Image processing method and device of mobile terminal and storage medium

By using discrete cosine transform and edge-guided interpolation algorithms, image blocks are processed in a targeted manner to generate high-quality super-resolution images, solving the problem of insufficient computing resources on mobile terminals and improving the real-time performance and efficiency of image processing.

CN120876227APending Publication Date: 2025-10-31SHENZHEN ZHUXIN NETWORK TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510934803.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-08
Publication Date
2025-10-31

AI Technical Summary

Technical Problem

Image super-resolution technology for mobile terminals is limited by insufficient computing resources, making it impossible to generate high-quality super-resolution images in a timely manner and failing to meet the real-time requirements of processing speed.

Method used

Image energy distribution is analyzed by discrete cosine transform, image blocks are divided, and edge-guided interpolation algorithm is used to improve edge sharpness. Low-complexity upsampling is performed on blocks with simple textures, and fusion processing is used to generate super-resolution images.

Benefits of technology

Under the limited resources of mobile terminals, high-quality super-resolution images are generated, image processing efficiency is improved, and collaborative optimization of image super-resolution reconstruction and real-time processing is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120876227A_ABST
    Figure CN120876227A_ABST
Patent Text Reader

Abstract

The invention discloses an image processing method and device of a mobile terminal and a storage medium, and belongs to the technical field of image processing. The method comprises the steps of calculating energy distribution information of a to-be-processed image in the mobile terminal through discrete cosine transform, determining a first image block and a second image block in the to-be-processed image according to the energy distribution information, executing directional interpolation on the first image block through an edge guidance interpolation algorithm to obtain a first reconstructed image block, and / or executing directional interpolation on the second image block to obtain a second reconstructed image block. And performing an up-sampling action on the second image block to obtain a second reconstructed image block, and performing fusion processing on the first reconstructed image block and the second reconstructed image block to obtain a super-resolution image. Through image energy distribution detection, differentiation processing is performed on the image blocks containing different image information detail degrees, so that the image processing efficiency is improved while high-quality image processing is ensured under the condition of limited resources of the mobile terminal.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an image processing method, device and storage medium for a mobile terminal. Background Technology

[0002] Image super-resolution refers to the process of reconstructing a first image block from a first image block or image sequence. In related technologies, image super-resolution methods can be based on deep learning image processing models such as Convolutional Neural Networks (CNNs) or Generative Adversarial Networks (GANs) to generate high-quality super-resolution images rich in detail based on the complex mapping relationships between pixels.

[0003] However, when image super-resolution technology is applied to mobile terminals, due to the limited computing resources of mobile terminals, deep learning-based image processing models cannot generate super-resolution images with sharp edges and rich texture details in a timely manner, making it difficult for image super-resolution technology to meet the real-time processing speed requirements of mobile terminals.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide an image processing method, device and storage medium for mobile terminals, which aims to solve the technical problem that the image processing model cannot generate high-quality super-resolution images in a timely manner, making it difficult to meet the real-time processing speed requirements of mobile terminals.

[0006] To achieve the above objectives, this application provides an image processing method for a mobile terminal, the method comprising the following steps: The energy distribution information of the image to be processed in the mobile terminal is calculated by using discrete cosine transform, and the first image block and the second image block in the image to be processed are determined based on the energy distribution information. The first image block is obtained by performing directional interpolation on the first image block using an edge-guided interpolation algorithm; And / or, perform an upsampling operation on the second image block to obtain a second reconstructed image block; The first reconstructed image block and the second reconstructed image block are fused to obtain a super-resolution image.

[0007] In one embodiment, the step of calculating the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determining the first image block and the second image block in the image to be processed based on the energy distribution information includes: Based on the preset image block size information, the image to be processed is divided into at least two initial image blocks; Perform a discrete cosine transform on the initial image block to determine the low-frequency component energy value of the initial image block; The low-frequency component energy value is compared with a preset energy threshold to determine the first image block whose low-frequency component energy value is higher than the preset energy threshold, and the second image block whose low-frequency component energy value is lower than the preset energy threshold.

[0008] In one embodiment, the step of fusing the first reconstructed image block and the second reconstructed image block to obtain a super-resolution image includes: In the first reconstructed image block and the second reconstructed image block, the region to be overlapped is determined; Based on a predefined convolution kernel, the gradient vector of the target pixel in the region to be overlapped is calculated, and the edge gradient information of the region to be overlapped is formed according to the gradient vector. Based on the edge gradient information, the Poisson equation of the region to be overlapped is solved, and the target overlapping region is generated based on the pixel values ​​corresponding to the solution results. Based on the target overlapping region, the first reconstructed image block and the second reconstructed image block are fused to obtain the super-resolution image.

[0009] In one embodiment, the step of performing directional interpolation on the first image block using an edge-guided interpolation algorithm to obtain the first reconstructed image block includes: Calculate the gradient vector information of pixels within the first image block; Based on the mapping relationship between the gradient vector information and the corresponding pixel coordinates, the edge direction information of the first image block is determined; The first pixel value is calculated based on the predefined interpolation convolution kernel and the edge direction information. The first image block is generated by performing an interpolation operation on the first image block based on the first pixel value.

[0010] In one embodiment, the step of performing an upsampling operation on the second image block to obtain a second reconstructed image block includes: In the second image block, obtain the neighboring pixels of the target pixel; The distance weight of the neighboring pixels is calculated using a cubic polynomial based on the relative position information between the neighboring pixels and the target pixel. Based on the distance weight, the pixel values ​​of the neighborhood pixels are weighted and summed to obtain the second pixel value; The second image block is generated by performing an interpolation operation on the second image block based on the second pixel value.

[0011] In one embodiment, before the step of calculating the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determining the first image block and the second image block in the image to be processed based on the energy distribution information, the method further includes: Obtain the temperature information and image processing frame rate information of the mobile terminal at the current moment; The policy controller generates a temperature adjustment factor based on the temperature information and a frame rate adjustment factor based on the frame rate information. Based on the weighted calculation results of the temperature adjustment factor and the frame rate adjustment factor, the energy threshold of the image to be processed is updated, wherein the energy threshold is used to distinguish between the first image block and the second image block.

[0012] In one embodiment, after the steps of obtaining the real-time temperature information and image processing frame rate information of the mobile terminal, the method further includes: When the temperature information is higher than the temperature threshold, the image block size information is adjusted to the target size information; And / or, when the image processing frame rate information is lower than the frame rate threshold, the first image fusion module that performs the first reconstructed image block and the second reconstructed image block fusion action is switched to the second image fusion module.

[0013] In one embodiment, the steps of generating a temperature adjustment factor based on the temperature information and generating a frame rate adjustment factor based on the frame rate information via a policy controller include: The temperature factor corresponding to the temperature information is obtained through the temperature adjustment function, and the frame rate factor of the frame rate information is obtained through the frame rate adjustment function. Based on the energy distribution information, calculate the temperature weighting coefficient and the frame rate weighting coefficient; Based on the temperature weight coefficient and the frame rate weight coefficient, the temperature factor and the frame rate factor are weighted and summed to obtain the strategy score; Based on the strategy score, the temperature factor and the frame rate factor are adjusted to form the temperature adjustment factor and the frame rate adjustment factor.

[0014] In addition, to achieve the above objectives, this application also provides an image processing device for a mobile terminal, the 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 image processing method for the mobile terminal as described above.

[0015] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the image processing method of the mobile terminal as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application utilizes discrete cosine transform to analyze image energy distribution and divides the image into blocks. For the first image block containing image details, an edge-guided interpolation algorithm is used to perform directional interpolation to improve edge sharpness. Simultaneously, for the second image block with simple textures, a low-complexity upsampling operation is performed. These are then fused to generate a super-resolution image. This combines image content awareness with a differentiated processing strategy, suppressing blurring and jagged artifacts generated by the interpolation algorithm in edge regions. Furthermore, by simplifying the processing flow for secondary regions, the computational load for image super-resolution is significantly reduced. Under the limited resources of mobile terminals, this approach ensures high-quality image processing while improving image processing efficiency, achieving synergistic optimization of image super-resolution reconstruction and real-time processing efficiency. Attached Figure Description

[0017] 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.

[0018] 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.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the image processing method for a mobile terminal according to this application; Figure 2 This is a flowchart illustrating the first embodiment of the image processing method for a mobile terminal according to this application; Figure 3 This is a schematic diagram of the structure of an image processing device for a mobile terminal in the hardware operating environment of the embodiments of this application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0022] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is as follows: Energy distribution information of the image to be processed in the mobile terminal is calculated by discrete cosine transform, and a first image block and a second image block in the image to be processed are determined based on the energy distribution information; directional interpolation is performed on the first image block using an edge-guided interpolation algorithm to obtain a first reconstructed image block; and / or upsampling is performed on the second image block to obtain a second reconstructed image block; the first reconstructed image block and the second reconstructed image block are fused to obtain a super-resolution image.

[0024] Existing image super-resolution methods can utilize deep learning image processing models such as Convolutional Neural Networks (CNNs) or Generative Adversarial Networks (GANs) to generate high-quality super-resolution images rich in detail based on complex pixel mapping relationships. However, when image super-resolution technology is applied to mobile terminals, the limited computing resources of these terminals prevent deep learning-based image processing models from generating super-resolution images with sharp edges and rich texture details in a timely manner. This makes it difficult for image super-resolution technology to meet the real-time processing speed requirements of mobile devices.

[0025] This application utilizes discrete cosine transform to analyze image energy distribution and divides the image into blocks. For the first image block containing image details, an edge-guided interpolation algorithm is used to perform directional interpolation to improve edge sharpness. Simultaneously, for the second image block with simple textures, a low-complexity upsampling operation is performed. These are then fused to generate a super-resolution image. This combines image content awareness with a differentiated processing strategy, suppressing blurring and jagged artifacts generated by the interpolation algorithm in edge regions. Furthermore, by simplifying the processing flow for secondary regions, the computational load for image super-resolution is significantly reduced. Under the limited resources of mobile terminals, this approach ensures high-quality image processing while improving image processing efficiency, achieving synergistic optimization of image super-resolution reconstruction and real-time processing efficiency.

[0026] To better understand the above technical solutions, exemplary embodiments of this application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0027] It should be noted that the executing entity in this embodiment can be an image processing system of a mobile terminal, 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 an electronic device or image processing device of a mobile terminal capable of performing the above functions. This embodiment does not specifically limit it in this regard. The following uses an image processing system of a mobile terminal as an example to describe this embodiment and the following embodiments.

[0028] Based on this, embodiments of this application provide an image processing method for a mobile terminal, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the image processing method for a mobile terminal according to this application.

[0029] In this embodiment, the image processing method of the mobile terminal includes steps S10 to S40: Step S10: Calculate the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determine the first image block and the second image block in the image to be processed based on the energy distribution information; In this embodiment, the image processing system calculates the energy distribution information in the image to be processed using Discrete Cosine Transform (DCT). The system divides the image into blocks and calculates the energy value of each block. Blocks with energy values ​​higher than a threshold are selected as first image blocks, and blocks with energy values ​​lower than the threshold are selected as second image blocks. The first image block is a region containing details and edges, while the second image block is a relatively flat region or a region with less detail.

[0030] It should be noted that Discrete Cosine Transform (DCT) is a mathematical transformation method that converts an image from the spatial domain to the frequency domain. By linearly combining the pixel values ​​of an image using cosine functions, the image is represented as a weighted sum of cosine signals at different frequencies. This effectively reflects the energy distribution characteristics of the image, where low-frequency components reflect the overall grayscale trend, and high-frequency components reflect image details and edge information. Energy distribution information refers to the proportion of energy in different frequency bands of the image. The energy value of each frequency component can be calculated using DCT for subsequent block segmentation.

[0031] As an optional implementation, the image processing system divides the image to be processed into at least two initial image blocks based on preset image block size information, performs discrete cosine transform on the initial image blocks to determine the low-frequency component energy value of the initial image blocks, compares the low-frequency component energy value with a preset energy threshold, and determines the first image block with a low-frequency component energy value higher than the preset energy threshold and the second image block with a low-frequency component energy value lower than the preset energy threshold.

[0032] Specifically, Directional Transformation (DCT) transforms image blocks from the spatial domain to the frequency domain, allowing the separation of high-frequency and low-frequency components within each block. High-frequency components typically correspond to the details of the image block, while low-frequency components correspond to the main outline. After the DCT transform, the energy value of the image block is obtained by calculating the sum of squares of the coefficients in each frequency domain.

[0033] For example, the image processing system decomposes a 64*64 pixel block into 4*4 image blocks, calculates only the 4*4 low-frequency DCT coefficients, and determines the energy value of the image block, thereby reducing the energy calculation complexity compared to DCT full-frequency domain calculation.

[0034] As another alternative implementation, the image processing system can also use wavelet transform (WT) or discrete Fourier transform (DFT) to divide the image into high-frequency and low-frequency components to obtain low-frequency energy coefficients.

[0035] Step S20: Perform directional interpolation on the first image block using an edge-guided interpolation algorithm to obtain the first reconstructed image block; It should be noted that the New Edge Diected Interpolation (NEDI) algorithm is an interpolation algorithm based on the edge direction information of an image. By analyzing the edge direction of a local region of the image, new pixels are inserted along the edge direction to maintain the continuity and sharpness of the interpolated image edges.

[0036] In this embodiment, the image processing system uses an edge-guided interpolation algorithm to guide the first image block to retain the edge information of the image block during the interpolation process.

[0037] In one embodiment, the image processing system calculates the gradient vector information of pixels within a first image block, determines the edge direction information of the first image block based on the mapping relationship between the gradient vector information and the coordinates of the corresponding pixels, calculates the first pixel value based on a predefined interpolation convolution kernel and the edge direction information, and performs an interpolation operation on the first image block based on the first pixel value to generate a first reconstructed image block.

[0038] Specifically, the image processing system analyzes the local covariance characteristics of the first image block and utilizes the geometric duality between the low-resolution and high-resolution covariances to calculate the value of the pixel to be inserted in the first reconstructed image block. That is, the four closest pixels to this point in the high-resolution raster along the diagonal direction.

[0039] For example, NEDI first performs four nearest neighbor interpolation on the image and calculates the variance of the neighborhood of each pixel to determine whether the pixel is an edge point. If it is, the value of the pixel is directly transferred to the newly generated image; otherwise, bilinear interpolation or bicubic interpolation is used to fill the edge.

[0040] Step S30: and / or, perform an upsampling operation on the second image block to obtain a second reconstructed image block; In this embodiment, the image processing system can estimate the grayscale value of the interpolated pixel position through upsampling methods such as bilinear interpolation or bicubic interpolation, thereby improving the image resolution.

[0041] As an optional implementation, the image processing system improves image resolution through bicubic upsampling. Specifically, in the second image block, the system acquires neighboring pixels of the target pixel (i.e., the pixel region within a 4x4 area surrounding the target pixel) based on a preset 4x4 image grid. Then, using a cubic polynomial, it calculates distance weights for these neighboring pixels based on their relative positions to the target pixel. Based on these distance weights, the pixel values ​​of the neighboring pixels are weighted and summed to obtain a second pixel value. A new pixel is then formed based on this second pixel value. At the interpolation image location, an interpolation operation is performed on the second image block to generate a second reconstructed image block.

[0042] As another alternative implementation, the image processing system can also use bilinear interpolation to estimate the approximate values ​​of discrete data points in continuous space by performing linear interpolation once in each of the two directions, thereby determining the pixel values ​​of different pixel coordinates in the second reconstructed image block and forming the second reconstructed image block.

[0043] Step S40: Perform fusion processing on the first reconstructed image block and the second reconstructed image block to obtain a super-resolution image.

[0044] In this embodiment, the overlapping region between the first reconstructed image block and the second reconstructed image block is determined. Gradient information of pixels in the overlapping region is calculated, and a weight mask is constructed based on the gradient magnitude and direction. Pixels at the edges of the first reconstructed image block and pixels in the smooth regions of the second reconstructed image block are then weighted and fused according to the weight mask. This image fusion process combines image blocks processed in different ways to achieve a visually smooth transition in the entire image, avoiding obvious seams caused by weight mixing.

[0045] As an optional implementation, the image processing system can use a Poisson edge blending algorithm to smooth the stitching region between the first and second reconstructed image blocks, thereby stitching them together to form a super-resolution image. The image reconstruction system determines the regions to be overlapped within the first and second reconstructed image blocks, calculates the gradient vectors of target pixels in these regions based on predefined convolution kernels, and generates edge gradient information for the overlapping regions based on these gradient vectors. Based on this edge gradient information, the system solves the Poisson equation for the overlapping regions and generates the target overlapping region based on the corresponding pixel values. The image processing system performs Poisson edge blending on the overlapping regions between different first and second reconstructed image blocks, and then fuses all first and second reconstructed image blocks based on the obtained target overlapping region to obtain the super-resolution image.

[0046] As an alternative implementation, the image processing system can also use a lightweight inpainting network based on a convolutional neural network (CNN) to construct the regions of the image to be overlapped, thereby fusing different first reconstructed image blocks and second reconstructed image blocks to form a super-resolution image.

[0047] This application embodiment analyzes the image energy distribution using discrete cosine transform and divides the image into blocks. For the first image block containing image details, directional interpolation is performed using an edge-guided interpolation algorithm to improve edge sharpness. At the same time, for the second image block with simple texture, a low-complexity upsampling operation is performed. The images are then fused to generate a super-resolution image. This combines image content awareness with a differentiated processing strategy, suppressing blurring and jagged artifacts generated by the interpolation algorithm in edge regions. Furthermore, by simplifying the processing flow of secondary regions, the computational load of image super-resolution is significantly reduced. Under the limited resources of mobile terminals, this ensures high-quality image processing while improving image processing efficiency, achieving synergistic optimization of image super-resolution reconstruction and real-time processing efficiency.

[0048] Based on the same inventive concept, this application also provides a second embodiment, referring to... Figure 2 , Figure 2This is a flowchart illustrating the second embodiment of the image processing method for a mobile terminal according to this application.

[0049] In this embodiment, the image processing method of the mobile terminal further includes steps S11 to S13: Step S11: Obtain the temperature information and image processing frame rate information of the mobile terminal at the current moment; In this embodiment, the image processing system can obtain the temperature information of the mobile terminal through the temperature sensor of the mobile terminal, and at the same time, obtain the image processing frame rate information by counting the frame rate of image processing through the frame rate monitoring module.

[0050] Step S12: The policy controller generates a temperature adjustment factor based on the temperature information and a frame rate adjustment factor based on the frame rate information. In this embodiment, the strategy controller is used to formulate corresponding control strategies based on real-time monitored data, and to adjust the temperature adjustment factor and frame rate adjustment factor according to the real-time processing parameters of the mobile terminal. The temperature adjustment factor and frame rate adjustment factor are values ​​generated based on temperature and frame rate information, used to adjust the parameters of image processing.

[0051] Specifically, the policy controller in the mobile terminal receives device temperature and frame rate information. Based on preset temperature adjustment rules and frame rate adjustment rules, it calculates and generates temperature adjustment factors and frame rate adjustment factors.

[0052] It should be noted that the policy controller includes two core functions: a central decision unit and a multi-objective optimizer. The central decision unit dynamically adjusts the super-resolution parameters based on the real-time hardware status (temperature / frame rate) and content characteristics (texture complexity), while the multi-objective optimizer simultaneously pursues three major objectives: maximizing image quality, minimizing power consumption, and stabilizing the frame rate.

[0053] As an optional implementation, the policy controller can obtain the temperature factor corresponding to the temperature information through a temperature adjustment function, and the frame rate factor of the frame rate information through a frame rate adjustment function. Based on the energy distribution information, a temperature weight coefficient and a frame rate weight coefficient are calculated. Then, based on these coefficients, a weighted sum of the temperature factor and the frame rate factor is calculated to obtain a policy score. Further, the policy controller adjusts the temperature factor and the frame rate factor based on this policy score, and selects the temperature factor and frame rate factor that result in the highest policy score as the temperature adjustment factor and frame rate adjustment factor, respectively.

[0054] As an alternative implementation, the principle of generating adjustment factors is based on the degree of deviation between the device state and the ideal state. The adjustment factors quantify the impact of this deviation on image processing parameters. The temperature adjustment factor reflects the heat dissipation pressure of the device, and the frame rate adjustment factor reflects the processing speed pressure. They balance image quality and processing performance by comprehensively adjusting the energy threshold.

[0055] Step S13: Update the energy threshold of the image to be processed based on the weighted calculation results of the temperature adjustment factor and the frame rate adjustment factor, wherein the energy threshold is used to distinguish between the first image block and the second image block.

[0056] In this embodiment, based on temperature adjustment factors and frame rate adjustment factors, the image processing module can adjust the number of image blocks after image segmentation and perform different interpolation methods based on energy values. For example, when the mobile terminal power is high, by increasing the energy threshold, the number of image blocks for edge-guided interpolation is reduced, and the number of upsampled image blocks is increased, thereby reducing the amount of data computation.

[0057] For example, based on preset weights, such as a temperature weight of 0.6 and a frame rate weight of 0.4, the obtained temperature adjustment factor and frame rate adjustment factor are weighted and calculated. The calculation formula is: Overall adjustment coefficient = Temperature adjustment factor × 0.6 + Frame rate adjustment factor × 0.4. Then, the original preset energy threshold is multiplied by the overall adjustment coefficient to obtain the updated energy threshold. For example, if the original energy threshold is 1000 and the overall adjustment coefficient is 1.2 × 0.6 + 0.9 × 0.4 = 1.08, then the updated energy threshold is 1000 × 1.08 = 1080.

[0058] Optionally, when the temperature information is higher than a temperature threshold, the policy controller will also adjust the image block size information to the target size information, for example, adjust the image block size to 256*256. And / or, when the image processing frame rate information is lower than a frame rate threshold, the first image fusion module that performs the first reconstructed image block and the second reconstructed image block fusion action will be switched to the second image fusion module. The second image fusion module is an image fusion module that does not include Poisson edge blending function, thereby disabling the Poisson edge blending function of the first image fusion module to further improve image processing efficiency.

[0059] Since the system described in Embodiment 2 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0060] The following is for reference. Figure 3This document illustrates a schematic diagram of an image processing device suitable for implementing the embodiments of this application in a mobile terminal. The image processing device for the mobile terminal in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The image processing device for the mobile terminal shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0061] like Figure 3 As shown, the image processing device of a mobile terminal may include a processing unit 1001 (e.g., a core processor, a graphics processor, 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 random access memory 1004 also stores various programs and data required for the operation of the image processing device of the mobile terminal. The processing unit 1001, the read-only memory 1002, and the random access memory 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 I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the image processing device of the mobile terminal to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an image processing device of a mobile terminal with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0062] 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 read-only memory 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.

[0063] The image processing device for mobile terminals provided in this application, employing the image processing method for mobile terminals in the above embodiments, can solve the technical problem that the image processing model cannot generate high-quality super-resolution images in a timely manner, making it difficult to meet the real-time processing speed requirements of mobile terminals. Compared with the prior art, the beneficial effects of the image processing device for mobile terminals provided in this application are the same as those of the image processing method for mobile terminals provided in the above embodiments, and other technical features in the image processing device for mobile terminals are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0064] 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.

[0065] 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.

[0066] 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 processing method of the mobile terminal in the above embodiments.

[0067] 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, 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, radio frequency (RF), etc., or any suitable combination thereof.

[0068] The aforementioned computer-readable storage medium may be included in the image processing device of the mobile terminal; or it may exist independently and not assembled into the image processing device of the mobile terminal.

[0069] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the image processing device of a mobile terminal, cause the image processing device of the mobile terminal to: calculate the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determine a first image block and a second image block in the image to be processed based on the energy distribution information; perform directional interpolation on the first image block through an edge-guided interpolation algorithm to obtain a first reconstructed image block; and / or perform upsampling on the second image block to obtain a second reconstructed image block; and perform fusion processing on the first reconstructed image block and the second reconstructed image block to obtain a super-resolution image.

[0070] 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++, as well as 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).

[0071] 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 instructions.

[0072] 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.

[0073] 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 image processing method of the mobile terminal described above. This solves the technical problem that image processing models cannot generate high-quality super-resolution images in a timely manner, making it difficult to meet the real-time processing speed requirements of mobile terminals. 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 processing method of the mobile terminal provided in the above embodiments, and will not be repeated here.

[0074] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An image processing method for a mobile terminal, characterized in that, The method includes the following steps: The energy distribution information of the image to be processed in the mobile terminal is calculated by using discrete cosine transform, and the first image block and the second image block in the image to be processed are determined based on the energy distribution information. The first image block is obtained by performing directional interpolation on the first image block using an edge-guided interpolation algorithm; And / or, perform an upsampling operation on the second image block to obtain a second reconstructed image block; The first reconstructed image block and the second reconstructed image block are fused to obtain a super-resolution image.

2. The method as described in claim 1, characterized in that, The step of calculating the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determining the first image block and the second image block in the image to be processed based on the energy distribution information includes: Based on the preset image block size information, the image to be processed is divided into at least two initial image blocks; Perform a discrete cosine transform on the initial image block to determine the low-frequency component energy value of the initial image block; The low-frequency component energy value is compared with a preset energy threshold to determine the first image block whose low-frequency component energy value is higher than the preset energy threshold, and the second image block whose low-frequency component energy value is lower than the preset energy threshold.

3. The method as described in claim 1, characterized in that, The step of fusing the first reconstructed image block and the second reconstructed image block to obtain a super-resolution image includes: In the first reconstructed image block and the second reconstructed image block, the region to be overlapped is determined; Based on a predefined convolution kernel, the gradient vector of the target pixel in the region to be overlapped is calculated, and the edge gradient information of the region to be overlapped is formed according to the gradient vector. Based on the edge gradient information, the Poisson equation of the region to be overlapped is solved, and the target overlapping region is generated based on the pixel values ​​corresponding to the solution results. Based on the target overlapping region, the first reconstructed image block and the second reconstructed image block are fused to obtain the super-resolution image.

4. The method as described in claim 1, characterized in that, The step of performing directional interpolation on the first image block using an edge-guided interpolation algorithm to obtain the first reconstructed image block includes: Calculate the gradient vector information of pixels within the first image block; Based on the mapping relationship between the gradient vector information and the corresponding pixel coordinates, the edge direction information of the first image block is determined; The first pixel value is calculated based on the predefined interpolation convolution kernel and the edge direction information. The first image block is generated by performing an interpolation operation on the first image block based on the first pixel value.

5. The method as described in claim 1, characterized in that, The step of performing an upsampling operation on the second image block to obtain the second reconstructed image block includes: In the second image block, obtain the neighboring pixels of the target pixel; The distance weight of the neighboring pixels is calculated using a cubic polynomial based on the relative position information between the neighboring pixels and the target pixel. Based on the distance weight, the pixel values ​​of the neighborhood pixels are weighted and summed to obtain the second pixel value; The second image block is generated by performing an interpolation operation based on the second pixel value.

6. The method as described in claim 1, characterized in that, Before the step of calculating the energy distribution information of the image to be processed in the mobile terminal through discrete cosine transform, and determining the first image block and the second image block in the image to be processed based on the energy distribution information, the method further includes: Obtain the temperature information and image processing frame rate information of the mobile terminal at the current moment; The policy controller generates a temperature adjustment factor based on the temperature information and a frame rate adjustment factor based on the frame rate information. Based on the weighted calculation results of the temperature adjustment factor and the frame rate adjustment factor, the energy threshold of the image to be processed is updated, wherein the energy threshold is used to distinguish between the first image block and the second image block.

7. The method as described in claim 6, characterized in that, Following the steps of acquiring the real-time temperature information and image processing frame rate information of the mobile terminal, the method further includes: When the temperature information is higher than the temperature threshold, the image block size information is adjusted to the target size information; And / or, when the image processing frame rate information is lower than the frame rate threshold, the first image fusion module that performs the first reconstructed image block and the second reconstructed image block fusion action is switched to the second image fusion module.

8. The method as described in claim 6, characterized in that, The steps of generating a temperature adjustment factor based on the temperature information and generating a frame rate adjustment factor based on the frame rate information via the policy controller include: The temperature factor corresponding to the temperature information is obtained through the temperature adjustment function, and the frame rate factor of the frame rate information is obtained through the frame rate adjustment function. Based on the energy distribution information, calculate the temperature weighting coefficient and the frame rate weighting coefficient; Based on the temperature weight coefficient and the frame rate weight coefficient, the temperature factor and the frame rate factor are weighted and summed to obtain the strategy score; Based on the strategy score, the temperature factor and the frame rate factor are adjusted to form the temperature adjustment factor and the frame rate adjustment factor.

9. An image processing device for a mobile terminal, characterized in that, The 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 image processing method for a mobile terminal as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the image processing method of the mobile terminal as described in any one of claims 1 to 8.