Method and device for reading off the influence of laser printing on a photographed image

Abstract

The present application relates to the technical field of certificate shooting and reading device, and discloses a reading method and device for eliminating or reducing the influence of laser printing on shooting images, wherein the method comprises the following steps: placing an object to be identified in an image collection area, using at least two groups of light sources to provide light for the image collection area, and collecting at least one original picture of the object to be identified under the condition that each group of light sources provides light for the image collection area; converting all the original pictures into target pictures in RGB color mode; selecting the minimum value of the R channel, the minimum value of the G channel and the minimum value of the B channel in the same pixel point of all the target pictures to combine them into a target pixel point; and splicing all the target pixel points into a result picture. The technical scheme provided by the present application reduces the calculation process of a large number of gray values, achieves the purpose of eliminating or reducing the laser highlight reflection in the target picture, and improves the accuracy of image recognition.

Description

Technical Field

[0001] This invention relates to the field of document photographing and reading devices, and in particular to a method and apparatus for eliminating or mitigating the impact of laser printing on photographed images. Background Technology

[0002] Currently, passports, ID cards, driver's licenses, and other documents from various countries use laser printing. When viewed from different angles, the bright reflective areas of the laser printing can be seen with the naked eye, thus achieving the purpose of anti-counterfeiting. However, when photographed with a regular camera, due to the fixed position of the standard shooting light source (white light source), there will be bright reflections in the obtained image. These bright reflections are caused by the laser printing, resulting in bright spots that obscure the text and other true images, making them unrecognizable or reducing the accuracy of recognition. Summary of the Invention

[0003] The purpose of this invention is to provide a method and apparatus for recognizing images by eliminating or mitigating the impact of laser printing on captured images. This involves acquiring multiple target images through multi-light source illumination, selecting the minimum values ​​of the R channel (red component), G channel (green component), and B channel (blue component) of the same pixel in all the target images, and combining these minimum values ​​to form a target pixel. All target pixels are then stitched together to create a final image. Alternatively, the invention compares the lightness (L) or brightness (V / B) values ​​of all pixels in all the target images, selecting the pixel with the smallest lightness (L) or brightness (V / B) value from the same pixel in all the target images as the target pixel, converting all target pixels to RGB color mode, and stitching them together to create a final image. This eliminates or reduces light spots in the target images, improving the accuracy of image recognition.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] This invention provides a method for recognizing images that eliminates or mitigates the impact of laser printing on captured images, comprising:

[0006] The object to be identified is placed in the image acquisition area, and at least two sets of light sources are used to provide illumination to the image acquisition area. Under the condition that each set of light sources provides illumination to the image acquisition area, at least one original image of the object to be identified is acquired. The original image is converted into a target image in RGB color mode. The minimum values ​​of the R channel, G channel, and B channel of the same pixel in the target image are selected and combined into a target pixel. The target pixels are then stitched together to form a result image.

[0007] Furthermore, the original image is converted into a target image in RGB color mode, then converted into HSL mode. For the target image converted into HSL mode, the minimum L value among the same pixel in the target image is selected as the target pixel. The target pixel is then converted into RGB color mode and stitched together to form the final image.

[0008] Furthermore, the original image is converted into a target image in RGB color mode, then converted into HSV mode. For the target image converted to HSV mode, the minimum V value among the same pixel in the target image is selected as the target pixel. The target pixel is then converted into RGB color mode and stitched together to form the final image.

[0009] Furthermore, the light source includes at least one standard light source arranged adjacent to each other, or at least one standard light source and at least one infrared light source, or at least one standard light source, at least one infrared light source and at least one ultraviolet light source.

[0010] A reading device for eliminating or mitigating the impact of laser printing on captured images, wherein the reading device includes at least two sets of light sources, an image acquisition module, and an image processing module.

[0011] The light source is used to provide illumination to the image acquisition area; the image acquisition module is used to acquire at least one original image of the object to be identified placed in the image acquisition area when each group of the light sources provides illumination to the image acquisition area, and convert all the original images into target images in RGB color mode; the image processing module is used to select the minimum R channel value, minimum G channel value, and minimum B channel value of the same pixel in all the target images in RGB color mode, combine them into a target pixel, and stitch all the target pixels into a result image; or select the minimum L value of the same pixel in all the target images in HSL mode as the target pixel, convert the target pixel into RGB color mode, and stitch it into a result image; or select the minimum V value of the same pixel in all the target images in HSV mode as the target pixel, convert the target pixel into RGB color mode, and stitch it into a result image.

[0012] Furthermore, the image processing module includes a calculation unit, a determination unit, and a processing unit; the calculation unit is used to calculate the brightness L value or lightness V value of all pixels in all the target images; the determination unit is used to select the pixel with the smallest brightness L value or lightness V value among the same pixels in all the target images as the target pixel; the processing unit is used to convert all the target pixels into RGB color mode and stitch them together to form a result image.

[0013] Furthermore, the recognition device includes two sets of light sources; and the image acquisition module is used to acquire an original image of the object to be identified placed in the image acquisition area when each set of light sources provides illumination to the image acquisition area.

[0014] Furthermore, the light source includes at least one standard light source arranged adjacent to each other, or at least one standard light source and at least one infrared light source, or at least one standard light source, at least one infrared light source and at least one ultraviolet light source.

[0015] Furthermore, the light source includes a standard light source, an infrared light source, and an ultraviolet light source.

[0016] This invention provides a method and apparatus for eliminating or mitigating the impact of laser printing on captured images. By comparing RGB values, for the same location point, from multiple or two target images, the minimum values ​​of the R channel (red component), G channel (green component), and B channel (blue component) of the same pixel are selected as the target pixel, and all target pixels are then combined to form a result image. Alternatively, by comparing brightness (L) or lightness (V) / brightness (B) values, for the same location point, the pixel with the smallest brightness (L) or lightness (V) / brightness (B) value is selected as the target pixel, and all target pixels are converted to RGB color mode and combined to form a result image. This results in the result image having no or very small light spots, achieving the purpose of eliminating or reducing light spots in the target image and improving the accuracy of image recognition. Using the implementation scheme of this application, not only can result images with no or almost no light spots be obtained, improving the accuracy of image recognition, but also the efficiency of image recognition is effectively improved because a recognition result with a high accuracy rate can be obtained from a single shot. When using RGB value comparison, many internal calculation processes are reduced, increasing the operating speed of the device. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort, wherein:

[0018] Figure 1 This is a flowchart of a method embodiment 1 of the present invention for eliminating or mitigating the impact of laser printing on captured images;

[0019] Figure 2 This is a schematic block diagram of the structure of Embodiment 1 of the recognition device for eliminating or mitigating the impact of laser printing on captured images according to the present invention;

[0020] Figure 3 This is a flowchart of a second embodiment of the method for eliminating or mitigating the impact of laser printing on captured images according to the present invention.

[0021] Figure 4 This is a schematic block diagram of embodiment 2 of the recognition device for eliminating or mitigating the impact of laser printing on captured images according to the present invention.

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

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Specific Implementation Example 1: Please refer to Figure 1 As shown, Figure 1 This is a flowchart of a method for eliminating or mitigating the impact of laser printing on captured images, provided by an embodiment of the present invention. While the present invention provides method operation steps as shown in the following embodiments or accompanying drawings, the method may include more or fewer operation steps based on conventional or non-inventive effort. For steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order described in the embodiments and accompanying drawings. When the method is applied in actual devices or terminal products, it can be executed sequentially or in parallel according to the methods shown in the embodiments or accompanying drawings (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0025] This invention provides a method for recognizing images by eliminating or mitigating the impact of laser printing on captured images. Multiple light sources are used, and under different lighting conditions, multiple original images of the object to be identified in the image acquisition area are captured. All original images are converted into target images in RGB color mode. By comparing the RGB values ​​of each pixel in each target image, the minimum values ​​of the R channel (red component), G channel (green component), and B channel (blue component) of the same pixel in all target images are selected and combined to form a target pixel. All target pixels are then combined to form a result image, which is the recognition image for image recognition. The scanning device can easily obtain RGB data, acquiring corresponding RGB data under different lighting conditions. The minimum values ​​of R, G, and B in the RGB data channels of the same pixel are selected and recombine to form a target pixel. The target pixels are then combined to form target RGB data, thus obtaining the recognition result image. The calculation process is simplified. Since the resulting image is composed of target pixels formed by combining the minimum R, G, and B values ​​from the RGB values ​​of all target images, the resulting image contains little or no light spots. This achieves the purpose of eliminating or reducing light spots in the target image, thereby improving the accuracy of image recognition. Using the embodiments of this invention, not only can result images with no or virtually no light spots be obtained, greatly improving the accuracy of image recognition, but also, since a high-accuracy recognition result can be obtained from a single shot, the efficiency of image recognition is effectively improved.

[0026] The RGB color model is an industry-standard color model that uses variations in the red (R), green (G), and blue (B) color channels and their combinations to create a wide variety of colors. The RGB color model assigns an intensity value from 0 to 255 to the R, G, and B components of each pixel in an image. For example, pure red has an R value of 255, a G value of 0, and a B value of 0; gray has equal R, G, and B values ​​(except for 0 and 255); white has R, G, and B values ​​of 255; and black has R, G, and B values ​​of 0. Using only these three colors, RGB images can be mixed in different proportions to reproduce 16,777,216 colors on the screen. In RGB mode, each RGB component can use values ​​from 0 (black) to 255 (white). For example, bright red uses an R value of 246, a G value of 20, and a B value of 50. Gray is produced when all three component values ​​are equal. When all component values ​​are 255, the result is pure white; when the value is 0, the result is pure black.

[0027] Specifically, such as Figure 1 As shown, Embodiment 1 of the present invention provides a method for eliminating or mitigating the impact of laser printing on captured images, which may include:

[0028] S110: Place the object to be identified in the image acquisition area;

[0029] The object to be identified can be a second-generation ID card, passport, driver's license, or vehicle registration certificate, or it can be a bank card, medical insurance card, or other items that need to be image-recognized.

[0030] S120: At least two sets of light sources are used to provide illumination to the image acquisition area, and at least one original image of the object to be identified is acquired when each set of light sources provides illumination to the image acquisition area.

[0031] The light source includes at least one standard light source arranged adjacent to each other, or at least one standard light source and at least one infrared light source, or at least one standard light source, at least one infrared light source and at least one ultraviolet light source.

[0032] Standard light sources are artificial light sources that simulate various ambient light conditions, allowing production plants or laboratories to achieve lighting effects essentially consistent with those light sources in specific environments, even off-site. Standard light sources are typically installed in standard light source boxes and are primarily used to detect color deviations of objects. For example, D65—International Standard Artificial Daylight—color temperature: 6500K, power: 18W. The light source only needs to include at least one adjacent standard light source to meet the image acquisition requirements of this application.

[0033] Infrared light sources are a special type of light source that can provide high-contrast image inspection when objects are difficult to inspect within the visible light range. Therefore, when the light source includes at least one standard light source and at least one infrared light source arranged adjacent to each other, the acquired original image not only has high contrast but also has a large amount of interference information filtered out.

[0034] Ultraviolet (UV) light sources are a special type of light source; they are non-illuminating electric light sources primarily designed to generate UV radiation. To utilize the fluorescence effect of UV light sources, the light source may also include a UV light source to excite fluorescent agents to emit light, and it can also be used to verify the authenticity of documents.

[0035] In one feasible implementation, the light source includes a standard light source, an infrared light source, and an ultraviolet light source.

[0036] In this step, the original images of the object to be identified are collected; that is, two original images of the object to be identified are collected.

[0037] To further improve the recognition rate and efficiency of image OCR (Optical Character Recognition), two or more sets of light sources can be used. With each set of light sources providing illumination to the image acquisition area, at least one original image of the object to be identified is acquired, thereby acquiring multiple original images of the object to be identified and proceeding to the next step.

[0038] S130: Convert all the original images into target images in RGB color mode;

[0039] Each pixel in the target image in RGB color mode has a red component, a green component, and a blue component, so that the next step of selection is made based on the red component, green component, and blue component of that pixel.

[0040] S140: Select the minimum values ​​of the R channel, G channel, and B channel of the same pixel in the target image and combine them into a target pixel;

[0041] For example, if the RGB values ​​of the same pixel in the first target image are (120, 240, 130), and the RGB values ​​of the same pixel in the second target image are (250, 125, 255), then the R channel (red component) of the first target image (120), the G channel (green component) of the second target image (125), and the B channel (blue component) of the first target image (130) are selected; and the RGB values ​​(120, 125, 130) are combined to form the target pixel.

[0042] The advantage of this method is that:

[0043] First, it eliminates the need to calculate the grayscale value of each pixel, thus reducing the computational load.

[0044] Second: Avoid highlighting a single channel or two channels in a pixel, as this will affect the final composite effect;

[0045] For example, the RGB values ​​of the same pixel in the first target image are (120, 240, 130); the RGB values ​​of the same pixel in the second target image are (250, 125, 255). If a grayscale algorithm is used, the grayscale value of the same pixel in the first target image is 191.58, and the grayscale value of the same pixel in the second target image is 177.195. According to the rule of selecting the pixel with the smallest grayscale value, the pixel in the second target image should be selected as the target pixel. Obviously, the pixel (250, 125, 255) in the second target image has bright R channel (red component) and B channel (blue component) (i.e., there is a bright spot). However, the target pixel obtained by the new method is (120, 125, 130), and there are no bright spots (i.e., no bright spots) in any of the channels.

[0046] The grayscale value algorithm is calculated according to the following formula: Grey = 0.299*R + 0.587*G + 0.114*B.

[0047] S150: Combine the target pixels into a result image;

[0048] The resulting image in S150, formed by stitching together all the target pixels obtained in step S140, has had its light spots eliminated or reduced, and can obtain a high-accuracy image recognition result when performing the next image recognition step.

[0049] As can be seen from the above, by using the implementation scheme of this application, a result image with no or almost no light spots can be obtained, thereby improving the accuracy of image recognition. At the same time, since a recognition result with a high accuracy rate can be obtained from a single shot, the efficiency of image recognition can also be effectively improved. The minimum values ​​of R, G, and B in the RGB data channel of the same pixel are selected and recombined into the target pixel. The target pixel is then used to form the target RGB data, thereby obtaining the recognition result image. The entire data processing process is simplified, eliminating the need for complex processing and simplifying the calculation program.

[0050] Based on the same inventive concept, Embodiment 1 of the present invention also provides a reading device for eliminating or mitigating the impact of laser printing on captured images, as described in the following embodiments. Since the principle of the reading device for eliminating or mitigating the impact of laser printing on captured images is similar to that of the reading method for eliminating or mitigating the impact of laser printing on captured images, the implementation of the reading processing device for eliminating or mitigating the impact of laser printing on captured images can refer to the implementation of a reading method for eliminating or mitigating the impact of laser printing on captured images, and will not be repeated. As used below, the terms "unit," "subunit," or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0051] Figure 2 This is a schematic block diagram of the structure of a reading device embodiment 1 of the present invention for mitigating the impact of laser printing on captured images. While the present invention provides a device structure as shown in the following embodiments or figures, more or fewer modular units may be included in the device based on conventional or non-inventive methods. In structures where there is no logically necessary causal relationship, the modular structure of these devices is not limited to the modular structure described in the embodiments and figures of this application. When the modular structure is applied in actual devices or terminal products, it can be executed sequentially or in parallel according to the modular structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0052] Specifically, such as Figure 2 As shown, the reading device of the present invention for eliminating or mitigating the impact of laser printing on captured images includes:

[0053] At least two sets of light sources 210, an image acquisition module 220, and an image processing module 230.

[0054] The light source 210 is used to provide illumination to the image acquisition area;

[0055] The image acquisition module 220 is used to acquire at least one original image of the object to be identified placed in the image acquisition area when each group of light sources 210 provides illumination to the image acquisition area, and to convert all the original images into target images in RGB color mode.

[0056] The image processing module 230 includes a selection unit 231, a combination unit 232, and a processing unit 233. The selection unit 231 is used to select the minimum value of the R channel, the minimum value of the G channel, and the minimum value of the B channel. The combination unit 232 is used to combine the minimum values ​​of the R channel, the minimum value of the G channel, and the minimum value of the B channel selected from the same pixel in all the target images into a target pixel. The processing unit 233 is used to stitch all the target pixels together to form a result image.

[0057] The light source 210 includes at least one standard light source 211 and / or at least one infrared light source 212 and / or at least one ultraviolet light source 213 arranged adjacent to each other; and at least two sets of the light sources 210 are arranged adjacent to each other. That is, the light source 210 includes at least one standard light source 211 arranged adjacent to each other, or the light source 210 includes at least one standard light source 211 and at least one infrared light source 212 arranged adjacent to each other, or the light source 210 includes at least one standard light source 211, at least one infrared light source 212 and at least one ultraviolet light source 213 arranged adjacent to each other, or the light source 210 includes at least one standard light source 211, at least one infrared light source 212 and at least one ultraviolet light source 213 arranged adjacent to each other.

[0058] In a preferred embodiment, the recognition device for eliminating or mitigating the impact of laser printing on captured images includes two sets of light sources 210; and the image acquisition module 220 is used to acquire an original image of the object to be identified placed in the image acquisition area when each set of light sources 210 provides illumination to the image acquisition area.

[0059] Specific Implementation Example 2: Please refer to Figure 3 As shown, Figure 3 This is a flowchart of Embodiment 2 of a method for eliminating or mitigating the impact of laser printing on captured images according to the present invention. Although the present invention provides method operation steps as shown in the following embodiments or figures, the method may include more or fewer operation steps based on conventional or non-inventive effort. For steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order described in the embodiments and figures of the present invention. When the method is applied in actual devices or terminal products, it can be executed sequentially or in parallel according to the methods shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0060] This invention provides a method for recognizing images by eliminating or mitigating the impact of laser printing on captured images. Multiple light sources are set up, and with different light sources illuminating the image acquisition area, multiple or two original images of the object to be identified in the image acquisition area are acquired. All the original images are converted to RGB color mode and then to HSL or HSV (HSB) target images. By comparing the brightness (L) or lightness (V) (B) values ​​of all pixels in all the target images, the pixel with the smallest brightness (L) or lightness (V) / B value among all pixels in the target images is selected as the target pixel. All the target pixels are converted to RGB color mode and stitched together to form a result image, which is the recognition image for image recognition. Converting RGB data to HSL or HSV (HSB) mode, taking the minimum brightness (L) or lightness (V) (B) value for the same pixel to obtain the target pixel, and then converting to RGB color mode to obtain the result image simplifies the comparison steps and obtains the target pixel more quickly. Since the target image is composed of pixels with the smallest brightness (L) value, luminance (B) value, or V(B) value within the same pixel, the resulting image contains little or no light spots. This eliminates or reduces light spots in the target image, improving the accuracy of image recognition. Using the embodiments of this invention, not only can result images with no or virtually no light spots be obtained, significantly improving image recognition accuracy, but also, since a high-accuracy recognition result can be obtained from a single capture, the efficiency of image recognition is effectively improved.

[0061] HSL color model is another color standard in the industry. It obtains various colors by changing the three color channels of Hue, Saturation, and Lightness, and their superposition. The H (hue) component of HSL represents the range of colors that the human eye can perceive. These colors are distributed on a flat color wheel, with values ​​ranging from 0° to 360°, each angle representing a different color. The significance of hue values ​​is that we can change colors by rotating the color wheel without altering the perception of light. In practical applications, we need to remember the six primary colors on the color wheel as basic references: 360° / 0° red, 60° yellow, 120° green, 180° cyan, 240° blue, and 300° magenta. They are arranged on the color wheel at 60° intervals. HSV is another color standard used in the industry. It expresses color images using three parts: Hue (hue), Saturation (saturation, color purity), and Value (brightness). Also known as HSB, where B stands for Brightness. In HSV mode, H (hue) represents hue, S (saturation) represents saturation, and V (value) represents brightness. The medium corresponding to HSV mode is the human eye. Hue (H, hue): On a standard color wheel from 0° to 360°, the hue... Hue is measured by position. In common usage, hue is identified by the color name, such as red, green, or orange. Black and white have no hue. Saturation (S) represents the purity of a color. A value of 0 indicates gray. White, black, and other gray colors have no saturation. At maximum saturation, each hue has the purest light. The value range is 0-100%. Brightness (V, value or B, brightness) is the lightness or darkness of a color. A value of 0 indicates black. Maximum brightness is the most vivid state of a color. The value range is 0-100%. HSL or HSV (HSB) are both representations of points in the RGB color model in a cylindrical coordinate system. The difference between HSV (HSB) and HSL: HSV and HSL are literally the same. H refers to hue (Hu), which is the name of the color, such as red, blue, etc.; S refers to saturation, i.e., the purity of the color; L (Lightness) and V / B (Value / Brightness) refer to lightness or darkness, the brightness of the color.In principle and performance, H (hue) in HSL and HSV are completely the same, but S (saturation) and L (brightness) are different. In HSB, S controls the amount of white mixed into a pure color. The higher the value, the less white and the purer the color. In HSV, V controls the amount of black mixed into a pure color. The higher the value, the less black and the higher the brightness. In HSL, S has nothing to do with black and white. Saturation does not control the amount of black and white mixed into a color. In HSL, L controls the amount of black and white mixed into a pure color.

[0062] Specifically, such as Figure 3 As shown, Embodiment 2 of the present invention provides a method for eliminating or mitigating the impact of laser printing on captured images, comprising:

[0063] S310: The steps are the same as S110.

[0064] S320: The steps are the same as S120.

[0065] S330: Convert the original image into a target image in RGB color mode, and then convert it into a target image in HSL or HSV color mode.

[0066] The following formulas can be used to convert images between RGB and HSL color modes, or between RGB and HSV (HSB) color modes:

[0067] Formula for converting RGB color mode to HSL color mode:

[0068] r, g, and b are the components of the corresponding channels in the RGB color mode, max = max(r, g, b), min = min(r, g, b), where r, g, and b are real numbers between 0 and 1, and h, s, and l are the components of the corresponding channels in the HSL color mode, where h ∈ [0°, 360°] hue angle, and s and l ∈ [0, 1] saturation and brightness, respectively.

[0069]

[0070]

[0071]

[0072] Formula for converting HSL color mode to RGB color mode:

[0073] h, s, and l are the components of the corresponding channels in the HSL color mode, where h ∈ [0°, 360°] is the hue angle, and s and l ∈ [0, 1] are saturation and brightness, respectively. r, g, and b are the components of the corresponding channels in the RGB color mode, corresponding to red, green, and blue, respectively, with values ​​in the range [0, 1]. First, if s = 0, the resulting color is achromatic or gray. In this special case, r, g, and b are all equal to l. Note that the value of h is undefined in this case. When s ≠ 0, the following conversion process can be used:

[0074]

[0075] p = 2 × lq

[0076] (h is normalized to the range [0, 1))

[0077]

[0078] t G =h k

[0079]

[0080] if t C <0→t C =t C +1.0 for each C∈{R,G,B}

[0081] if t C >1→t C =t C -1.0 for each C∈{R,G,B}

[0082] For each color vector Color = (Color R Color G Color B ) = (r, g, b),

[0083]

[0084] for each C∈{R,G,B}

[0085] Formula for converting RGB color mode to HSV color mode:

[0086] r, g, and b are the components of the corresponding channels in the RGB color mode, where max = max(r, g, b) and min = min(r, g, b). r, g, and b are real numbers between 0 and 1, and can be converted using the following process:

[0087]

[0088]

[0089] v = max

[0090] Formula for converting HSV color mode to RGB color mode:

[0091] Where h, s, and v are the components of the corresponding channels in the HSL color mode, where h∈[0°, 360°] is the hue angle, and s and v∈[0, 1] are saturation and lightness, respectively; r, g, and b are the components of the corresponding channels in the RGB color mode, corresponding to red, green, and blue, respectively. r, g, and b are also in the value range [0, 1], and can be converted using the following process:

[0092]

[0093]

[0094] p = v × (1 - s)

[0095] q = v × (1 - f × s)

[0096] t = v × (1 - (1 - f) × s)

[0097] For each color component (r, g, b),

[0098]

[0099] Each pixel in the target image under HSL or HSV (HSB) color mode has three color channel components: HSL: Hue (H), Saturation (S), and Lightness (L), or HSV (HSB): Hue (H), Saturation (S), and Value / Brightness (V / B), for the next comparison.

[0100] S340: Compare the lightness (L) value or brightness (V / B) value of all pixels in the target image, and select the pixel with the smallest lightness (L) value or brightness (V / B) value as the target pixel from all pixels in the same image.

[0101] S350: Convert the target pixels to RGB color mode and stitch them together to form a result image.

[0102] The resulting image in S350, formed by stitching together all the target pixels obtained in step S340, has had its light spots eliminated or reduced, thus enabling a more accurate image recognition result in the next step of image recognition.

[0103] As described above, the implementation scheme of this application can obtain images with little or no light spots, improving the accuracy of image recognition. Furthermore, since a high-accuracy recognition result can be obtained from a single shot, the efficiency of image recognition is also effectively improved. The target pixel is obtained by taking the minimum value of the brightness (L) or luminance (V(B)) value of the same pixel, and then converting it to RGB color mode to obtain the result image. This simplifies the comparison steps and allows for faster acquisition of the target pixel.

[0104] Based on the same inventive concept, Embodiment 2 of the present invention also provides a reading device for eliminating or mitigating the impact of laser printing on captured images, as described in the following embodiments. Since the principle of the reading device for eliminating or mitigating the impact of laser printing on captured images is similar to that of the reading method for eliminating or mitigating the impact of laser printing on captured images, the implementation of the reading processing device for eliminating or mitigating the impact of laser printing on captured images can refer to the implementation of a reading method for eliminating or mitigating the impact of laser printing on captured images, and will not be repeated. As used below, the terms "unit," "subunit," or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0105] Figure 4 This is a schematic block diagram of a second embodiment of a recognition device for mitigating the impact of laser printing on captured images, according to an embodiment of the present invention. While the invention provides device structures as shown in the following embodiments or figures, more or fewer modular units may be included in the device based on conventional or non-inventive effort. In structures where there is no logically necessary causal relationship, the modular structures of these devices are not limited to the modular structures described in the embodiments and figures of this application. When applied in actual devices or terminal products, the modular structures can be executed sequentially or in parallel according to the modular structures shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0106] Specifically, such as Figure 4 As shown, a reading device for eliminating or mitigating the impact of laser printing on captured images according to Embodiment 2 of the present invention includes:

[0107] At least two light sources 410, an image acquisition module 420, and an image processing module 430.

[0108] The light source 410 is used to provide illumination to the image acquisition area;

[0109] The image acquisition module 420 is used to acquire at least one original image of the object to be identified placed in the image acquisition area when each group of light sources 410 provides illumination to the image acquisition area, and to convert all the original images into target images of HSL or HSV (HSB).

[0110] The image processing module 430 includes a calculation unit 431, a determination unit 432, and a processing unit 433. The calculation unit 431 is used to calculate the brightness L value or lightness V / B value of all pixels in all the target images. The determination unit 432 is used to select the pixel with the smallest brightness L value or lightness V / B value among the same pixels in all the target images as the target pixel. The processing unit 433 is used to convert all the target pixels into RGB color mode and stitch them together to form a result image.

[0111] The calculation unit calculates all pixels of the target image using the following formula, and converts the image between RGB and HSL color modes or between RGB and HSV color modes using the following formula:

[0112] Formula for converting RGB color mode to HSL color mode:

[0113] r, g, and b are the components of the corresponding channels in the RGB color mode, max = max(r, g, b), min = min(r, g, b), where r, g, and b are real numbers between 0 and 1, and h, s, and l are the components of the corresponding channels in the HSL color mode, where h ∈ [0°, 360°] is the hue angle, and s and l ∈ [0, 1] are saturation and brightness.

[0114]

[0115]

[0116]

[0117] Formula for converting HSL color mode to RGB color mode:

[0118] h, s, and l are the components of the corresponding channels in the HSL color mode, where h ∈ [0°, 360°] is the hue angle, and s and l ∈ [0, 1] are the saturation and brightness, respectively. r, g, and b are the components of the corresponding channels in the RGB color mode, corresponding to red, green, and blue, respectively. r, g, and b are also in the value range [0, 1]. First, if s = 0, the resulting color is achromatic or gray. In this special case, r, g, and b are all equal to l. Note that the value of h is undefined in this case. When s ≠ 0, the following conversion process can be used:

[0119]

[0120] p = 2 × lq

[0121] (h is normalized to the range [0, 1))

[0122]

[0123] t G =h k

[0124]

[0125] if t C <0→t C =t C +1.0 for each C∈{R,G,B}

[0126] if t C >1→t C =t C -1.0 for each C∈{R,G,B}

[0127] For each color vector Color = (Color R Color G Color B ) = (r, g, b),

[0128]

[0129] for each C∈{R,G,B}

[0130] Formula for converting RGB color mode to HSV color mode:

[0131] r, g, and b are the components of the corresponding channels in the RGB color mode, where max = max(r, g, b) and min = min(r, g, b). r, g, and b are real numbers between 0 and 1, and can be converted using the following process:

[0132]

[0133]

[0134] v = max

[0135] Formula for converting HSV color mode to RGB color mode:

[0136] Where h, s, and v are the components of the corresponding channels in the HSL color mode, h∈[0°, 360°] is the hue angle, and s and v∈[0, 1] are saturation and lightness, respectively; r, g, and b are the components of the corresponding channels in the RGB color mode, corresponding to red, green, and blue, respectively. r, g, and b are also in the value range [0, 1], and can be converted using the following process:

[0137]

[0138]

[0139] p = v × (1 - s)

[0140] q = v × (1 - f × s)

[0141] t = v × (1 - (1 - f) × s)

[0142] For each color component (r, g, b),

[0143]

[0144] The light source 410 includes at least one standard light source 411 and / or at least one infrared light source 412 and / or at least one ultraviolet light source 413 arranged adjacent to each other; and at least two sets of the light sources 410 are arranged adjacent to each other. That is, the light source 410 includes at least one standard light source 411 arranged adjacent to each other, or the light source 410 includes at least one standard light source 411 and at least one infrared light source 412 arranged adjacent to each other, or the light source 410 includes at least one standard light source 411, at least one infrared light source 412 and at least one ultraviolet light source 413 arranged adjacent to each other, or the light source 410 includes at least one standard light source 411, at least one infrared light source 412 and at least one ultraviolet light source 413 arranged adjacent to each other.

[0145] In a preferred embodiment, the recognition device for eliminating or mitigating the impact of laser printing on captured images includes two sets of light sources 410; and the image acquisition module 420 is used to acquire an original image of the object to be identified placed in the image acquisition area when each set of light sources 410 provides illumination to the image acquisition area.

[0146] The apparatus or module described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. For ease of description, the above apparatus is described by dividing it into various modules according to their functions. In implementing this application, the functions of each module can be implemented in one or more software and / or hardware. Of course, a module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0147] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, or it can be embodied in the process of data migration. All or part of the present invention can be used in a variety of general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, mobile communication terminals, multiprocessor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0148] Although the invention has been described by way of examples, those skilled in the art will recognize that the invention has many variations and modifications without departing from the spirit of this application, and it is intended that the appended claims cover such variations and modifications without departing from the spirit of the invention.

Claims

1. A method of reading to eliminate or reduce the effect of laser printing on a captured image, characterized by, The method comprises the following steps: Placing the object to be identified in an image acquisition area; Providing illumination to the image acquisition area by at least two groups of light sources, and acquiring at least one original picture of the object to be identified under the illumination of each group of light sources; Converting the original picture into a target picture in RGB color mode, selecting the minimum values of R channel, G channel and B channel of the same pixel point of the target picture, combining them into a target pixel point, and splicing the target pixel points into a result picture; Or Converting the original picture into a target picture in RGB color mode, and then converting it into HSL mode, selecting the minimum value of L value of the same pixel point of the target picture as a target pixel point, converting the target pixel point into RGB color mode and splicing it into a result picture; Or Converting the original picture into a target picture in RGB color mode, and then converting it into HSV mode, selecting the minimum value of V value of the same pixel point of the target picture as a target pixel point, converting the target pixel point into RGB color mode and splicing it into a result picture.

2. The method of claim 1, wherein, The light source comprises at least one standard light source arranged adjacent to each other, or at least one standard light source and at least one infrared light source, or at least one standard light source, at least one infrared light source and at least one ultraviolet light source.

3. A reading device that eliminates or mitigates the effects of laser printing on a captured image, characterized by, The reading device for eliminating or reducing the influence of laser printing on the photographed image comprises at least two groups of light sources, an image acquisition module and an image processing module, The light source is used to provide illumination to the image acquisition area; The image acquisition module is used to acquire at least one original picture of the object to be identified placed in the image acquisition area under the illumination of each group of light sources, and convert all the original pictures into target pictures in RGB color mode; The image processing module is used to select the minimum values of R channel, G channel and B channel of the same pixel point of all the target pictures in RGB color mode, combine them into a target pixel point, and splice all the target pixel points into a result picture; Or select the minimum value of L value of the same pixel point of all the target pictures in HSL mode as a target pixel point, convert the target pixel point into RGB color mode and splice it into a result picture; Or select the minimum value of V value of the same pixel point of all the target pictures in HSV mode as a target pixel point, convert the target pixel point into RGB color mode and splice it into a result picture.

4. The reading apparatus according to claim 3, wherein The image processing module comprises a calculation unit, a determination unit and a processing unit; the calculation unit is used to calculate the brightness L value or the lightness V value of all the pixel points of all the target pictures; the determination unit is used to select the pixel point with the minimum brightness L value or lightness V value in the same pixel point of all the target pictures as a target pixel point; and the processing unit is used to convert all the target pixel points into RGB color mode and splice them into a result picture.

5. The reading apparatus according to claim 4, wherein The reading device comprises two groups of the light sources; and the image acquisition module is configured to acquire an original picture of the to-be-identified object placed in the image acquisition area under the condition that each group of the light sources provides illumination to the image acquisition area.

6. The reading apparatus according to claim 5, wherein The light source comprises at least one standard light source, or at least one standard light source and at least one infrared light source, or at least one standard light source, at least one infrared light source and at least one ultraviolet light source.

7. The reading device according to any one of claims 4 to 6, wherein The light source comprises one standard light source, one infrared light source and one ultraviolet light source.

Images