A printing control method, system and device based on image content semantic segmentation
Patent Information
- Application Number
- CN202610406853.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-31
- Publication Date
- 2026-08-18
AI Technical Summary
这种一刀切的控制方式导致了大量的能源浪费，并可能因纸张过度受热而产生卷曲，缩短定影器寿命
Smart Images
Figure CN122593720A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of printing control technology, and in particular to a printing control method, system and device based on image content semantic segmentation. Background Technology
[0002] Laser printers and other imaging devices typically employ a global pixel-sampling strategy to reduce toner consumption in ink-saving or economy modes. For example, they might skip printing every few pixels to reduce overall toner coverage. However, this coarse-grained approach results in all content on the printed page, including text and images, being sparsified to the same degree. While the quality degradation in image areas is still acceptable, text strokes become broken and incomplete, leading to blurred edges and reduced clarity, severely impacting the readability of the printed document.
[0003] On the other hand, the printer's fusing unit (fusing unit) is responsible for melting and fixing the toner onto the paper, and its operating temperature directly affects print quality and energy consumption. In existing technology, the fusing unit is typically controlled to operate at a constant high temperature (e.g., around 180°C), regardless of whether the current print job has high page coverage (e.g., printing a completely black image) or low coverage (e.g., printing only a period), its heating power remains essentially constant. This one-size-fits-all control method leads to significant energy waste and can potentially cause paper curling due to overheating, shortening the fusing unit's lifespan. Summary of the Invention
[0004] To address the aforementioned issues, this application provides a printing control method, system, and device based on image content semantic segmentation; achieving a clear, ink-saving mode and optimizing energy consumption management during the printing process.
[0005] The first technical solution adopted in this application is: providing a printing control system based on image content semantic segmentation, including: The semantic segmentation module is configured to identify the content type of the original printed page data in order to separate text regions and non-text regions. A differentiated rasterization module, communicatively connected to the semantic segmentation module, is configured to apply a first rasterization processing strategy to the text region to generate first rasterized data, and apply a second rasterization processing strategy to the non-text region to generate second rasterized data; wherein, the first rasterization processing strategy has higher text edge clarity in the rasterization result compared to the second rasterization processing strategy. The coverage assessment module is communicatively connected to the differentiated rasterization module and is configured to determine the consumable coverage of the current printing task based on the first rasterization data and the second rasterization data. The dynamic thermal management module is communicatively connected to the coverage assessment module and is configured to adjust the target operating temperature of the fixing unit in real time based on the coverage of the consumables.
[0006] In an optional embodiment, the semantic segmentation module is configured as follows: Based on the gradient features and pixel value distribution features of pixel blocks, the content type of the original printed page data is identified; Regions where gradient changes meet preset conditions and pixel values are binary are identified as text regions; regions where gradient changes do not meet the preset conditions or pixel values are multi-valued are identified as non-text regions.
[0007] In an optional embodiment, the first rasterization strategy includes: applying an edge-enhanced threshold matrix; The edge-enhanced threshold matrix is configured such that the threshold of its internal regions is higher than the threshold of its edge regions, so that during rasterization, edge pixels of text strokes are preferentially preserved, while pixels in the internal regions of the strokes are selectively omitted.
[0008] In an optional embodiment, the edge-enhanced threshold matrix is configured as follows: The threshold for its central region is set to trigger printing only when the grayscale value of the original pixel is higher than the first threshold; The threshold for its outer region is set to trigger printing when the grayscale value of the original pixel is higher than the second threshold; Wherein, the first threshold is higher than the second threshold.
[0009] In an optional embodiment, the second rasterization processing strategy includes: applying a brightness-adaptive error diffusion algorithm; The brightness-adaptive error propagation algorithm is configured to dynamically adjust the weighting coefficients of error propagation based on the brightness characteristics of the current processing area.
[0010] In an optional embodiment, the brightness-adaptive error propagation algorithm is further configured as follows: When the brightness value of the current processing area is detected to be lower than the preset brightness threshold, the attenuation coefficient in the error diffusion process is increased to actively reduce the density of printed dots in the low brightness area.
[0011] In an optional embodiment, the dynamic thermal management module is further configured to: Based on the preset mapping relationship between consumable coverage and temperature, determine the optimized target temperature that matches the current consumable coverage. The heating element of the fixing unit is controlled to adjust the fixing temperature to the optimized target temperature.
[0012] The second technical solution adopted in this application is: providing a printing control method based on image content semantic segmentation, including the following steps: Identify the content type of the original printed page data to separate text areas from non-text areas; A first rasterization strategy is applied to the text region to generate first rasterized data, and a second rasterization strategy is applied to the non-text region to generate second rasterized data; wherein, the first rasterization strategy has higher text edge clarity in the rasterization result compared to the second rasterization strategy. Based on the first rasterized data and the second rasterized data, determine the consumable coverage of the current printing task; The target operating temperature of the fixing unit is adjusted in real time based on the consumable coverage.
[0013] The third technical solution adopted in this application is: providing a printing device, including the image content semantic segmentation-based printing control system of any of the foregoing.
[0014] The fourth technical solution adopted in this application is: providing a computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the aforementioned printing control method based on image content semantic segmentation.
[0015] Due to the adoption of the above technical solution, this application has at least one of the following beneficial effects compared with the prior art: 1. By semantically segmenting the page content and using different rasterization strategies for text and non-text areas, especially applying edge-enhanced threshold matrix and other technologies to text areas, we have achieved overall ink saving while prioritizing the clarity and sharpness of text edges. This solves the problem of broken and blurry text strokes in traditional ink-saving modes and significantly improves the user experience.
[0016] 2. The coverage assessment module accurately calculates the toner load of the current page, and the dynamic thermal management module adjusts the fixing target temperature in real time. When printing pages with low coverage, the operating temperature is automatically reduced to avoid ineffective heating and improve energy efficiency.
[0017] 3. The dynamic thermal management module precisely controls the temperature, reducing the phenomenon of paper becoming brittle and curling due to excessive water loss caused by excessive temperature, thus reducing the risk of paper jams. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 A schematic diagram of the framework of a printing control system based on image content semantic segmentation provided in an embodiment of this application; Figure 2 A schematic flowchart of a printing control method based on image content semantic segmentation provided in an embodiment of this application; Figure 3 A schematic diagram of the frame of a printing device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application. Detailed Implementation
[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are only for explaining this application and not for limiting it. Furthermore, it should be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all structures. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0020] The terms "first," "second," etc., used in this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0022] Existing printing control technologies face a technical contradiction in ink-saving mode: while traditional global spot-dip ink-saving strategies can reduce toner consumption, they uniformly sparse out page content indiscriminately, resulting in broken strokes and blurred edges in text areas, severely affecting the readability of printed documents. At the same time, the fixing units of existing printing equipment usually operate in a constant high-temperature mode. Regardless of the page coverage of the current printing task (for example, the toner requirements of plain text pages and full-page image pages are very different), its heating power is maintained at the same level. This energy management method, which lacks a dynamic adjustment mechanism, causes significant energy waste and paper curling and deformation due to excessive heating.
[0023] In view of this, the printing control system of this application identifies the page content type through a semantic segmentation module and applies differentiated rasterization strategies to text and non-text areas to save ink while ensuring the clarity of text edges; at the same time, it dynamically adjusts the working temperature of the fixing unit according to the actual consumable coverage to achieve on-demand heating, thereby improving print quality while achieving energy saving and emission reduction; the printing control system includes: The semantic segmentation module is configured to identify the content type of the original printed page data in order to separate text regions and non-text regions.
[0024] The differential rasterization module communicates with the semantic segmentation module and is configured to apply a first rasterization processing strategy to text regions to generate first rasterized data, and apply a second rasterization processing strategy to non-text regions to generate second rasterized data; wherein, the first rasterization processing strategy has higher text edge clarity in the rasterization result compared with the second rasterization processing strategy.
[0025] The coverage assessment module communicates with the differential rasterization module and is configured to determine the consumable coverage of the current printing task based on the first rasterization data and the second rasterization data.
[0026] The dynamic thermal management module communicates with the coverage assessment module and is configured to adjust the target operating temperature of the fixing unit in real time based on the consumable coverage.
[0027] like Figure 1 As shown, Figure 1 This is a schematic diagram of the framework of a printing control system based on image content semantic segmentation according to an embodiment of this application. The printing control system 100 includes a semantic segmentation module 110, a differential rasterization module 120, a coverage evaluation module 130, and a dynamic thermal management module 140.
[0028] After the print job is initiated, the raw print page data is first input to the semantic segmentation module 110. The raw print page data can be bitmap data generated after interpreting page description language data, or it can be other formats of image data to be printed. The semantic segmentation module 110 is used to identify the content type of the raw print page data. By analyzing the image features of each area on the page, it divides it into text areas and non-text areas. Text areas typically include text, lines, symbols, and other content that requires high-resolution display, while non-text areas include photographs, gradient graphics, backgrounds, and other content with relatively lower resolution requirements.
[0029] The differential rasterization module 120 is communicatively connected to the semantic segmentation module 110 and is used to receive the segmented region data. The differential rasterization module 120 has at least two pre-set rasterization processing strategies. For received text regions, the differential rasterization module 120 applies a first rasterization processing strategy to generate first rasterized data; for received non-text regions, it applies a second rasterization processing strategy to generate second rasterized data. The first rasterization processing strategy is designed to have higher text edge sharpness in the rasterization result than the second rasterization processing strategy, thereby prioritizing text readability while achieving overall ink saving.
[0030] The coverage assessment module 130 is communicatively connected to the differential rasterization module 120. It receives first and second rasterization data and, based on this data, calculates the actual number of pixels to be printed in the current print job, thereby determining the consumable coverage (e.g., toner coverage). Consumable coverage refers to the ratio of the area occupied by printed dots in the printed image to the total area of the page; its value directly reflects the amount of toner required for this print job and the heat required for fixing.
[0031] The dynamic thermal management module 140 is communicatively connected to the coverage assessment module 130. It receives the filament coverage rate and adjusts the target operating temperature of the fusing unit in real time based on this rate. The fusing unit melts and fixes the toner onto the printing medium, and its operating temperature directly affects print quality and energy consumption. The dynamic thermal management module 140 dynamically adjusts the target temperature based on the filament coverage rate; for example, it lowers the temperature to save energy at low coverage and maintains or increases the temperature at high coverage to ensure effective fusing, thus achieving on-demand heating.
[0032] Considering the computing power limitations of the main control chip in the printing device, the semantic segmentation module 110 adopts a lightweight image feature recognition method rather than a complex deep learning model; the semantic segmentation module 110 is configured as follows: Based on the gradient features and pixel value distribution features of pixel blocks, the content type of the original printed page data is identified. Among them, regions where the gradient change meets the preset conditions and the pixel values are binary are identified as text regions; regions where the gradient change does not meet the preset conditions or the pixel values are multi-valued are identified as non-text regions.
[0033] In one embodiment, the semantic segmentation module 110 divides the original printed page data into multiple pixel blocks, for example, each pixel block is 8×8 pixels or 16×16 pixels in size. For each pixel block, the semantic segmentation module 110 extracts its gradient features and pixel value distribution features. The gradient features are obtained by calculating the gray-level change rate between adjacent pixels within the pixel block, and are used to characterize the severity of image edges. The pixel value distribution features are obtained by statistically analyzing the distribution of gray-level values within the pixel block, and are used to determine whether the image is a binary image or a multi-valued image.
[0034] The semantic segmentation module 110 makes the following judgment: If the gradient change of a pixel block meets the preset gradient threshold (e.g., the average gradient is higher than a certain threshold) and its pixel value distribution shows a typical binary distribution (e.g., there are only two obvious peaks in the histogram), then the pixel block is identified as a text region; if the gradient change of a pixel block does not meet the preset gradient threshold, or its pixel value distribution shows a multi-value distribution (e.g., the histogram distribution is scattered), then the pixel block is identified as a non-text region.
[0035] In this way, the semantic segmentation module 110 can quickly complete the semantic segmentation of page content with low computational overhead, providing a foundation for subsequent differentiated rasterization processing.
[0036] The first rasterization strategy includes: applying an edge-enhanced threshold matrix; The edge-enhanced threshold matrix is configured such that the threshold for its internal regions is higher than the threshold for its edge regions, so that during rasterization, edge pixels of text strokes are preferentially preserved, while pixels in the internal regions of the strokes are selectively omitted.
[0037] The edge-enhanced threshold matrix is configured as follows: The threshold for its central region is set to trigger printing only when the grayscale value of the original pixel is higher than the first threshold; The threshold for its outer region is set to trigger printing when the grayscale value of the original pixel is higher than the second threshold; The first threshold is higher than the second threshold.
[0038] This embodiment details the specific implementation of the first rasterization processing strategy. The first rasterization processing strategy employs an edge-enhanced threshold matrix, which is a predefined two-dimensional array, such as an 8×8 matrix.
[0039] The numerical distribution of the edge-enhanced threshold matrix is non-uniform: the threshold of its inner region (e.g., the central 4×4 region) is set to a higher first threshold, for example, 240-255 in the grayscale range of 0-255; the threshold of its outer region (e.g., other regions besides the central region) is set to a lower second threshold, for example, 100-128. The first threshold is higher than the second threshold.
[0040] When rasterizing text regions, for each original pixel, its grayscale value is compared with the threshold at the corresponding position in the edge-enhanced thresholding matrix. When a pixel is located at the edge of a text stroke, it is mapped to the outer region of the matrix. Due to the lower threshold at the outer edge, the grayscale value of this pixel is more likely to exceed the second threshold, thus triggering printing and prioritizing the preservation of the text stroke edge. When a pixel is located inside a text stroke, it is mapped to the inner region of the matrix. Due to the higher threshold at the inner edge, the grayscale value of this pixel is less likely to exceed the first threshold, thus being selectively omitted, i.e., not printed. In the resulting printed dot matrix, the text strokes exhibit a microstructure with sharp edges and sparse interior, saving toner while ensuring visual clarity.
[0041] The second rasterization strategy includes: applying a brightness-adaptive error diffusion algorithm; The brightness-adaptive error propagation algorithm is configured to dynamically adjust the weighting coefficients of error propagation based on the brightness characteristics of the current processing area.
[0042] The brightness-adaptive error propagation algorithm is further configured as follows: When the brightness value of the current processing area is detected to be lower than the preset brightness threshold, the attenuation coefficient in the error diffusion process is increased to actively reduce the density of printed dots in the low brightness area.
[0043] This embodiment details the implementation of the second rasterization processing strategy. The second rasterization processing strategy employs a brightness-adaptive error diffusion algorithm, which introduces a brightness-adaptive mechanism based on the traditional error diffusion algorithm.
[0044] When rasterizing non-text areas, the differential rasterization module 120 divides the image into multiple pixel blocks and calculates the average brightness value L of each pixel block. A preset brightness threshold T is used, for example, T=50 (assuming the brightness range is 0-255, where 0 represents pure black and 255 represents pure white). When the average brightness value L of the currently processed pixel block is detected to be greater than or equal to the brightness threshold T, the algorithm uses a standard or near-standard error diffusion coefficient for error diffusion processing to maintain the image's sense of depth and detail. When the average brightness value L is detected to be less than the brightness threshold T, i.e., the current area is a dark area, the algorithm dynamically increases the attenuation coefficient during the error diffusion process. The increase in the attenuation coefficient means that the quantization error is weakened when it propagates to surrounding pixels, resulting in a proactive reduction in the print dot density in the dark area, thereby reducing toner consumption. Since the human eye has a low ability to distinguish details in dark areas, this processing has little impact on the overall visual appearance of the image; the brightness-adaptive error diffusion algorithm can achieve ink-saving printing in non-text areas while ensuring the visual effect of the image.
[0045] The dynamic thermal management module is further configured as follows: Based on the preset mapping relationship between consumable coverage and temperature, determine the optimized target temperature that matches the current consumable coverage. The heating element of the fixing unit is controlled to adjust the fixing temperature to the optimized target temperature.
[0046] This embodiment details the specific control method of the dynamic thermal management module 140. The dynamic thermal management module 140 internally stores the mapping relationship between consumable coverage and target temperature, which can be implemented through a lookup table or function.
[0047] Lookup table method: The optimal fixing temperature corresponding to different consumable coverage rates (e.g., 0%, 2%, 5%, 10%, 20%, 40%) is pre-determined experimentally and stored in a lookup table. Upon receiving the current consumable coverage rate, the dynamic thermal management module 140 determines the corresponding optimized target temperature through table lookup and interpolation.
[0048] Functional approach: The relationship between consumable coverage and target temperature is fitted into a function to adapt to the physical characteristics of different models and different toners; the function can be a linear function or a non-linear function, without any restrictions.
[0049] After determining the optimized target temperature, the dynamic thermal management module 140 adjusts the power of the heating element of the fixing unit (e.g., controlling the duty cycle of the heating lamp) through a PID controller or other control methods to adjust the actual temperature of the fixing unit to the optimized target temperature. For example, when the consumable coverage is 2%, the target temperature can be lowered from the usual 180°C to 165°C; when the consumable coverage is 40%, the target temperature can be maintained at 180°C or appropriately increased to ensure that the toner is fully melted.
[0050] This application also provides a printing control method based on image content semantic segmentation, applicable to the printing control system of any of the above embodiments, such as... Figure 2 As shown, Figure 2 A flowchart illustrating a printing control method based on image content semantic segmentation provided in an embodiment of this application includes the following steps: Identify the content type of the original printed page data to separate text areas from non-text areas; A first rasterization strategy is applied to the text region to generate first rasterized data, and a second rasterization strategy is applied to the non-text region to generate second rasterized data; wherein, the first rasterization strategy has higher text edge clarity in the rasterized result compared with the second rasterization strategy. Based on the first raster data and the second raster data, determine the consumable coverage of the current printing task; The target operating temperature of the fixing unit is adjusted in real time based on the consumable coverage.
[0051] This application also provides a printing device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the framework of a printing device provided in one embodiment of the present application, including a printing control system based on image content semantic segmentation as described in any of the above embodiments.
[0052] The methods described in the above embodiments can be implemented as computer programs; therefore, this application proposes a computer-readable storage medium. Please refer to [link to relevant documentation]. Figure 4 , Figure 4 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application. The computer-readable storage medium stores program data that can be executed by a processor to implement the steps of any embodiment of the above-described printing control method based on image content semantic segmentation.
[0053] In this embodiment, the computer-readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or other media capable of storing program data. Alternatively, it can be a server storing the program data, which can send the stored program data to other devices for execution, or it can execute the stored program data itself. In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0055] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0056] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A print control system based on image content semantic segmentation, characterized by, include: The semantic segmentation module is configured to identify the content type of the original printed page data in order to separate text regions and non-text regions. A differentiated rasterization module, communicatively connected to the semantic segmentation module, is configured to apply a first rasterization processing strategy to the text region to generate first rasterized data, and apply a second rasterization processing strategy to the non-text region to generate second rasterized data; wherein, the first rasterization processing strategy has higher text edge clarity in the rasterization result compared to the second rasterization processing strategy. The coverage assessment module is communicatively connected to the differentiated rasterization module and is configured to determine the consumable coverage of the current printing task based on the first rasterization data and the second rasterization data. The dynamic thermal management module is communicatively connected to the coverage assessment module and is configured to adjust the target operating temperature of the fixing unit in real time based on the coverage of the consumables.
2. The printing control system according to claim 1, characterized in that, The semantic segmentation module is configured as follows: Based on the gradient features and pixel value distribution features of pixel blocks, the content type of the original printed page data is identified; Regions where gradient changes meet preset conditions and pixel values are binary are identified as text regions; regions where gradient changes do not meet the preset conditions or pixel values are multi-valued are identified as non-text regions.
3. The printing control system according to claim 1 or 2, characterized in that, The first rasterization strategy includes: applying an edge-enhanced threshold matrix; The edge-enhanced threshold matrix is configured such that the threshold of its internal regions is higher than the threshold of its edge regions, so that during rasterization, edge pixels of text strokes are preferentially preserved, while pixels in the internal regions of the strokes are selectively omitted.
4. The printing control system according to claim 3, characterized in that, The edge-enhanced threshold matrix is configured as follows: The threshold for its central region is set to trigger printing only when the grayscale value of the original pixel is higher than the first threshold; The threshold for its outer region is set to trigger printing when the grayscale value of the original pixel is higher than the second threshold; Wherein, the first threshold is higher than the second threshold.
5. The printing control system according to claim 1 or 2, characterized in that, The second rasterization strategy includes: applying a brightness-adaptive error diffusion algorithm; The brightness-adaptive error propagation algorithm is configured to dynamically adjust the weighting coefficients of error propagation based on the brightness characteristics of the current processing area.
6. The printing control system according to claim 5, characterized in that, The brightness-adaptive error propagation algorithm is further configured as follows: When the brightness value of the current processing area is detected to be lower than the preset brightness threshold, the attenuation coefficient in the error diffusion process is increased to actively reduce the density of printed dots in the low brightness area.
7. The printing control system according to claim 1, characterized in that, The dynamic thermal management module is further configured as follows: Based on the preset mapping relationship between consumable coverage and temperature, determine the optimized target temperature that matches the current consumable coverage. The heating element of the fixing unit is controlled to adjust the fixing temperature to the optimized target temperature.
8. A printing control method based on image content semantic segmentation, characterized in that, Includes the following steps: Identify the content type of the original printed page data to separate text areas from non-text areas; A first rasterization strategy is applied to the text region to generate first rasterized data, and a second rasterization strategy is applied to the non-text region to generate second rasterized data; wherein, the first rasterization strategy has higher text edge clarity in the rasterization result compared to the second rasterization strategy. Based on the first rasterized data and the second rasterized data, determine the consumable coverage of the current printing task; The target operating temperature of the fixing unit is adjusted in real time based on the consumable coverage.
9. A printing device, characterized in that, The printing control system includes the image content semantic segmentation based on any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the printing control method based on image content semantic segmentation as described in claim 8.