CN114298932A - A text enhancement processing method, device, equipment and medium - Google Patents

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for character enhancement processing. The method comprises the following steps: acquiring a scanning gray scale image with uniform brightness; performing enhancement processing on the edge points of the scanning gray level image to obtain a target image with hardened text edges; adjusting the gray distribution interval of the target image to obtain an adjusted image; and carrying out edge marking and edge enhancement processing on the adjusted image to obtain a character enhanced image. By the technical scheme of the embodiment of the invention, the character enhancement processing can be carried out on the character image while the algorithm complexity is simplified, the algorithm running speed is increased and the accuracy of the printed characters is ensured, so that the speed and the accuracy of the character enhancement are increased.

Description

A text enhancement processing method, device, equipment and medium

technical field

Embodiments of the present invention relate to image processing technologies, and in particular, to a text enhancement processing method, apparatus, device, and medium.

Background technique

With the gradual development of science and technology, people have higher requirements for the clarity of text printed by copiers and printers. Therefore, it is necessary to use an image text enhancement algorithm to perform text enhancement processing on the scanned text image, so as to improve the clarity of the printed text.

In the prior art, a series of algorithms such as edge finding, image blurring, layer stacking, and contrast enhancement operations are usually used to enhance the edges of image text. It is complicated and causes great troubles to equipment with limited resources and high real-time requirements. Therefore, how to perform text enhancement processing on text images while simplifying the complexity of the algorithm, improving the running speed of the algorithm and ensuring the accuracy of the printed text is an urgent problem to be solved at present.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a text enhancement processing method, device, device and medium, which can implement text enhancement processing on text images while simplifying algorithm complexity, improving algorithm running speed, and ensuring the accuracy of printed text.

In a first aspect, an embodiment of the present invention provides a text enhancement processing method, including:

Obtain a scanned grayscale image with uniform brightness;

Performing enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges;

Adjusting the gray distribution interval of the target image to obtain an adjusted image;

Perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image.

In a second aspect, an embodiment of the present invention further provides a text enhancement processing device, the device comprising:

The data acquisition module is used to acquire the scanned grayscale image with uniform brightness;

a first enhancement processing module, configured to perform enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges;

a grayscale distribution interval adjustment module, which is used to adjust the grayscale distribution interval of the target image to obtain an adjusted image;

The second enhancement processing module is configured to perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image.

In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

one or more processors;

storage means for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the text enhancement processing method according to any embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the text enhancement described in any embodiment of the present invention is implemented Approach.

The technical scheme of the embodiment of the present invention obtains the target image by performing edge point enhancement processing on the acquired scanned grayscale image with uniform brightness, then adjusts the grayscale distribution interval of the target image, and performs edge marking and edge enhancement processing on the adjusted image. , obtain text-enhanced images, solve the problem that the algorithm preprocessing process used in the prior art is too complicated, and cause great troubles to equipment with limited resources and high real-time requirements, and realizes simplifying algorithm complexity and improving algorithm operation. While ensuring the accuracy of the printed text, the text image is enhanced.

Description of drawings

1 is a schematic flowchart of a text enhancement method in the prior art;

2a is a flowchart of a text enhancement processing method provided by an embodiment of the present invention;

2b is a schematic diagram of an image detail display provided by an embodiment of the present invention;

2c is a schematic diagram of the distribution of a grayscale distribution interval provided by an embodiment of the present invention;

3a is a flowchart of a text enhancement processing method provided by an embodiment of the present invention;

3b is a schematic diagram of a surrounding pixel pattern diagram provided by an embodiment of the present invention;

3c is a schematic diagram of a result of a target image provided by an embodiment of the present invention;

3d is a schematic diagram of a result of adjusting an image according to an embodiment of the present invention;

3e is a schematic diagram of a process for generating a target marker map according to an embodiment of the present invention;

3f is a schematic diagram of a target edge filtering graph provided by an embodiment of the present invention;

3g is a schematic diagram of a result of superimposing a target marker map and a target edge filter map according to an embodiment of the present invention

3h is a schematic diagram of a text-enhanced image generation process provided by an embodiment of the present invention;

3i is a schematic diagram of a result of a text-enhanced image provided by an embodiment of the present invention;

3j is a schematic diagram of a result of a binarization process provided by an embodiment of the present invention;

Fig. 4a is a schematic diagram of the flow of a preferred text enhancement processing method provided by an embodiment of the present invention;

4b is a schematic diagram of a result of a halftone image provided by an embodiment of the present invention;

5 is a schematic structural diagram of a text enhancement processing device provided by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, the drawings only show some but not all structures related to the present invention.

FIG. 1 is a schematic flowchart of a text enhancement method in the prior art. First, use coarse positioning or fine positioning to identify the text area and the picture area, and separate the text area from the picture area; further, perform image optimization processing on the text area, eliminate invalid pixels in the background, scan the pixels to confirm the text edge points and continue to search Adjacent edge points, record the edge position data; further, blur the original image of the text image, superimpose the edge position deepening map with the blurred edge, and superimpose it on the original image; finally, perform dynamic contrast enhancement on the text area to make the text as a whole. clear. However, the recognition algorithm and feature analysis algorithm used in the text enhancement method used in the prior art have high complexity and unstable accuracy, and a large number of floating-point operations will lead to a decrease in operating efficiency; When identifying the edge points of the text, the edge recognition algorithm is easily affected by the characteristics of the input image itself. If the text in the image is not clear, it will increase the calculation amount of the edge recognition algorithm, resulting in a large memory consumption. . Therefore, the text enhancement method used in the prior art is quite challenging for embedded devices that require high integration, computational complexity and real-time performance.

Therefore, in order to solve the problem that the algorithm preprocessing process used in the prior art is too complicated and causes great trouble to devices with limited resources and high real-time requirements, an embodiment of the present invention proposes a text enhancement processing method.

FIG. 2a is a flowchart of a text enhancement processing method provided by an embodiment of the present invention. This embodiment can be applied to the case of performing enhancement processing on text in an image. The method can be executed by a text enhancement processing device, and the device can It is implemented by means of hardware and/or software, and can generally be integrated into electronic devices, such as copiers, printers, or embedded devices such as text scanning and recognition devices.

As shown in FIG. 2a, a text enhancement processing method provided by an embodiment of the present invention includes the following specific steps:

S210: Obtain a scanned grayscale image with uniform brightness.

The scanned grayscale image may refer to a grayscale image scanned by a contact image sensor (Contact Image Sensor, CIS). The scanned grayscale image with uniform brightness may refer to the scanned grayscale image with uniform grayscale distribution, and the grayscale interval is a standard image with a grayscale value of 0-255.

S220: Perform enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges.

Among them, the edge point can refer to the pixel point on the edge of the text image in the scanned grayscale image; the edge of the text image can also be called the shadow area, which is a gradient area from black to white. When the camera accuracy and various indicators meet the requirements, the shadow area Can be controlled in one pixel. The enhancement processing may refer to deepening the pixel value of the edge point of the text to enhance the edge point of the text, for example, setting the pixel value of the edge point of the text to a smaller pixel value than the pixel value of the current edge point. The target image may refer to the hardened grayscale image of the text edge obtained after edge point enhancement processing.

S230: Adjust the gray distribution interval of the target image to obtain an adjusted image.

FIG. 2b is a schematic diagram of an image detail display provided by an embodiment of the present invention. After the grayscale image is converted into a binary image, as shown in Figure 2b, the first two lines of numbers in the first line of text images are displayed more clearly than the last line of numbers; the numbers in the second line of text images can be clearly displayed ; The second line of numbers in the third line of text images can hardly be displayed clearly; the first two lines of numbers in the fourth line of text images can hardly be displayed clearly. Therefore, in order to improve the final performance effect of the text image, ensure that the contrast between light and dark is clearer, and the image details are more obvious, it is necessary to adjust the grayscale distribution interval of the text image.

FIG. 2c is a schematic diagram of the distribution of a gray-scale distribution interval provided by an embodiment of the present invention, wherein the black marks are the ink points of the printing press. In the embodiment of the present invention, a cylinder type ink printing machine is used as a test machine, and the gray scale distribution interval is adjusted as shown in Figure 2c. In the area with lower value, the degree of discrimination is not obvious, so it is necessary to deepen the dark part to make more grayscale intervals; the degree of discrimination in the second dark part (80-120) is still not obvious, so it is also necessary to expand the range to improve the contrast. ; The bright part (120~240) has obvious contrast, and the interval can be compressed to the right to make room for the second dark part; the highlight part (above 240) does not change much, and does not need to be adjusted again. Finally, the gray distribution interval of the dark part of the image is 0-50, the sub-dark part is 50-155, the bright part is 155-245, and the highlight part is 245-255. Therefore, by adjusting the grayscale image of the text image, the dark part of the text image can be made darker, and the bright part of the text image can be brighter, so that the edge of the text can be sharper, and the text can be enhanced while taking into account the clarity of the image.

It is worth noting that although the distribution schematic diagram of a grayscale distribution interval provided by the embodiment of the present invention can reflect the trend of visual uniform change, different printing methods and printing conditions will affect the size of the ink dots, resulting in actual printing. Therefore, in different application environments, the parameters should be further adjusted or processed according to the properties of the machine and consumables on the basis of the embodiment of the present invention, which is not limited in the embodiment of the present invention .

S240: Perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image.

The edge marking may refer to marking the text edge points in the adjusted image, for example, the text edge points in the adjusted image may be marked at corresponding positions in the marking map in a newly created marking map. The edge enhancement processing may refer to enhancing the edge points obtained by the edge marking to obtain the text-enhanced image after edge enhancement.

The technical scheme of the embodiment of the present invention obtains the target image by performing edge point enhancement processing on the acquired scanned grayscale image with uniform brightness, then adjusts the grayscale distribution interval of the target image, and performs edge marking and edge enhancement processing on the adjusted image. , obtain text-enhanced images, solve the problem that the algorithm preprocessing process used in the prior art is too complicated, and cause great troubles to equipment with limited resources and high real-time requirements, and realizes simplifying algorithm complexity and improving algorithm operation. While ensuring the accuracy of the printed text, the text image is enhanced.

FIG. 3a is a flowchart of a text enhancement processing method provided by an embodiment of the present invention. In this embodiment, optionally, performing enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges includes: using the surrounding pixel pattern map to perform an enhancement process on each pixel in the scanned grayscale image. Analyze, obtain the target edge point and reference point of the text; Determine the edge deepening pixel value based on the pixel value of the reference point and the pixel value of the target edge point, and utilize the edge deepening pixel value to the target edge in the scanning grayscale image Point to darken to get the target image with hardened text edges.

Optionally, performing edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image includes: constructing a marker map whose initial value of each pixel value is a minimum pixel value; obtaining a pixel value in the adjusted image that is greater than or equal to Mark the pixel value of the target pixel of the background value, and calculate the number of pixels whose pixel value is lower than the marked entity value and the number of pixels whose pixel value is higher than the marked background value in the set area centered on the target pixel. If the first number is less than or equal to the first number threshold or the second number is less than or equal to the second number threshold, the corresponding position of the target pixel in the marker map The pixel value of is marked as the first target pixel value, otherwise, marked as the pixel value of the target pixel point, to obtain a preprocessing mark map; wherein, the first quantity threshold is less than the second quantity threshold; the first target pixel value is greater than the minimum pixel value; search the preset area centered on the pixel whose pixel value is greater than the background value of the marker in the preprocessing marker map, and set the pixel value in the preset area equal to the minimum pixel value The pixel value of the pixel point of the value is marked as the second target pixel value, and the target marker map is obtained; wherein, the second target pixel value is greater than the first target pixel value; the adjusted image is backed up to obtain a copy of the adjusted image, Filling and blurring the adjusted image copy according to the target marker map to obtain a blurred image, and using the blurred image to perform edge enhancement processing on the adjusted image to obtain a text-enhanced image.

As shown in FIG. 3a, a text enhancement processing method provided by an embodiment of the present invention includes the following specific steps:

S310: Obtain a scanned grayscale image with uniform brightness.

S320: Use the surrounding pixel pattern map to analyze each pixel in the scanned grayscale image to obtain the target edge point and reference point of the text.

The surrounding pixel pattern map may refer to a pattern map prepared according to the surrounding environment of the pixels in the text image. Exemplarily, usually, the background pixels should be above the edge points, and the upper edge pattern map can be generated according to the pattern of the pixels above the edge points. . The target edge point may refer to the edge pixel point of the text image that needs to be obtained from the scanned grayscale image, and is usually the center point representing the entity pixel point in the surrounding pixel pattern image. The reference point may refer to a reference pixel point that can be used to process the target edge point in the scanned grayscale image.

3b is a schematic diagram of a surrounding pixel pattern diagram provided by an embodiment of the present invention, wherein M1 represents the upper edge mode, M2 represents the lower edge mode, M3 represents the left edge mode, M4 represents the right edge mode, and M5 represents the upper left edge mode. Edge mode, M6 represents the lower left edge mode, M7 represents the upper right edge mode, M8 represents the lower right edge mode, the solid circle in the figure represents the solid pixel point, the blank circle represents the background pixel point, X represents the reference point, and the solid circle with the gray background represents the target edge point. Among them, it is necessary to determine whether the current pixel is a solid pixel or a background pixel according to two thresholds. Exemplarily, in this embodiment of the present invention, the pixel value threshold of the background pixel is set to dW, and the The pixel value threshold is set to dB. If the pixel value of the current pixel is less than dB, the pixel is determined to be a solid pixel. If the pixel value of the current pixel is greater than dW, the pixel is determined to be a background pixel. In the embodiment of , the dW value is 250, and the dB value can be 160-240 according to the actual needs of the image. Specifically, first, each pixel in the scanned grayscale image is scanned, and each pixel in the scanned grayscale image is determined according to the pixel value threshold to obtain a solid pixel point and a background pixel point, and then according to the surrounding pixel pattern map The position of each pixel point in M1-M8 can determine the target edge point and the reference point.

S330: Determine an edge deepening pixel value based on the pixel value of the reference point and the pixel value of the target edge point, and use the edge deepening pixel value to deepen the target edge point in the scanned grayscale image to obtain a text edge hardening target image.

Wherein, the edge deepening pixel value may refer to the calculated pixel value that deepens the pixel value of the target edge point. Exemplarily, the middle value of the pixel value of the reference point and the pixel value of the target edge point may be used as the edge deepening pixel. value. Specifically, if the position of each pixel in the scanned grayscale map matches the position of each pixel in the surrounding pixel pattern maps M1-M8, after determining the target edge point and the reference point, you can follow the formula: edge deepening pixel value =(the pixel value of the reference point + the pixel value of the target edge point)/2, calculate the edge deepening pixel value, and use the calculated edge deepening pixel value to deepen the target edge point in the scanned grayscale image to obtain target image.

In an optional implementation manner, the step of deepening the target edge points in the scanned grayscale image by using the edge deepening target value to obtain the target image of text edge hardening includes: obtaining the image obtained by calculating in each surrounding pixel pattern map. The minimum edge deepening pixel value, and the minimum edge deepening pixel value is compared with the pixel value of the target edge point; if the minimum edge deepening pixel value is less than the pixel value of the target edge point, then the target edge point The pixel value is assigned as the minimum edge deepening pixel value to obtain the target image with hardened text edges. Specifically, if the position of each pixel in the scanned grayscale image is successfully matched with the position of each pixel in the surrounding pixel pattern map M1, the edge deepening pixel value VT1 is calculated, and if the edge deepening pixel value VT1 is smaller than the pixel of the target edge point value, then the pixel value of the target edge point is assigned as the edge deepening pixel value VT1; Further, the position of each pixel point in the scanning grayscale map is matched with the position of each pixel point in the surrounding pixel pattern map M2 , if the position of each pixel in the scanned grayscale image is successfully matched with the position of each pixel in the surrounding pixel pattern map M2, the edge deepening pixel value VT2 is calculated, and if the edge deepening pixel value VT2 is less than the edge deepening pixel value VT1, then Use the edge deepening pixel value VT2 to replace the edge deepening pixel value VT1, and assign the pixel value of the target edge point to the edge deepening pixel value VT2; take this as an example, and then complete the matching of the surrounding pixel pattern maps M3-M8 in turn, and finally the target The pixel value of the edge point is assigned as the minimum edge deepening pixel value, that is, the target image with hardened text edge can be obtained.

FIG. 3c is a schematic diagram of a result of a target image provided by an embodiment of the present invention. Among them, the left side is the scanned grayscale image, and the right side is the target image with hardened text edges. It can be seen from FIG. 3c that, in the target image obtained in the embodiment of the present invention, some pixels in the text edge region are obviously deepened, so that the text image is clearer.

S340: Adjust the gray distribution interval of the target image to obtain an adjusted image.

FIG. 3d is a schematic diagram of a result of adjusting an image according to an embodiment of the present invention. Among them, the left side is the target image before the gray distribution interval adjustment, and the right side is the adjusted image after the gray distribution interval adjustment. It can be seen from Figure 3d that adjusting the image has obvious contrast enhancement effect, the excess grayscale between the strokes of the word "Weng" is weakened, and the surrounding of the word "Dang" is clearer, and the transition area of the edge of the text image is distributed in the grayscale. The interval adjustment process has been lightened, which provides convenience for the follow-up work.

S350: Constructing a marker map in which the initial value of each pixel value is the minimum pixel value.

The minimum pixel value may refer to that the initial pixel value of each pixel is 0. A marker map can refer to an image in which the initial value of each pixel is 0.

S360: Acquire the pixel value of the target pixel whose pixel value is greater than or equal to the marked background value in the adjusted image, and calculate the pixel value of the pixel whose pixel value is lower than the marked entity value in the set area centered on the target pixel. The number and the number of pixel points whose pixel value is higher than the marked background value are taken as the first number and the second number, respectively.

The setting area may refer to a square area centered on the target pixel, for example, a 5×5 area centered on the target pixel. The marked background value may refer to the threshold mW used to mark the entity pixels, for example, mW may be 230; the marked entity value may refer to the threshold mB used to mark the background pixels, for example, mB may take the value of 230. 135. Generally, the pixels whose pixel values are higher than the marked background value mW are regarded as marked background pixels, and the pixels whose pixel values are lower than the marked entity value mB are regarded as marked real pixels. The first number may refer to the number nB of marked entity pixels in the set area centered on the target pixel; the second number may refer to the number nW of marked background pixels in the set area centered on the target pixel.

Specifically, scan each pixel in the adjusted image, and when the pixel value f(x, y) of the target pixel is greater than or equal to the marked background value mW, take the target pixel as the center point, and sample and analyze in the form of Table 1. Retrieve the pixels within a 5×5 range around the target pixel, and count the number nB of marked entity pixels and the number of marked background pixels nW within the 5×5 range to obtain the first number and the second number.

Table 1 takes the target pixel as the center point and the pixels in the range of 5 × 5

S370: If the first quantity is less than or equal to the first quantity threshold or the second quantity is less than or equal to the second quantity threshold, marking the pixel value at the corresponding position of the target pixel in the marking map as the first target pixel value, Otherwise, mark the pixel value of the target pixel to obtain a preprocessing mark map; wherein the first number threshold is less than the second number threshold; the first target pixel value is greater than the minimum pixel value.

Wherein, the first quantity threshold may refer to a numerical value used for evaluating the first quantity; the second quantity threshold may refer to a numerical value used for evaluating the second quantity. The first target pixel value may refer to a value that modifies the initial value of the pixel at the corresponding position of the target pixel in the marker diagram when the first quantity is less than or equal to the first quantity threshold or the second quantity is less than or equal to the second quantity threshold. Exemplarily, in the embodiment of the present invention, the first quantity threshold may be set to 1; the second quantity threshold may be set to 2; Specifically, when f(x,y)>=mW, the target pixel corresponding to f(x,y) may be the background pixel. If nB is too small, the target pixel is far away from the entity. If nW is too small, the target Pixels that are far from the blank may be in a color block. Since there are usually both solid pixels and background pixels around the edge pixels, if nB is too small or nW is too small, the target pixels cannot be used as pixels near the edge. , so when the first number nB<=1 or the second number nW<=2, the pixel value of the corresponding position (x, y) of the target pixel in the marked image is marked as 1, which is regarded as a background pixel far away from the edge , otherwise marked as the pixel value f(x,y) of the target pixel.

S380: Retrieve a preset area centered on the pixels whose pixel values are greater than the marked background value in the preprocessed marking map, and retrieve the pixels whose pixel values are equal to the minimum pixel value in the preset area. The value is marked as a second target pixel value, and a target marker map is obtained; wherein, the second target pixel value is greater than the first target pixel value.

The preset area may refer to a square area centered on a pixel whose pixel value is greater than the marked background value, exemplarily, may be a 3×3 area as shown in Table 2, where the pixel value of the center point is denoted as f(x,y). The second target pixel value may refer to a value for modifying the pixel point when there is a pixel point with the minimum pixel value in the preset area. In the embodiment of the present invention, the second target pixel value may be 2, which indicates that the pixel point is to be deepened. edge pixels.

Specifically, when retrieving the 3 × 3 range centered on the pixels whose pixel values in the preprocessing marker map are greater than the marker background value, if a pixel with a pixel value of 0 is retrieved, the pixel of the pixel is retrieved. The value is marked as 2, that is, the edge pixels to be deepened, and the final target mark map is obtained.

Table 2 Pixels within a 3×3 range centered on the pixel whose pixel value is greater than the marked background value

FIG. 3e is a schematic diagram of a process of generating a target marker map according to an embodiment of the present invention. Among them, Figure (a) is the adjusted image, Figure (b) is a partial enlarged image of the adjusted image, Figure (c) is the local target marker image, and Figure (d) is the edge pixel with a value of 2 in the target marker image. Adjusts the image resulting from the image overlay. As can be seen from Figure 3e, the edge pixels with a value of 2 in the target marker map are more accurate. If the edge of the adjusted image is enhanced again according to the target marker map, the resulting image (d) will be more accurate than image (a). There are better text enhancements.

S390: Backing up the adjusted image to obtain a copy of the adjusted image, and filling and blurring the copy of the adjusted image according to the target marker map to obtain a blurred image, and using the blurred image to align the adjusted image Perform edge enhancement processing to obtain text-enhanced images.

Wherein, filling the target marker map may refer to filling the pixel values of the pixel points whose pixel values in the target marker map exceed the marker background value mW. Blur processing can refer to the use of algorithms to blur the filled target marker map; through blurring processing, the background pixels and solid pixels near the text edge can simultaneously infect the text edge, and the text edge can be blurred in the process of processing. is significantly darkened, while solid pixels near the edge of the text can be lightened. The adjusted image copy may refer to a duplicate image that is backed up of the adjusted image.

In an optional implementation manner, the adjusted image copy is filled and blurred according to the target marker map to obtain a blurred image, and edge enhancement processing is performed on the adjusted image by using the blurred image , obtaining the text-enhanced image includes: replacing the pixel value of the pixel corresponding to the pixel whose pixel value in the target marker map exceeds the marker background value in the adjustment image copy with the target pixel value to obtain the target fill map; using The linear interpolation scaling method scales and transforms the target fill image to obtain a blurred image; assigns pixel values that meet the set conditions in the blurred image to corresponding positions in the adjusted image to obtain a text-enhanced image. Wherein, in this embodiment of the present invention, the target pixel value may be set to 155. The pixel value of the setting condition may refer to the pixel value of the darkened pixel point in the blurred image. Adjusting the corresponding position of the image can refer to the position of the pixel that has a value of 2 in the target marker map and is valid in the target edge filter map; it can also refer to the pixel value that is invalid in the target edge filter map but has a deep pixel value, such as pixel value The position of the pixel that is less than 80. Among them, the target edge filter map may refer to the edge filter map for judging the edge points of the adjusted image according to the surrounding pixel pattern maps M1-M8. Make solid pixels, and use non-blank pixels in the target edge filtering image as edge filtering marks. FIG. 3f is a schematic diagram of a target edge filter map provided by an embodiment of the present invention, wherein the schematic diagram is a result map after superimposing the target edge filter map and the adjusted image. Figure 3g is a schematic diagram of the superimposed result of a target marker graph and a target edge filter graph provided by an embodiment of the present invention, wherein the light gray is the edge result of the target edge filter graph, and the dark gray is the edge result of the target marker graph, The black color is the superposition result of the target marker image and the target edge filter image. Due to the edge of the marker in the target marker image, the adjacent strokes of small characters are easily marked as edge deepening, but this part of the deepening can easily make the stroke gap smaller, making the final handwriting blurred Not clear; in addition, if a circle around the text is completely marked, the edge of the mark will be too full, and after deepening, it may cause the font stroke to be too thick and a large circle thicker than the original. Therefore, when the embodiment of the present invention is actually deepened, the deepened area must be the intersection of the target marker map and the target edge filter map.

Figure 3h is a schematic diagram of a text-enhanced image generation process provided by an embodiment of the present invention, wherein Figure (a) is a target fill map, and Figure (b) is a blurred image. Exemplarily, first, replace the pixel value of the pixel point corresponding to the pixel point in the target marker image with the pixel value exceeding the marker background value mW with 155 in the adjustment image copy to obtain the target fill image, and then use the linear interpolation scaling method to fill the target image. The image is scaled twice, for example, the target fill image is first enlarged to 1.5 times, and then the enlarged image is reduced back to the original size to obtain a blurred image. If there is a pixel with a value of 2 in the target marker map and is valid in the target edge filter map, or a pixel point that is invalid in the target edge filter map but has a deep pixel value, the pixels of the pixel in the blurred image will be blurred. The value is assigned to the corresponding position of the adjusted image, and the text-enhanced image is obtained. Figure 3i is a schematic diagram showing the result of a text-enhanced image provided by an embodiment of the present invention, wherein Figure (a) is an adjusted image, and Figure (b) is an enhanced image. It can be seen from the figure that the enhanced text edge It is moderately deepened, and the parts where the strokes are approached are avoided, which is beneficial to obtain more ink dots on the edge of the text in the subsequent operations.

In another optional implementation manner, after assigning pixel values that meet the set conditions in the blurred image to corresponding positions in the adjusted image to obtain a text-enhanced image, the method further includes: matching out a text-enhanced image in the text-enhanced image. The pixel corresponding to the pixel with the non-minimum pixel value in the target marker map, and the pixel value of the matched pixel is modified to the maximum pixel value to remove the padded target pixel value. Specifically, the pixel value of the pixel in the text-enhanced image corresponding to the pixel with the non-zero pixel value in the target marker image is modified to a pixel value of 255 to erase the previously filled target pixel value. In another optional implementation, it is also possible to pay attention to a pixel with a pixel value of 1 in the target marker image, and modify the pixel value of the pixel at the position corresponding to the pixel in the text-enhanced image to a pixel value of 255 to remove the text. Enhances the bottom noise in the image.

The technical scheme of the embodiment of the present invention obtains the target image by performing edge point enhancement processing on the obtained scanned grayscale image with uniform brightness, then adjusts the grayscale distribution interval of the target image, and performs edge marking and edge enhancement processing on the adjusted image. , obtain text-enhanced images, solve the problem that the algorithm preprocessing process used in the prior art is too complicated, and cause great troubles to equipment with limited resources and high real-time requirements, and realizes simplifying algorithm complexity and improving algorithm operation. While ensuring the accuracy of the printed text, the text image is enhanced.

On the basis of the above embodiment, after performing edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image, the method further includes: using an error diffusion method to binarize the text-enhanced image to obtain a half- Toned image to provide dot signal for printing equipment. Since the printing equipment needs two signals of 0 and 1 to determine whether there is an ink dot at a certain position, the 8-bit grayscale image must be converted into a 2-bit binary image before it can be transferred to the printing equipment, that is, the printing equipment is binarized. The process must convert the continuous-tone image of the grayscale image into a half-tone image, that is, use the density change of the distribution of black dots to simulate the shade change of the image. In the embodiment of the present invention, the error diffusion method is used to transform the text-enhanced image, and the "Javis filter" which has a large diffusion range and is easy to improve edge contrast is used in the error diffusion operation. Among them, the working form of the filter can be as shown in Table 3, and "*" is the pixel to be processed in the text-enhanced image. Specifically, when the pixel value at * is converted to 0 or 255, the resulting error will be accumulated to the pixels at the corresponding surrounding positions according to the weights in Table 3. Exemplarily, the median value of 127 is used as the threshold. If the pixel value 60 is binarized to 0, an error of -60 will be generated. To balance the value, it should be +60 at other pixel positions, that is, the surrounding pixels are scanned by the filter. For example, the weight of the pixel value of the right pixel is 7/ 48, then the pixel value of the pixel on the right should accumulate a value of +60*(7/48), the position of other pixels in the filter changes in the same way, each pixel is a new pixel after the error of the previous pixel is diffused Binarization is performed on the basis of the value, and new errors are diffused to subsequent pixels to achieve error diffusion. FIG. 3j is a schematic diagram showing a result of a binarization process provided by an embodiment of the present invention, wherein the left image is a continuous tone 8-bit grayscale image, and the right image is a halftone 1-bit image. It can be seen from Fig. 3j that the generated halftone image dots are clearer, and can provide dot signals for printing equipment.

Table 3 The working form of the filter

FIG. 4a is a schematic diagram of a flow of a preferred text enhancement processing method provided by an embodiment of the present invention. Specifically, first, a scanned grayscale image with balanced brightness is input. After that, input the scanned grayscale image into the image enhancement processing module to complete the first edge enhancement processing (ie the first enhancement processing module), the light and dark contrast adjustment (ie the grayscale distribution interval adjustment module) and the second edge enhancement processing (ie the second enhancement processing module). Enhancement processing module) to obtain a text-enhanced image. Exemplarily, first, the edge points of the scanned grayscale image are enhanced to obtain a target image with hardened text edges; then, the contrast of light and dark is adjusted to obtain an adjusted image; further, Prepare a backup image of 0 initial pixel value with the same size as the adjusted image, and determine the binarized background threshold hW and background fill value hB for better edge hardening effect, where hW is 230 and hB is 220. The backup image marks the pixel points whose pixel value exceeds hW in the adjusted image, and at the same time replaces the pixel value of the pixel point whose pixel value in the adjusted image is higher than hW with hB to obtain a text-enhanced image. Finally, the text-enhanced image is halftoned, and the binarized image is output to the printing device. Figure 4b is a schematic diagram of the result of a halftone image provided by an embodiment of the present invention, wherein the upper figure is a processing result obtained by directly binarizing the scanned grayscale image, and the lower figure is an embodiment of the present invention after the text The processing result obtained by binarization after enhancement processing. It can be seen from FIG. 4b that the binarized image obtained in the embodiment of the present invention can enhance the text display effect of the printed image under the condition that the influence on the text image is extremely small.

FIG. 5 is a schematic structural diagram of a text enhancement processing apparatus according to an embodiment of the present invention, and the apparatus can execute the text enhancement processing methods involved in the above embodiments. The device can be implemented in software and/or hardware. As shown in FIG. 5 , the text enhancement processing device specifically includes: a data acquisition module 510, a first enhancement processing module 520, a gray distribution interval adjustment module 530, a second Enhanced processing module 540.

Wherein, the data acquisition module 510 is used to acquire a scanned grayscale image with uniform brightness;

The first enhancement processing module 520 is configured to perform enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges;

The grayscale distribution interval adjustment module 530 is used to adjust the grayscale distribution interval of the target image to obtain an adjusted image;

The second enhancement processing module 540 is configured to perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image.

The technical scheme of the embodiment of the present invention obtains the target image by performing edge point enhancement processing on the obtained scanned grayscale image with uniform brightness, then adjusts the grayscale distribution interval of the target image, and performs edge marking and edge enhancement processing on the adjusted image. , obtain text-enhanced images, solve the problem that the algorithm preprocessing process used in the prior art is too complicated, and cause great troubles to equipment with limited resources and high real-time requirements, and realizes simplifying algorithm complexity and improving algorithm operation. While ensuring the accuracy of the printed text, the text image is enhanced.

Optionally, the first enhancement processing module 520 may include a pixel point acquisition unit and a target image acquisition unit;

Wherein, the pixel point acquisition unit can be used to analyze each pixel in the scanned grayscale image by using the surrounding pixel pattern map to obtain the target edge point and reference point of the text;

The target image acquisition unit can be used to determine the edge deepening pixel value based on the pixel value of the reference point and the pixel value of the target edge point, and utilize the edge deepening pixel value to deepen the target edge point in the scanned grayscale image, Get the target image with hardened text edges.

Optionally, the second enhancement processing module 540 may include a label map construction unit, a quantity calculation unit, a preprocessing label map acquisition unit, a target label map acquisition unit, and a text-enhanced image acquisition unit;

Among them, the label map construction unit is used to construct a label map whose initial value of each pixel value is the minimum pixel value;

A quantity calculation unit, used to obtain the pixel value of the target pixel whose pixel value in the adjusted image is greater than or equal to the marked background value, and calculates that the pixel value in the set area centered on the target pixel is lower than the marked entity value The number of pixels and the number of pixels whose pixel value is higher than the marked background value are taken as the first number and the second number, respectively;

A preprocessing marker map obtaining unit, configured to mark the pixel value of the corresponding position of the target pixel in the marker map if the first number is less than or equal to the first number threshold or the second number is less than or equal to the second number threshold is the first target pixel value, otherwise, it is marked as the pixel value of the target pixel point to obtain a preprocessing mark map; wherein, the first quantity threshold is less than the second quantity threshold; the first target pixel value is greater than the minimum pixel value;

A target marker map acquisition unit, configured to retrieve a preset area in the preprocessed marker map centered on pixels whose pixel values are greater than the marker background value, and set the pixel value in the preset area equal to the minimum pixel value The pixel value of the pixel point of the value is marked as the second target pixel value, and a target mark map is obtained; wherein, the second target pixel value is greater than the first target pixel value;

The text-enhanced image acquisition unit is used for backing up the adjusted image to obtain an adjusted image copy, and filling and blurring the adjusted image copy according to the target marker map to obtain a blurred image, and use the blurred image to obtain a copy of the adjusted image. The image performs edge enhancement processing on the adjusted image to obtain a text-enhanced image.

Optionally, the text-enhanced image acquisition unit may be specifically configured to replace the pixel value of the pixel corresponding to the pixel whose pixel value in the target marker map exceeds the marker background value in the adjusted image copy with the target pixel value, Obtaining a target fill map; scaling and transforming the target fill map using a linear interpolation scaling method to obtain a blurred image; assigning pixel values that meet the set conditions in the blurred image to corresponding positions in the adjusted image , to get a text-enhanced image.

Optionally, the target image acquisition unit can be specifically used to obtain the minimum edge deepening pixel value calculated in each surrounding pixel pattern map, and compare the minimum edge deepening pixel value with the pixel value of the target edge point; If the minimum edge deepening pixel value is smaller than the pixel value of the target edge point, the pixel value of the target edge point is assigned as the minimum edge deepening pixel value to obtain a target image with hardened text edges.

Optionally, the text enhancement processing device may further include a binarization processing module for performing edge marking and edge enhancement processing on the adjusted image to obtain the text enhanced image, and then using the error diffusion method to perform the text enhanced image processing. The binarization process obtains a halftone image to provide a dot signal for printing equipment.

Optionally, the text enhancement processing device may also include a target pixel value removal module for assigning pixel values that meet the set conditions in the blurred image to the corresponding position of the adjusted image, and after obtaining the text enhanced image, In the text-enhanced image, the pixel corresponding to the pixel with the non-minimum pixel value in the target marker map is matched, and the pixel value of the matched pixel is modified to the maximum pixel value to remove the filled target pixel value. The text enhancement processing apparatus provided by the embodiment of the present invention can execute the text enhancement processing method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in FIG. 6 , the electronic device includes a processor 610, a memory 620, an input device 630, and an output device 640; the number of processors 610 in the electronic device There may be one or more, and a processor 610 is taken as an example in FIG. 6 ; the processor 610, memory 620, input device 630 and output device 640 in the electronic device can be connected by a bus or in other ways. Connect as an example.

As a computer-readable storage medium, the memory 620 can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the text enhancement processing method in the embodiment of the present invention (for example, the The data acquisition module 510, the first enhancement processing module 520, the gray distribution interval adjustment module 530, and the second enhancement processing module 540). The processor 610 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 620 , that is, to implement the above-mentioned text enhancement processing method.

The memory 620 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Additionally, memory 620 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory 620 may further include memory located remotely from processor 610, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 630 may be used to receive input numerical or character information, and generate key signal input related to user settings and function control of the electronic device. The output device 640 may include a display device such as a display screen.

An embodiment of the present invention also provides a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute a text enhancement processing method when executed by a computer processor, and the method includes:

Obtain a scanned grayscale image with uniform brightness;

Performing enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges;

Adjusting the gray distribution interval of the target image to obtain an adjusted image;

Perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image.

Of course, a storage medium containing computer-executable instructions provided by an embodiment of the present invention is not limited to the above-mentioned method operations, and can also execute the text enhancement processing method provided by any embodiment of the present invention. related operations.

From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be realized by software and necessary general-purpose hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment . Based on such understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in a computer-readable storage medium, such as a floppy disk of a computer , read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), flash memory (FLASH), hard disk or CD, etc., including several instructions to make a computer device (which can be a personal computer, A server, or a network device, etc.) executes the methods described in the various embodiments of the present invention.

It is worth noting that, in the above embodiments of the text enhancement processing device, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, The specific names of the functional units are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present invention.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention. The scope is determined by the scope of the appended claims.

Claims (10)

1. a text enhancement processing method, is characterized in that, comprises: Obtain a scanned grayscale image with uniform brightness; performing enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges; Adjusting the grayscale distribution interval of the target image to obtain an adjusted image; Perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image. 2. The method according to claim 1, characterized in that, performing enhancement processing on the edge points of the scanned grayscale image, and obtaining the target image of character edge hardening comprises: Use the surrounding pixel pattern map to analyze each pixel in the scanned grayscale image to obtain the target edge point and reference point of the text; Based on the pixel value of the reference point and the pixel value of the target edge point, the edge deepening pixel value is determined, and the edge deepening pixel value is used to deepen the target edge point in the scanned grayscale image to obtain a target image with hardened text edges. 3. The method according to claim 1, wherein, performing edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image comprising: Construct a marker map whose initial value of each pixel value is the minimum pixel value; Obtain the pixel value of the target pixel whose pixel value is greater than or equal to the marked background value in the adjusted image, and calculate the number of pixels whose pixel value is lower than the marked entity value in the set area centered on the target pixel point and The number of pixel points whose pixel value is higher than the marked background value are used as the first number and the second number respectively; If the first number is less than or equal to the first number threshold or the second number is less than or equal to the second number threshold, the pixel value at the corresponding position of the target pixel in the marked map is marked as the first target pixel value, otherwise, Marking the pixel value of the target pixel point to obtain a preprocessing marked map; wherein, the first number threshold is less than the second number threshold; the first target pixel value is greater than the minimum pixel value; Retrieve the preset area centered on the pixel whose pixel value is greater than the marked background value in the preprocessing marking map, and mark the pixel value of the pixel whose pixel value is equal to the minimum pixel value in the preset area. is the second target pixel value to obtain a target marker map; wherein, the second target pixel value is greater than the first target pixel value; The adjusted image is backed up to obtain an adjusted image copy, and the adjusted image copy is filled and blurred according to the target marker map to obtain a blurred image, and the adjusted image is edged with the blurred image. Enhance the processing to get text-enhanced images. 4 . The method according to claim 3 , wherein the adjustment image copy is filled and blurred according to the target marker map to obtain a blurred image, and the blurred image is used to align the adjustment image. 5 . Adjust the image to perform edge enhancement processing, and obtain a text-enhanced image including: Replacing the pixel value of the pixel corresponding to the pixel whose pixel value in the target marking map exceeds the marking background value in the adjustment image copy is the target pixel value to obtain the target filling map; Use the linear interpolation scaling method to scale and transform the target fill image to obtain a blurred image; The pixel values in the blurred image that meet the set conditions are assigned to corresponding positions in the adjusted image to obtain a text-enhanced image. 5. The method according to claim 2, wherein the target edge point in the scanned grayscale image is deepened by using the edge deepening target value to obtain the target image of character edge hardening comprising: Obtain the minimum edge deepening pixel value calculated in each surrounding pixel pattern map, and compare the minimum edge deepening pixel value with the pixel value of the target edge point; If the minimum edge deepening pixel value is smaller than the pixel value of the target edge point, the pixel value of the target edge point is assigned as the minimum edge deepening pixel value to obtain a target image with hardened text edges. 6. The method according to claim 1, wherein, after performing edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image, the method further comprises: Using the error diffusion method, the text-enhanced image is binarized to obtain a halftone image, which provides a dot signal for printing equipment. 7. The method according to claim 4, characterized in that, after assigning the pixel value that meets the setting condition in the blurred image to the corresponding position of the adjustment image, after obtaining the text-enhanced image, it also comprises: In the text-enhanced image, the pixels corresponding to the pixels with non-minimum pixel values in the target marker map are matched, and the pixel values of the matched pixels are modified to the maximum pixel value to remove the filled target pixel value. 8. A character enhancement processing device, comprising: The data acquisition module is used to acquire the scanned grayscale image with uniform brightness; a first enhancement processing module, configured to perform enhancement processing on the edge points of the scanned grayscale image to obtain a target image with hardened text edges; a grayscale distribution interval adjustment module, which is used to adjust the grayscale distribution interval of the target image to obtain an adjusted image; The second enhancement processing module is configured to perform edge marking and edge enhancement processing on the adjusted image to obtain a text-enhanced image. 9. An electronic device, characterized in that the electronic device comprises: one or more processors; storage means for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the text enhancement processing method according to any one of claims 1-7. 10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the text enhancement processing method according to any one of claims 1-7 is implemented.

Images