Image printing data generation method, device, system and storage medium

Abstract

The application discloses a printing data generation method, device and system of an image and a storage medium, relates to the technical field of electronic digital data processing, and comprises the following steps: acquiring an image to be printed and identifying the image type of the image to be printed; determining the rendering mode and the halftone mode matched by the image to be printed based on the image type; and analyzing the image to be printed according to the rendering mode and the halftone mode matched by the image to be printed, so as to obtain the printing data of the image to be printed. The application can realize adaptive recommendation of the printing data of an image, thereby improving the overall quality of printing output.

Description

Technical Field

[0001] This application relates to the field of printing technology, and in particular to a method, apparatus, system and storage medium for generating printing data of an image. Background Technology

[0002] Currently, printer data includes many aspects, such as the ICC (International Color Consortium) file which determines the color mapping, the color mode which affects how colors are presented, and the print resolution which determines the image sharpness. For the same image, different parameter settings will produce different printing results.

[0003] In related technologies, users need to manually adjust these print data according to their needs and experience to obtain satisfactory print results. However, for ordinary users, it is difficult to accurately find the optimal combination of print data, which may result in poor print quality. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, system, and storage medium for generating print data of images, aiming to solve the technical problem in the prior art that it is difficult to accurately find the optimal combination of print data, resulting in poor print quality.

[0005] To achieve the above objectives, this application provides a method for generating print data for an image, the method comprising:

[0006] Acquire the image to be printed and identify the image type of the image to be printed;

[0007] Based on the image type, determine the rendering mode and halftone mode that the image to be printed should match;

[0008] Based on the rendering mode and halftone mode matched by the image to be printed, the image to be printed is parsed to obtain the printing data of the image to be printed.

[0009] In one embodiment, the step of identifying the image type of the image to be printed includes:

[0010] Input the image to be printed into the image classification model;

[0011] The image to be printed is classified using the image classification model to obtain the image type of the image to be printed.

[0012] In one embodiment, the step of identifying the image type of the image to be printed includes:

[0013] Obtain the probability value of each image type corresponding to the image to be printed;

[0014] The image type with the highest probability value is selected as the image type to be printed.

[0015] In one embodiment, the step of determining the rendering mode matching the image to be printed based on the image type includes:

[0016] If the image type is associated with an associated rendering mode, then the associated rendering mode is determined as the rendering mode that matches the image to be printed.

[0017] If the image type is not associated with an associated rendering mode, then the default rendering mode is determined as the rendering mode that matches the image to be printed.

[0018] In one embodiment, the step of determining the halftone mode matching the image to be printed based on the image type includes:

[0019] If the image type is associated with an associated halftone mode, then the associated halftone mode is determined as the halftone mode that matches the image to be printed.

[0020] If the image type is not associated with an associated halftone mode, then the default halftone mode is determined as the halftone mode that matches the image to be printed.

[0021] In one embodiment, the image type includes natural, text, humanistic, abstract, and simple color types; the rendering mode includes perceptual mode, relative mode, absolute mode, and saturation mode; the halftone mode includes second-order halftone mode and third-order halftone mode. Based on the image type, determining the matching rendering mode and halftone mode for the image to be printed includes:

[0022] If the image type is natural, the rendering mode is determined to be a perceptual mode, and the halftone mode is determined to be a third-order halftone mode;

[0023] If the image type is text, the rendering mode is determined to be a perceptual mode, and the halftone mode is determined to be a second-order halftone mode;

[0024] If the image type is humanistic, the rendering mode is determined to be a relative mode, and the halftone mode is determined to be a third-order halftone mode;

[0025] If the image type is an abstract type, the rendering mode is determined to be an absolute mode, and the halftone mode is determined to be a second-order halftone mode;

[0026] If the image type is a simple color type, the rendering mode is determined to be a saturation mode, and the halftone mode is determined to be a third-order halftone mode.

[0027] In one embodiment, before the step of parsing the image to be printed based on the rendering mode and halftone mode matched by the image to be printed to obtain the printing data of the image to be printed, the method further includes:

[0028] If the image type is associated with an image processing mode, then the image to be printed is processed based on the image processing mode to obtain an updated image to be printed.

[0029] In one embodiment, the step of processing the image to be printed based on the image processing mode includes:

[0030] If the image type is either humanistic or natural, then super-resolution processing is performed on the image to be printed; and / or

[0031] If the image type is abstract or text, then edge enhancement processing is performed on the image to be printed.

[0032] In one embodiment, prior to the step of determining the rendering mode and halftone mode based on the image type of the image to be printed, the method further includes:

[0033] The image to be printed is subjected to image quality assessment to obtain the resolution and noise of the image to be printed;

[0034] The image to be printed is optimized based on the resolution and the noise.

[0035] In addition, to achieve the above objectives, this application also provides a computer device, the computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for generating print data of the image as described above.

[0036] In addition, to achieve the above objectives, this application also provides an inkjet printing device, characterized in that the step of the printing data generation method based on the image described above involves determining the printing data of the image to be printed, and then printing the image to be printed based on the printing data.

[0037] Furthermore, to achieve the above objectives, this application also provides a printing system, comprising a host computer and an inkjet printer. The host computer is used to acquire an image to be printed, generate printing data for the image to be printed based on the steps of the image printing data generation method described above, and send the printing data to the inkjet printing device. The inkjet printing device is used to print the image to be printed based on the printing data; or,

[0038] The host computer is used to acquire the image to be printed and send the image to be printed to the inkjet printing device; the inkjet printing device is used to generate printing data of the image to be printed based on the steps of the image printing data generation method described above, and then print the image to be printed based on the printing data.

[0039] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, on which a program for implementing a method for generating print data of an image is stored. The program for implementing the method for generating print data of an image is executed by a processor to implement the steps of the method for generating print data of an image as described above.

[0040] In addition, to achieve the above objectives, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the image printing data generation method described above.

[0041] This application provides a method for generating print data for images, a computer device, a printing system, and a storage medium. This application acquires an image to be printed and identifies its image type; based on the image type, it determines the matching rendering mode and halftone mode for the image to be printed; and it parses the image to be printed according to the matching rendering mode and halftone mode to obtain the print data. In other words, this application extracts the image type corresponding to the image to be printed, then maps the image type to the rendering mode and halftone mode to finally obtain the print data, thereby achieving adaptive recommendation of print data for images, optimizing image resolution, color balance, brightness, etc., and thus improving the overall quality of the printed output. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating steps S10-S30 in one embodiment of the method for generating print data for the image of this application.

[0045] Figure 2A schematic diagram illustrating the determination of rendering mode and halftone mode for image type in one embodiment of the image printing data generation method of this application;

[0046] Figure 3 This is a flowchart illustrating steps A21-A22 in one embodiment of the method for generating print data for the image of this application;

[0047] Figure 4 This is a comparative schematic diagram of natural type image processing in one embodiment of the image printing data generation method of this application;

[0048] Figure 5 This is a comparative schematic diagram of text type image processing in one embodiment of the image printing data generation method of this application;

[0049] Figure 6 This is a comparative schematic diagram of humanistic image processing in one embodiment of the image printing data generation method of this application;

[0050] Figure 7 This is a comparative schematic diagram of abstract type image processing in one embodiment of the image printing data generation method of this application;

[0051] Figure 8 This is a comparative schematic diagram of simple color type image processing in one embodiment of the image printing data generation method of this application;

[0052] Figure 9 This is a schematic diagram of the printing system for this application;

[0053] Figure 10 This is a schematic diagram of the hardware structure of the computer device involved in the embodiments of this application;

[0054] Figure 11 This is a schematic diagram of the hardware structure of the inkjet printing device in the embodiments of this application.

[0055] Explanation of icon numbers:

[0056] Printing system 1000; host computer 100; inkjet printing device 200; printing component 210; slide rail 211; print head 212; processor 230; memory 220.

[0057] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0058] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0059] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0060] Currently, users need to manually adjust these print data according to their needs and experience to obtain satisfactory print results. However, for non-professional users, it is difficult to accurately find the optimal combination of print data, resulting in poor print quality.

[0061] The main solution of this application is as follows: First, acquire the image to be printed and identify its image type. Second, based on the image type, determine the matching rendering mode and halftone mode for the image to be printed. Third, parse the image to be printed according to the matching rendering mode and halftone mode to obtain its printing data. In other words, this application extracts the image type corresponding to the image to be printed, then maps the image type to the rendering mode and halftone mode to finally obtain the printing data. This achieves adaptive recommendation of image printing data, optimizing image resolution, color balance, brightness, and other aspects, thereby improving the overall quality of the printed output.

[0062] It should be noted that the execution entity in some embodiments can be a printing system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a computer device capable of performing the above functions, or an inkjet printer, or a host computer of the inkjet printer. Some embodiments do not specifically limit this. The following uses the host computer as the execution entity to describe some embodiments and the embodiments described below.

[0063] Based on this, one embodiment of this application proposes a method for generating print data for images, please refer to... Figure 1 The method for generating print data for the image includes steps S10 to S30:

[0064] Step S10: Obtain the image to be printed and identify the image type of the image to be printed.

[0065] In some embodiments, the image to be printed is an image uploaded or selected by the user that needs to be printed. The image type refers to the main style of the image to be printed, including but not limited to natural, text, humanistic, abstract, and simple color types.

[0066] As an optional implementation, a pre-trained image classification model is used to identify the image to be printed, thus determining the image type corresponding to the image to be printed. That is, at this point, an image type is uniquely identified.

[0067] As another alternative implementation, the possible image types corresponding to the image to be printed are determined, and then the final image type is selected based on the probability value of each image type.

[0068] Step S20: Based on the image type, determine the rendering mode and halftone mode that match the image to be printed.

[0069] In some embodiments, the rendering mode is the color mode for overall image rendering, including but not limited to perceptual mode, relative mode, absolute mode, and saturation mode.

[0070] In some embodiments, a default rendering mode can be preset, which is any one of perceptual, relative, absolute, and saturated modes selected by the user. Optionally, the default rendering mode is the perceptual mode.

[0071] Furthermore, in response to the click operation of the interactive interface to change the rendering mode control, a rendering mode setting control pops up. This control displays candidate controls, which are perceptual mode, relative mode, absolute mode, and saturation mode. Based on the click operation received for any candidate control, the selected mode is used as the rendering mode for subsequent rendering.

[0072] As an optional implementation, the rendering mode and halftone mode associated with the image type are obtained. If the image type is not associated with a rendering mode, the rendering mode is determined to be the default rendering mode; and / or, if no halftone mode is associated, the halftone mode is determined to be the default halftone mode.

[0073] Step S30: Based on the rendering mode and halftone mode matched by the image to be printed, the image to be printed is parsed to obtain the printing data of the image to be printed.

[0074] In some embodiments, print data refers to configuration parameters used by an inkjet printer to print an image. Based on this print data, the image can be printed. This print data may include print content data (such as the color value of each pixel in the image, composed of the values ​​of the red, green, and blue color channels, which is converted into instructions that the printer head can understand) and print control instruction data (such as color management instructions). Print data may be PRN data.

[0075] Based on the defined rendering mode, the image to be printed is rendered. This includes adjusting parameters such as color, contrast, and brightness to optimize the image display. The rendered image is then halftone-processed using a defined halftone mode. Halftone processing involves converting a continuous-tone image (such as a photograph) into an image where tonal variations are represented by discrete dots. Its purpose is to simulate the visual effect of continuous tones using limited ink colors and print resolution. Finally, the rendered and halftone-processed image is converted into print data that the printing device can understand, including the image's pixel data, color information, and print resolution.

[0076] As an optional implementation, the host computer first receives the image to be printed, either uploaded by the user or selected by the user. Then, it invokes a pre-trained model, such as a deep learning-based image classification model, like a Convolutional Neural Network (CNN), which, after being trained on a large number of different types of images, can classify the input image and identify the image to be printed, determining the corresponding image type. For example, if the image mainly presents natural scenery, such as mountains, rivers, flowers, and plants, the model will classify it as the "Nature" image type; if the image content is mostly text layout, such as a document screenshot, it will be classified as the "Text" type. For different image types, the host computer matches the corresponding rendering mode according to preset rules. For example, when the image type is "Nature," the "Perception" rendering mode can be selected. This mode adjusts the image colors according to the characteristics of human color perception, making the printed image colors more consistent with human visual perception. Simultaneously, it can receive user-specified default rendering modes. Users can choose from "Perceptual," "Relative," "Absolute," and "Saturated" rendering modes as their preferred default mode. Subsequent image processing will prioritize the user-specified mode unless a more suitable preset mode is available for a specific feature type. The selected rendering mode is used for overall rendering processing of the image to be printed. During processing, the image resolution is optimized, for example, by using super-resolution algorithms to increase image resolution for greater clarity during printing; color balance is adjusted to ensure harmonious proportions between colors and avoid color casts; brightness is also adjusted to ensure the overall image has appropriate brightness and darkness, meeting normal visual viewing and printing requirements. After these processes, the target image is obtained. A set of rules based on the correspondence between different target image features and inkjet printing device parameters is stored. These rules were established through extensive printing experiments and combined with relevant knowledge in color science, image processing, and other related fields. For example, if the target image has high color saturation, the ink ejection volume parameter of the corresponding inkjet printer may need to be appropriately increased; if the target image has high resolution and rich details, the printhead movement speed parameter may need to be appropriately decreased to ensure that the printhead has enough time to accurately eject ink at each pixel position, achieving clear detail rendering. Based on the actual characteristics of the target image and according to the above correspondence rules, the host computer parses the specific printing data suitable for the image to be printed. This printing data includes, but is not limited to, ink ejection volume, printhead movement speed, print resolution, and consumable type selection. Different image content may be compatible with different consumables; for example, images with high color saturation are suitable for printing on consumables with good gloss. This parameter configuration information is then sent to the inkjet printer so that it can perform the printing operation according to the recommended parameters.

[0077] For example, a user selects a landscape photograph as the image to be printed through the software interface of a host computer connected to the inkjet printer. A pre-trained CNN-based image classification model can be invoked to identify the image, determining that it belongs to the "natural" image type. Then, according to preset rules, the "perceptual mode" rendering mode is selected to process the image. During processing, the host computer uses bilinear interpolation to appropriately increase the image's original resolution, for example, from 1920×1080 pixels to 3840×2160 pixels, to enhance detail during printing; it also uses color adjustment algorithms to optimize color balance, making the red of the sunset, the blue of the sea, and other colors more vibrant and harmonious; simultaneously, it adjusts the overall brightness of the image to a moderate level, avoiding excessive brightness or darkness. After these processes, the target image is generated. The printing data is then analyzed based on the features of the target image. Because the image boasts richer colors and higher resolution, the ink ejection volume parameter of the inkjet printer is increased by 20% from its default value to ensure color saturation; the printhead movement speed parameter is reduced by 30%, allowing the printhead sufficient time to precisely eject ink from each pixel, ensuring complete detail rendering at high resolution; and it is recommended to choose photo-grade paper with high gloss and good ink absorption. After the host computer sends this printing data to the inkjet printer, the printer performs the printing operation according to these parameters, ultimately producing a vibrant and detailed print of a sunset scene at the seaside.

[0078] This method of generating print data for images and its specific implementation can help ordinary users obtain satisfactory print results and improve print quality.

[0079] This application first determines at least one feature type based on the image type of the image to be printed; acquires the image to be printed and identifies the image type of the image to be printed; determines the rendering mode and halftone mode matching the image to be printed based on the image type; parses the image to be printed according to the rendering mode and halftone mode matching the image to be printed to obtain the printing data of the image to be printed, thereby realizing adaptive recommendation of image printing data, optimizing the image resolution, color balance, brightness, etc., thereby improving the overall quality of the printed output.

[0080] Based on any embodiment, in one possible embodiment of this application, step S10 includes:

[0081] Step A10: Obtain the image to be printed.

[0082] It possesses compatibility with various common image formats, supporting the reading and processing of image files such as JPEG, PNG, BMP, and TIFF. Upon receiving images of different formats to be printed, the internal image parsing module performs corresponding decoding operations based on the characteristics of the image format, converting the image data into a unified internal data structure for subsequent image type determination and other processing steps. For example, for JPEG format images, it decompresses and decodes them according to their compression encoding rules; for PNG format images, it parses the image data, transparency information, and other content contained within, converting them into a format suitable for subsequent operations, ensuring that images of any format can smoothly enter the subsequent image type determination stage.

[0083] Step A20: Identify the image type of the image to be printed.

[0084] In some embodiments, the image to be printed is input into an image classification model; then, the image classification model is used to classify the image to be printed to obtain the image type of the image to be printed. In some embodiments, various low-level features of the image to be printed are extracted by image analysis algorithms, including but not limited to color histogram features, such as statistically analyzing the distribution ratio of different colors in the image; texture features, such as analyzing the repetitive arrangement pattern of elements in the image, like the texture of a beach, the texture of clothing fabric, etc.; shape features, such as describing the outline shape of obvious objects in the image, such as a round sun, a square building, etc.; and spatial layout features, such as the relative positional relationship of objects in the image, etc. Then, these extracted feature vectors are input into a pre-trained classification model, which can be constructed based on algorithms such as support vector machine (SVM), decision tree, or convolutional neural network (CNN) in deep learning. For example, using a CNN model trained with a large number of different types of image samples, such as images, natural, humanistic, abstract, etc., it will output the corresponding image type prediction result after multi-layer convolution, pooling and other operations based on the input feature vectors. If an image's color histogram shows a high proportion of natural colors, its texture exhibits irregular yet delicate patterns common in natural scenes, its shape features include various natural object outlines, and its spatial layout conforms to the distribution patterns of natural scenes, then the model may ultimately classify the image as "natural." In other words,

[0085] Optionally, an image classification model can be invoked to directly identify the image type of the image to be printed.

[0086] Optionally, in addition to the image feature-based classification methods mentioned above, the host computer may also attempt to read the metadata information inherent in the image to be printed to assist in determining the image type. Many image files embed descriptive metadata during the generation or editing process, such as information about the shooting device, shooting time, shooting location, and image keyword tags. The host computer reads this information through the corresponding metadata parsing module. For example, if the metadata shows that the shooting device is a professional SLR camera and the shooting location is a famous tourist attraction, and the keyword tags include words such as "scenery," then combined with the classification results based on image feature extraction, it can more accurately determine that the image is likely to belong to the "natural" type. If the metadata shows that the image was generated by document editing software and the keyword tags include words such as "report" and "document," then it is more likely to determine that the image type is "text," thereby further improving the accuracy of image type determination.

[0087] The above optional implementation methods can obtain the image to be printed more comprehensively and accurately, and determine its corresponding image type, laying the foundation for subsequent operations such as determining the rendering mode and feature type.

[0088] Optionally, refer to Figure 3 Step A20 includes:

[0089] Step A21: Obtain the probability value of each image type corresponding to the image to be printed.

[0090] As an optional implementation, at least one possible image type is determined from the image to be printed, including natural, text, humanistic, abstract, and simple color images. Then, a probability value for each image type is determined.

[0091] In some embodiments, image type refers to the overall artistic expression or thematic characteristics of the image to be printed, mainly including natural (images showing natural scenery such as mountains, rivers, flowers, and celestial phenomena), text (images whose main body is text layout content, such as document screenshots, book page scans, etc.), humanistic (images reflecting human activities, cultural relics, folk customs, etc.), abstract (images composed of shapes, lines, colors, etc. in a non-representational way to express a certain mood or emotion), and simple color (images with a relatively simple and concise color composition, without complex color matching and rich details). The image type category is determined by analyzing the image content.

[0092] Image analysis algorithms can be used to scan and analyze images pixel by pixel, extracting key elements and feature information to determine the image type. For example, if an image contains a large number of continuous natural elements, such as green vegetation, blue sky, and flowing water, it can be preliminarily identified as a "natural" image. If clear text outlines are identifiable and the text occupies a large area of ​​the image, it is identified as a "text" image. Images containing elements related to human society and culture, such as ancient architecture or scenes of human activity, can be identified as "humanistic" images. When an image is composed of irregular geometric shapes, random lines, and color blocks that are difficult to directly correspond to specific real-world objects, it can be classified as an "abstract" image. An image with few colors and a relatively uniform and simple color distribution can be considered a "simple color" image. In this process, an image may simultaneously possess characteristics of multiple image types. For example, a landscape photo with a few text annotations may simultaneously possess both "natural" and "text" image types.

[0093] In some embodiments, the probability value is a numerical value calculated by an image analysis algorithm or image analysis model based on factors such as the significance and proportion of features related to each image type in the image. It is used to measure the likelihood that the image belongs to a certain image type. The value ranges from 0 to 1, and the higher the value, the greater the likelihood that the image belongs to that image type.

[0094] In one embodiment, a deep learning-based image classification model (e.g., a convolutional neural network, CNN) is used to calculate the probability values ​​for each image type. The image to be printed is input into a CNN model that has been trained on a large number of labeled image samples of different image types. The model extracts the deep features of the image through multiple convolutional and pooling operations, and then outputs the predicted probability values ​​corresponding to different image types through fully connected layers. Taking the "natural" image type as an example, the model will output a probability value indicating that the image belongs to the "natural" image type based on the feature matching degree and quantity ratio of natural scene elements in the image. For example, an output of 0.7 means that the image has a 70% probability of belonging to the "natural" image type. Similarly, corresponding probability values ​​will be output for image types such as "text," "humanistic," "abstract," and "simple colors." For example, for a wall painting photo containing some artistic graffiti (similar to abstract elements) and some text descriptions, the model may output a probability value of 0.4 for the "abstract" image type and a probability value of 0.3 for the "text" image type, etc. In some embodiments, relevant image analysis algorithms can also be used to analyze the image type. Image analysis algorithms can identify the image type based on at least one of the image's color features, texture features, and shape features.

[0095] Step A22: The image type with the highest probability value is selected as the image type of the image to be printed.

[0096] In some embodiments, when classifying based on probability values, the calculated probability values ​​of each image type are compared, and the image type with the highest probability value is selected as the target image type. For example, for the aforementioned mural photo, the analysis shows that the probability value of the "abstract" image type is 0.4, the probability value of the "text" image type is 0.3, and the probability values ​​of other image types are all less than 0.3. Therefore, the "abstract" image type is the target image type, and the image type is determined to be "abstract". If the probability values ​​are the same, additional rules such as the hierarchy of elements in the image can be used for further judgment. For example, if two image types have the same and highest probability values, but one of the image types has elements in the central area of ​​the image and occupies the main part of the image, then this image type is prioritized as the target image type. This ensures accurate determination of the image type and provides a basis for subsequent operations such as printing data recommendation.

[0097] For example, a user prepares to print a photo they took of a forest park, which contains typical natural elements such as dense forests, clear streams, and flying birds. Using an image analysis algorithm, it's easy to determine that the image belongs to the "Nature" image type. Additionally, because there's a small sign with text in the corner of the image, it also belongs to the "Text" image type. During the image type analysis, based on the fact that natural elements occupy the majority of the image and their features are obvious, the probability value for the "Nature" image type is output as 0.85, while the probability value for the "Text" image type is only 0.1 because it occupies a very small portion. Determining the target image type and the image type: Comparing the probability values, 0.85 is greater than 0.1, so the "Nature" image type is the target image type, and the image type is determined to be "Nature".

[0098] For example, consider an art poster image where the main body is composed of various irregular geometric shapes and colorful lines interwoven to form a seemingly fantastical spatial pattern, with a small tagline below. Based on the image content, it possesses the "abstract" image type due to the presence of elements constituting the abstract pattern, and also the "text" image type. After processing by a CNN model, given the dominance of abstract elements, the probability value for the "abstract" image type reaches 0.7, while the probability value for the "text" image type is 0.2. Determining the target image type and the image type: Since 0.7 is greater than 0.2, the "abstract" image type becomes the target image type; therefore, the image type is determined to be "abstract."

[0099] Optionally, in the above embodiments, determining at least one image type among the images to be printed, the image type including natural, text, humanistic, abstract, and simple color; determining the probability value of each image type; determining the target image type among the image types according to the probability value; and using the target image type as the image type can all be completed by the host computer calling a pre-trained model.

[0100] Through the above optional implementation methods and embodiments, the image type of the image to be printed can be determined more accurately, thereby providing an effective preliminary foundation for a series of printing-related operations based on the image type.

[0101] Based on any of the above embodiments, in one possible embodiment of this application, the step of determining the rendering mode matching the image to be printed based on the image type includes:

[0102] Step B1: If the image type is associated with an associated rendering mode, then the associated rendering mode is determined as the rendering mode that matches the image to be printed.

[0103] Step B2: If the image type is not associated with an associated rendering mode, then the default rendering mode is determined as the rendering mode that matches the image to be printed.

[0104] In some embodiments, after determining the image type of the image to be printed, it is determined whether the image type is associated with an associated rendering mode. If an associated rendering mode exists, the associated rendering mode is determined as the rendering mode matching the image to be printed. If the image type is not associated with an associated rendering mode, the default rendering mode is determined as the rendering mode matching the image to be printed. The default rendering mode can be any of the perceptual mode, relative mode, absolute mode, and saturation mode, or it can be a mode parsed from a rendering file imported by the user, which will not be elaborated here. The associated rendering mode can be a pre-set rendering mode associated with this image type, and different image types may correspond to different associated rendering modes.

[0105] Optionally, the step of determining the halftone mode matching the image to be printed based on the image type includes:

[0106] Step B3: If the image type is associated with an associated halftone mode, then the associated halftone mode is determined as the halftone mode that matches the image to be printed.

[0107] Step B4: If the image type is not associated with an associated halftone mode, then the default halftone mode is determined as the halftone mode that matches the image to be printed.

[0108] In some embodiments, the halftone mode includes a second-order halftone mode and a third-order halftone mode, and the associated halftone mode is the set halftone mode, which can be either a second-order or a third-order halftone mode. The default halftone mode is a halftone mode other than the set halftone mode.

[0109] For example, if the associated halftone mode is set to second-order halftone mode, the default halftone mode is third-order halftone mode. When determining the image type, if an associated halftone mode exists for the image type, the second-order halftone mode is used as the matching halftone mode for the image to be printed; if no associated halftone mode exists for the image type, the third-order halftone mode is used as the matching halftone mode for the image to be printed.

[0110] For example, if the associated halftone mode is set to third-order halftone mode, the default halftone mode is second-order halftone mode. When determining the image type, if an associated halftone mode exists for the image type, the third-order halftone mode is used as the matching halftone mode for the image to be printed; if no associated halftone mode exists for the image type, the second-order halftone mode is used as the matching halftone mode for the image to be printed.

[0111] Other combinations are not described in detail in some embodiments. For example, the halftone mode can also be a fourth-order halftone mode, a dithered halftone mode, an error diffusion halftone mode, an adaptive halftone mode, or a mixed halftone mode.

[0112] For example, refer to Figure 2 , Figure 2 This is an example of a mapping relationship. Specifically, if the image type is a natural type, the rendering mode is determined to be a perceptual mode, and the halftone mode is determined to be a third-order halftone mode; if the image type is a text type, the rendering mode is determined to be a perceptual mode, and the halftone mode is determined to be a second-order halftone mode; if the image type is a humanistic type, the rendering mode is determined to be a relative mode, and the halftone mode is determined to be a third-order halftone mode; if the image type is an abstract type, the rendering mode is determined to be an absolute mode, and the halftone mode is determined to be a second-order halftone mode; if the image type is a simple color type, the rendering mode is determined to be a saturation mode, and the halftone mode is determined to be a third-order halftone mode.

[0113] For example, by classifying image types and using the corresponding optimal rendering mode and halftone mode, the color, detail, and processing efficiency of image processing are all improved in a targeted manner, resulting in more accurate printed data.

[0114] Based on any of the above embodiments, in one possible embodiment of this application, before the step of parsing the image to be printed according to the rendering mode and halftone mode matched by the image to be printed to obtain the printing data of the image to be printed, the method further includes:

[0115] Step C1: If the image type is associated with an image processing mode, then process the image to be printed based on the image processing mode to obtain an updated image to be printed.

[0116] Image processing mode is a set of algorithms used to process images to be printed to obtain target images. It includes at least one processing algorithm for a specific feature type. These processing algorithms are designed to optimize images from different aspects such as resolution enhancement, color balance adjustment, and edge sharpening, so that they can achieve better results after printing.

[0117] Optionally, the image processing modes include super-resolution processing and edge enhancement processing.

[0118] As an optional implementation, after obtaining the image type, it is determined whether the image type has an associated image processing mode. If an image processing mode exists, the image to be printed is processed based on the image processing mode to obtain an updated image to be printed. The updated image to be printed is then parsed based on the corresponding rendering mode and halftone mode to obtain the printing data.

[0119] As another optional implementation, after obtaining the image type, it is determined whether the image type has an associated image processing mode. If no image processing mode exists, the original image to be printed is parsed based on the corresponding rendering mode and halftone mode to obtain the printing data.

[0120] Optionally, the step of processing the image to be printed based on the image processing mode includes: if the image type is humanistic or natural, then performing super-resolution processing on the image to be printed.

[0121] As an optional implementation, when the image type is either humanistic or natural, the host computer determines the corresponding image processing mode according to preset rules. For example, when the image type is humanistic or natural, the associated image processing mode is super-resolution processing, in which case a super-resolution algorithm is used. Alternatively, interpolation algorithms can be used to interpolate the image to improve the clarity of image details during printing. Furthermore, a color fine-tuning algorithm can be included to ensure accurate and harmonious colors in the details.

[0122] Optionally, the step of processing the image to be printed based on the image processing mode includes: if the image type is an abstract type or a text type, then performing edge enhancement processing on the image to be printed.

[0123] As an optional implementation, if the image type is an abstract type or a text type, and the determined image processing mode is edge enhancement processing, edge smoothing algorithm and anti-aliasing algorithm can be used. The edge smoothing algorithm makes the edge transition more natural, and the anti-aliasing algorithm is used to avoid the edge from appearing jagged, affecting aesthetics and clarity, etc.

[0124] For example, for natural-type images, the rendering mode is determined to be a perceptual mode, the halftone mode to be a third-order halftone mode, and the image processing mode to be super-resolution processing. Super-resolution processing is performed on the image to be printed, and the super-resolution image is then parsed using the corresponding rendering mode and halftone mode to obtain the printing data.

[0125] For example, for a natural-type image to be printed, its rendering mode is first determined to be perceptual mode, its halftone mode to be third-order halftone mode, and its image processing mode to be super-resolution processing. Processing is then performed according to the image processing mode. For natural-type images, a super-resolution algorithm (such as a deep learning-based super-resolution reconstruction algorithm) is used to enhance the image resolution, allowing detailed features in the natural image (such as leaf veins, petal textures, animal fur, etc.) to be presented more precisely, avoiding blurriness after printing. Simultaneously, an edge enhancement algorithm is used to highlight the contour edges of natural scenery (such as mountain peaks, tree branch shapes, etc.), enhancing the overall sense of depth in the image and making it more three-dimensional and realistic during printing. Next, the processed image to be printed is analyzed based on the determined rendering mode and halftone mode. The "perceptual" rendering mode is used to adjust the overall color presentation of the image according to the characteristics of human eye color perception, making the printed natural image more realistic and natural in color. By combining the third-level halftone mode, the processed image is converted into a print data format that the printing device can understand, resulting in a natural image with vibrant colors, rich details, and clear outlines, and a better overall visual effect.

[0126] For example, if the image type is text, the rendering mode is determined to be a perceptual mode, the halftone mode is determined to be a second-order halftone mode, and the image processing mode is determined to be edge enhancement processing. For text images, the image processing mode is determined to be edge enhancement processing. Edge enhancement algorithms can be used to make the stroke edges of the text sharper and clearer, so that even small or thin characters can be clearly recognized, avoiding problems such as blurred edges and strokes sticking together. The rendering mode of the text image is determined to be a perceptual mode. The perceptual mode can adjust the color of the text image according to the human eye's color perception characteristics. Although text is usually mainly black and white, appropriate adjustments can make the text stand out more against different backgrounds. At the same time, the halftone mode is determined to be a second-order halftone mode. The second-order halftone mode can optimize the color presentation of the text, making the text color more uniform and stable when printed. Based on the determined rendering mode and halftone mode, the host computer analyzes the image to be printed after edge enhancement processing. In perceptual mode, the color presentation of the text image is adjusted to better match the visual perception of the human eye. Then, a second-order halftone mode is used for processing, optimizing the color and clarity of the text through specific dot arrangements and other methods. Finally, the processed image is converted into a print data format that printing devices can understand, including the pixel information, color information, and print resolution of the text.

[0127] For example, if the image type is a humanistic image, the rendering mode is determined to be a relative mode, the halftone mode is determined to be a third-order halftone mode, and the image processing mode is determined to be super-resolution processing. For humanistic images, the image processing mode is determined to be super-resolution processing. Super-resolution algorithms are used to improve image resolution, making facial expressions, architectural details, and various elements of cultural activities more clearly discernible. This allows for better representation of the richness and realism of the humanistic scene after printing. The rendering mode for humanistic images is determined to be a relative mode. The relative mode can adjust color and contrast according to the specific content of the image, making the colors of people and scenes more natural and harmonious. Simultaneously, the halftone mode is determined to be a third-order halftone mode to better present the color levels and details in the image. Based on the determined rendering mode and halftone mode, the super-resolution processed image to be printed is analyzed. In the relative mode, parameters such as color, contrast, and brightness are adjusted to highlight the characteristics of people and scenes. Then, the third-order halftone mode is used for processing, and through fine dot arrangement, the image has higher color fidelity and clarity during printing. Finally, the processed image is converted into a print data format that the printing device can understand, including the image's pixel information, color information, and print resolution.

[0128] For example, if the image type is abstract, the rendering mode is determined to be absolute mode, the halftone mode is determined to be second-order halftone mode, and the image processing mode is determined to be edge enhancement processing. For abstract images, the image processing mode is determined to be edge enhancement processing. Edge enhancement algorithms can be used to highlight the edges of lines and shapes in abstract images, enhancing the visual impact and three-dimensionality of the image. This makes the printed abstract image more vivid and more attractive to the viewer. The rendering mode of the abstract image is determined to be absolute mode. Absolute mode can precisely control the color and brightness of the image, which is very suitable for the bold colors and strong contrasts that often appear in abstract images. At the same time, the halftone mode is determined to be second-order halftone mode. Second-order halftone mode can better present the details and textures in the abstract image while maintaining the color uniformity of the image. Based on the determined rendering mode and halftone mode, the host computer analyzes the image to be printed after edge enhancement processing. In absolute mode, the color and brightness parameters of the image are precisely adjusted to highlight the unique style of the abstract image. Then, second-order halftone mode is used for processing, and through reasonable dot arrangement, the image has higher color reproduction and clarity when printed. Finally, the processed image is converted into a print data format that the printing device can understand, including the image's pixel information, color information, and print resolution.

[0129] For example, if the image type is a simple color type, the rendering mode is determined to be saturation mode, the halftone mode is determined to be third-order halftone mode, and no image processing mode exists. The rendering mode for the simple color type image is determined to be saturation mode. Saturation mode enhances the saturation of image colors, making simple colors more vibrant and highlighting their concise and bright characteristics. Simultaneously, the halftone mode is determined to be third-order halftone mode to better present the color levels and details in the image. Based on the determined rendering mode and halftone mode, the image to be printed is analyzed. In saturation mode, the color saturation of the image is adjusted to make the colors more rich. Then, third-order halftone mode is used for processing, and through fine dot arrangement, the image has higher color fidelity and clarity during printing. Finally, the processed image is converted into a printing data format that the printing device can understand, including the image's pixel information, color information, and printing resolution.

[0130] Through the above examples, we can see how to determine the corresponding rendering mode, halftone mode, and image processing mode according to different image types, perform targeted processing on various images to be printed, and finally obtain high-quality target images to meet printing requirements.

[0131] Based on any combination of the above embodiments, in one possible embodiment of this application, referring to... Figure 4For images of the natural type to be printed, a perceptual rendering mode and super-resolution processing are used. This mode is suitable for color image objects with a large number of areas of continuous color change and a large number of color details. The observer pays more attention to the overall color visual effect of the image. Figure 4 The image on the left is the original image (i.e., the image to be printed), and the image on the right is the image after rendering (i.e., the updated image), with a significant improvement in color quality.

[0132] In one possible embodiment of this application, reference is made to Figure 5 For images to be printed that are text-based, a specific magnification algorithm is used for enhancement processing to reduce blur and distortion. Specifically, Figure 5 The image on the left is the original image, the image in the middle is the result of magnification five times without the corresponding step (edge ​​enhancement) processing in the printing data generation method of this application, and the image on the right is the result of magnification five times after the corresponding step (edge ​​enhancement) processing in the printing data generation method of this application. It can be seen that the printing quality of the image has been significantly improved.

[0133] Reference Figure 6 For images of humanities type to be printed, use absolute rendering mode and super-resolution to enhance detail. Figure 6 The left image is the original image, and the right image is the image after processing (super-resolution processing) according to the corresponding steps in the method of this application. The image details in the right image are significantly improved.

[0134] Reference Figure 7 For images of abstract type to be printed, edge features in the image can be enhanced by applying a sharpening filter. Figure 7 The left image is the original image, and the right image is the image after processing (edge ​​enhancement) by the corresponding steps in the method of this application. The edge information in the right image has been significantly enhanced.

[0135] Reference Figure 8 For images of simple color types to be printed, use the saturation rendering mode to print the purest and most saturated colors. Figure 8 The left image is the original image, and the right image is the image after processing (saturation rendering) according to the corresponding steps in the method of this application. The color information in the right image is more saturated.

[0136] Based on any of the above embodiments, in one possible embodiment of this application, before the step of determining the rendering mode and halftone mode based on the image type of the image to be printed, the method further includes:

[0137] Step D10: Perform an image quality assessment on the image to be printed to obtain the resolution and noise of the image to be printed.

[0138] In some embodiments, the image quality assessment algorithm used by the host computer is a method that comprehensively considers multiple image indicators to determine the image quality. It can be implemented based on various mature algorithm models, such as a combination of a full-reference peak signal-to-noise ratio algorithm and a structural similarity algorithm, or a no-reference natural image quality assessment algorithm. These algorithms measure image quality by analyzing pixel information, grayscale distribution, texture features, etc., thereby determining the image resolution and detecting noise present in the image.

[0139] To determine the resolution, the host computer first inputs the image to be printed into the image quality assessment algorithm module. Taking a pixel-based approach as an example, the algorithm counts the number of pixels in the horizontal and vertical directions of the image to directly obtain the original resolution information, such as determining that the image resolution is 1920×1080 pixels. Alternatively, it infers the effective resolution of the image by analyzing its high-frequency and low-frequency information. This is because high-frequency information is often related to image details, while low-frequency information is related to the general outline of the image. Based on their proportions, the actual resolution level that the image can clearly display can be determined.

[0140] In noise detection, image quality assessment algorithms analyze the grayscale value changes of image pixels. For example, if the grayscale values ​​of pixels in a local area of ​​an image fluctuate irregularly and drastically, showing a significant anomaly compared to the surrounding areas, the algorithm determines that noise exists in that area. Noise types include Gaussian noise and salt-and-pepper noise. Salt-and-pepper noise is characterized by randomly appearing black and white pixels in the image, resembling salt and pepper sprinkled on the screen. The algorithm can identify the type of noise, its approximate distribution range, and intensity by scanning and analyzing different regions of the image. For instance, it might detect Gaussian noise in the image, primarily concentrated at the image's edges, with a moderate noise intensity.

[0141] Step D20: Optimize the image to be printed based on the resolution and the noise.

[0142] In some embodiments, if the preceding evaluation determines that the resolution of the image to be printed is too low to meet the requirements of high-quality printing, the host computer will process it using an image super-resolution algorithm. For example, deep learning-based super-resolution reconstruction algorithms, such as SRCNN (Super-Resolution Convolutional Neural Network) and ESPCN (Efficient Sub-Pixel Convolutional Neural Network), can be used. These models learn the mapping relationship between a large number of high- and low-resolution image pairs, enabling them to predict and generate higher-resolution images based on the features of the low-resolution image. The host computer inputs the low-resolution image to be printed into the selected super-resolution model. After multiple layers of convolution and non-linear activation, the model outputs an image with improved resolution, such as upscaling an original 800×600 pixel image to 1600×1200 pixels, allowing the image to display more details during printing.

[0143] When the resolution of the image to be printed is too high, problems such as excessively large file size, long printing time, and excessive memory usage of the printing device may occur. In this case, the host computer, based on the printing device's performance parameters such as maximum supported printing resolution and memory capacity, as well as the target print size, performs appropriate downsampling processing on the high-resolution image. Downsampling algorithms such as bilinear interpolation and nearest neighbor interpolation are used to reduce the image resolution while minimizing the loss of key features and details, thus adapting it to the requirements of the printing device and achieving more efficient printing. For example, if the printing device's maximum supported resolution is 300 dpi, and the original image resolution corresponds to an excessively high dpi, the host computer adjusts it to a suitable dpi level using a downsampling algorithm to ensure smooth printing.

[0144] Furthermore, denoising algorithms are selected for different noise types. For different types of noise detected, the host computer uses the corresponding denoising algorithm for processing. For Gaussian noise, the Wiener filtering algorithm is commonly used. It estimates the pixel values ​​of the original image based on the local statistical characteristics of the image and the statistical characteristics of the noise, using the minimum mean square error criterion, thereby removing Gaussian noise. For salt-and-pepper noise, the median filtering algorithm is more effective. This algorithm sorts the gray values ​​of a pixel and its neighborhood pixels in the image, taking the median value as the new gray value for that pixel. This effectively removes isolated salt-and-pepper noise points, making the image smoother and cleaner. The host computer applies the appropriate denoising algorithm to the entire image or a specific noise region based on the detected noise type and distribution.

[0145] Optionally, to achieve better denoising results, the host computer can perform multiple iterations of the denoising process. For example, when using the Wiener filtering algorithm to remove Gaussian noise, after the first processing, the image is re-detected for noise. If residual noise remains, the Wiener filtering algorithm can be applied again or its parameters adjusted to continue denoising until the noise in the image is reduced to an acceptable range, ensuring that the printed image will not affect the visual effect due to noise.

[0146] By evaluating resolution and noise and performing corresponding optimization steps, the quality of the image to be printed can be improved before determining the image type, rendering mode, and feature type, laying a good foundation for obtaining better printing results.

[0147] For example, suppose a user wants to print a scanned image of an old photograph downloaded from the internet. This image has a low resolution of only 640×480 pixels, and due to scanning equipment and other factors, it contains some Gaussian noise, making the image appear somewhat blurry and grainy. After image quality assessment, pixel statistical analysis confirms the image resolution as 640×480 pixels. Noise detection reveals that the image's pixel grayscale values ​​exhibit random fluctuations following a Gaussian distribution, indicating the presence of Gaussian noise, which is relatively uniformly distributed and at a moderate intensity. The SRCNN super-resolution reconstruction algorithm can be used to process the image. The low-resolution image is input into the SRCNN model, and after processing, the image resolution is increased to 1280×960 pixels, significantly enriching the image details. For the detected Gaussian noise, Wiener filtering can be applied for denoising. Since the noise intensity is moderate, some residual noise remains after the first filtering step. Therefore, a second Wiener filtering iteration is performed, ultimately reducing the Gaussian noise in the image to a low level, resulting in a much clearer and smoother image.

[0148] After such resolution enhancement and noise removal, the image then enters subsequent processes such as determining the rendering mode based on the image type. The final printed photo has significantly improved clarity and image purity compared to the original image.

[0149] For example, a user prepares to print a high-resolution art illustration. The original image resolution is 5000×3500 pixels, but some salt-and-pepper noise was introduced during scanning or transmission, resulting in occasional black and white noise pixels that affect the aesthetics. Image quality assessment algorithms analyze the image, determining its true high resolution to be 5000×3500 pixels. Noise detection reveals scattered black and white pixels, consistent with salt-and-pepper noise characteristics, and these noise pixels are distributed across various areas of the image with relatively weak intensity. Considering the maximum supported resolution of the printing device and to avoid excessive printing time, the image can be downsampled. Based on the target print size and printing device performance, the image resolution is adjusted to 3000×2100 pixels, preserving key artistic details while ensuring efficient printing. Median filtering is then applied to address the salt-and-pepper noise. Due to the weak noise intensity, after a single median filtering step, the salt-and-pepper noise is largely removed, resulting in a cleaner and more aesthetically pleasing image.

[0150] After the resolution adaptation and noise removal operations described above, the artistic illustration image enters the subsequent processing flow. The final printed product can present the original artistic effect of the illustration in high quality without being adversely affected by high resolution and noise issues.

[0151] Based on any of the above embodiments, in one possible embodiment of this application, if there is an associated image processing mode for the image type, the image to be printed is first evaluated for image quality to obtain the resolution and noise of the image to be printed; based on the resolution and the noise, the image to be printed is optimized, and then processed based on the image processing mode, so as to obtain an updated image to be printed.

[0152] As an optional implementation, before determining the rendering mode and halftone mode based on the image type of the image to be printed, it is determined whether the image type is associated with a super-resolution processing mode. If so, an image quality assessment is first performed on the image to be printed to obtain the noise of the image to be printed, then the image to be printed is optimized based on the noise, and finally super-resolution processing is performed on the optimized image to be printed.

[0153] As an optional implementation, before determining the rendering mode and halftone mode based on the image type of the image to be printed, it is determined whether the image type is associated with edge enhancement processing. If edge enhancement processing is associated, the image to be printed is first evaluated for image quality to obtain the resolution and noise of the image to be printed. Then, the image to be printed is optimized based on the resolution and noise, and finally, edge enhancement processing is performed on the optimized image to be printed.

[0154] As another optional implementation, before determining the rendering mode and halftone mode based on the image type of the image to be printed, if the image type is not associated with an image processing mode, then the image to be printed is subjected to image quality assessment to obtain the resolution and noise of the image to be printed; based on the resolution and the noise, the image to be printed is optimized; then, according to the rendering mode and halftone mode matched to the image to be printed, the optimized image to be printed is parsed to obtain the printing data of the image to be printed.

[0155] This application also provides a printing system, referring to... Figure 9 The printing system 1000 includes a host computer 100 and an inkjet printer 200.

[0156] In some embodiments, the host computer 100 is used to acquire an image to be printed, and based on the steps of the image printing data generation method described above, determines the printing data of the image to be printed, and sends the printing data to the inkjet printing device 200. The inkjet printing device 200 is used to print the image to be printed based on the printing data.

[0157] In some embodiments, the host computer 100 is used to acquire an image to be printed and send the image to be printed to the inkjet printing device 200. The inkjet printing device 200 is used to determine the printing data of the image to be printed based on the steps of the image printing data generation method described above, and then print the image to be printed based on the printing data.

[0158] This application provides a computer device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the image printing data generation method of the above embodiment 1.

[0159] The following is for reference. Figure 10 The diagram illustrates a structural schematic of a computer device suitable for implementing embodiments of this application. The computer device in the embodiments of this application may include, but is not limited to, terminals such as mobile terminals, laptops, tablets, etc., and fixed terminals such as desktop computers. Figure 10 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0160] like Figure 10As shown, the computer device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the computer device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the computer device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows computer devices with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0161] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0162] The computer device provided in this application, employing the image printing data generation method described in the above embodiments, can solve the technical problem in the prior art where it is difficult to accurately find the optimal combination of printing data, resulting in poor printing quality. Compared with the prior art, the beneficial effects of the computer device provided in this application are the same as those of the computer device provided in the above embodiments, and other technical features of this computer device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0163] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0164] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0165] This application embodiment also provides an inkjet printing device 200, which is used to acquire printing data of an image to be printed determined based on the image printing data generation method described in any of the above embodiments, and then print the image to be printed based on the printing data.

[0166] Furthermore, referring to Figure 11 The inkjet printing equipment 200 includes:

[0167] The printing assembly 210 includes a slide rail 211 and a print head 212, wherein the print head 212 is slidably disposed on the slide rail 211.

[0168] Memory 220, wherein the memory stores computer program products that can be executed by a processor;

[0169] The processor 230 is configured to acquire printing data of an image to be printed generated by the image printing data generation method described in any of the above embodiments, and then control the print head to move on the slide rail and control the ink jetting of the print head based on the printing data to print the image to be printed.

[0170] The inkjet printing device 200 can receive printing data of an image to be printed generated based on the image printing data generation method described in any of the above embodiments; or generate printing data of an image to be printed based on the image printing data generation method described in any of the above embodiments.

[0171] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the image printing data generation method in the above embodiments.

[0172] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In some embodiments, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0173] The aforementioned computer-readable storage medium may be included in a computer device or may exist independently and not assembled into a computer device.

[0174] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a computer device, cause the computer device to: determine at least one feature type based on the image type of the image to be printed;

[0175] The image to be printed is processed according to the rendering mode corresponding to the feature type to obtain the target image;

[0176] The printing data of the image to be printed is obtained based on the analysis of the target image.

[0177] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0178] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer programs.

[0179] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0180] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described image printing data generation method. This solves the technical problem in the prior art where it is difficult to accurately find the optimal combination of printing data, leading to poor printing results. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the image printing data generation method provided in the above embodiments, and will not be repeated here.

[0181] This application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the image printing data generation method described above.

[0182] The computer program product provided in this application can solve the technical problem in the prior art that it is difficult to accurately find the optimal combination of print data, resulting in poor print quality. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this application are the same as the beneficial effects of the image print data generation method provided in the above embodiments, and will not be repeated here.

[0183] The above are merely preferred embodiments of this application and do 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 scope of this application.

Claims

1. A method for generating print data for an image, characterized in that, The method for generating print data for the image includes: Acquire the image to be printed and identify the image type of the image to be printed, including natural type, text type, humanistic type, abstract type and simple color type; Based on the image type, determine the rendering mode and halftone mode matching the image to be printed. The rendering mode includes perceptual mode, relative mode, absolute mode and saturation mode. The halftone mode includes second-order halftone mode and third-order halftone mode. Based on the rendering mode and halftone mode matched by the image to be printed, the image to be printed is parsed to obtain the printing data of the image to be printed. The step of determining the matching rendering mode and halftone mode of the image to be printed based on the image type includes: If the image type is natural, the rendering mode is determined to be perceptual mode, and the halftone mode is determined to be third-order halftone mode; If the image type is text, the rendering mode is determined to be perceptual mode, and the halftone mode is determined to be second-order halftone mode; If the image type is humanistic, the rendering mode is determined to be relative mode, and the halftone mode is determined to be third-order halftone mode; If the image type is an abstract type, the rendering mode is determined to be an absolute mode, and the halftone mode is a second-order halftone mode; If the image type is a simple color type, the rendering mode is determined to be a saturation mode and the halftone mode is a third-order halftone mode.

2. The print data generation method as described in claim 1, characterized in that, The step of identifying the image type of the image to be printed includes: Input the image to be printed into the image classification model; The image to be printed is classified using the image classification model to obtain the image type of the image to be printed.

3. The method for generating print data as described in claim 1, characterized in that, The step of identifying the image type of the image to be printed includes: Obtain the probability value of each image type corresponding to the image to be printed; The image type with the highest probability value is selected as the image type to be printed.

4. The method for generating print data as described in claim 1, characterized in that, The step of determining the rendering mode matching the image to be printed based on the image type includes: If the image type is associated with an associated rendering mode, then the associated rendering mode is determined as the rendering mode that matches the image to be printed. If the image type is not associated with an associated rendering mode, then the default rendering mode is determined as the rendering mode that matches the image to be printed.

5. The method for generating print data as described in claim 1, characterized in that, The step of determining the halftone mode matching the image to be printed based on the image type includes: If the image type is associated with an associated halftone mode, then the associated halftone mode is determined as the halftone mode that matches the image to be printed. If the image type is not associated with an associated halftone mode, then the default halftone mode is determined as the halftone mode that matches the image to be printed.

6. The method for generating print data as described in claim 1, characterized in that, Before the step of parsing the image to be printed based on the matching rendering mode and halftone mode to obtain the printing data of the image to be printed, the method further includes: If the image type is associated with an image processing mode, then the image to be printed is processed based on the image processing mode to obtain an updated image to be printed.

7. The method for generating print data as described in claim 6, characterized in that, The step of processing the image to be printed based on the image processing mode includes: If the image type is either humanistic or natural, then super-resolution processing is performed on the image to be printed; and / or If the image type is abstract or text, then edge enhancement processing is performed on the image to be printed.

8. The method for generating print data as described in claim 1, characterized in that, Before the step of determining the rendering mode and halftone mode matching the image to be printed based on the image type, the method further includes: The image to be printed is subjected to image quality assessment to obtain the resolution and noise of the image to be printed; The image to be printed is optimized based on the resolution and the noise.

9. A computer device, characterized in that, The computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the print data generation method as described in any one of claims 1 to 8.

10. An inkjet printing device, characterized in that, Used to acquire print data of an image to be printed determined based on the print data generation method as described in any one of claims 1 to 8, and then print the image to be printed based on the print data.

11. A printing system, characterized in that, The printing system includes a host computer and an inkjet printer. The host computer is used to acquire the image to be printed, generate printing data of the image to be printed based on the printing data generation method as described in any one of claims 1 to 8, and send the printing data to the inkjet printing device; The inkjet printing device is used to print the image to be printed based on the printing data; or, The host computer is used to acquire the image to be printed and send the image to be printed to the inkjet printing device; The inkjet printing device is used to generate print data of an image to be printed based on the print data generation method as described in any one of claims 1 to 8, and then print the image to be printed based on the print data.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the print data generation method as described in any one of claims 1 to 8.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the print data generation method as described in any one of claims 1 to 8.

Images