used to analyze color features is abnormal, a color abnormality type corresponding to any pixel point based on the abnormality of the color feature value corresponding to any pixel point; A color feature value adjustment module, configured to adjust the abnormal color feature corresponding to any of the pixel points according to a preset processing method corresponding to the color anomaly type, and the image forming device performs an image forming operation on the adjusted image; The abnormality determination module is specifically configured to determine the color abnormality type corresponding to any of the pixel points based on the abnormality of the color feature value corresponding to any of the pixel points through a convolutional neural network; The color feature values ​​include: brightness, hue and saturation; the color anomaly types include: at least one of: brightness anomaly, hue anomaly, saturation anomaly, brightness anomaly and hue anomaly, brightness anomaly and saturation anomaly, hue anomaly and saturation anomaly; The color feature value adjustment module is specifically used to, if the color abnormality type corresponding to any of the pixels is brightness abnormality, adjust the brightness corresponding to any of the pixels according to the weighted average brightness corresponding to other pixels within a first preset range around any of the pixels; and / or, if the color abnormality type corresponding to any of the pixels is hue abnormality, convert any of the pixels to the HSL color space, and adjust the hue corresponding to any of the pixels according to the difference between the hue of any of the pixels and the hue of other pixels within a second preset range around any of the pixels; and / or, if the color abnormality type corresponding to any of the pixels is saturation abnormality, equalize the saturation histogram of the target area according to the saturation mean and standard deviation of the scanned image, the target area being the area corresponding to the third preset range where any of the pixels is located; and / or, if the color abnormality type corresponding to any of the pixels is brightness abnormality and hue abnormality, first adjust the brightness corresponding to any of the pixels according to the weighted average brightness corresponding to other pixels within the first preset range around any of the pixels, and then convert any of the pixels to the HSL color space. color space, and adjusting the hue corresponding to any of the pixels according to the difference between the hue of any of the pixels and the hue of other pixels within the surrounding second preset range; and / or, if the color anomaly type corresponding to any of the pixels is brightness anomaly and saturation anomaly, first adjusting the brightness corresponding to any of the pixels according to the weighted average of the brightnesses corresponding to other pixels within the first preset range surrounding any of the pixels, and then performing equalization processing on the saturation histogram of the target area according to the saturation mean and standard deviation of the scanned image, wherein the target area is the area corresponding to the third preset range where any of the pixels is located; and / or, if the color anomaly type corresponding to any of the pixels is hue anomaly and saturation anomaly, first converting any of the pixels to the HSL color space, and adjusting the hue corresponding to any of the pixels according to the difference between the hue of any of the pixels and the hue of other pixels within the surrounding second preset range, and then performing equalization processing on the saturation histogram of the target area according to the saturation mean and standard deviation of the scanned image, wherein the target area is the area corresponding to the third preset range where any of the pixels is located.

7. An electronic device, characterized in that: include: processor; Memory; and a computer program, wherein the computer program is stored in the memory, and the computer program includes instructions, which, when executed by the processor, enable the electronic device to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

Images