WO2017215194A1 - 一种图像处理方法及其装置、存储介质 - Google Patents

一种图像处理方法及其装置、存储介质 Download PDF

Info

Publication number
WO2017215194A1
WO2017215194A1 PCT/CN2016/107004 CN2016107004W WO2017215194A1 WO 2017215194 A1 WO2017215194 A1 WO 2017215194A1 CN 2016107004 W CN2016107004 W CN 2016107004W WO 2017215194 A1 WO2017215194 A1 WO 2017215194A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
grayscale
black
scaled
primary
Prior art date
Application number
PCT/CN2016/107004
Other languages
English (en)
French (fr)
Inventor
刘冬梅
刘凤鹏
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2017215194A1 publication Critical patent/WO2017215194A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Definitions

  • the present invention relates to the field of communications technologies, and in particular, to an image processing method, an apparatus, and a storage medium.
  • the photographing effect of the smart terminal device is improved by upgrading the existing optical device, but the method for improving the photographing effect of the smart terminal device by improving the existing optical device is limited by factors such as volume, and the cost is high, and The effect is limited.
  • a commonly used method for improving the image effect of the smart terminal device by optimizing the software algorithm generally improves the image effect only by improving the single effect and only shooting the current image by the user. The image is processed without using other reasonable resources to improve the overall quality of the image.
  • the embodiment of the present invention is to provide an image processing method, a device thereof, and a storage medium, which can improve the photographing effect of the terminal device by using resources such as a network without increasing the hardware cost.
  • an embodiment of the present invention provides an image processing method, where the method includes:
  • the original image is image-fused with the final image to obtain an improved original image.
  • the original image and the primary selected image are size-scaled to obtain a zoomed original image and a zoomed primary selected image
  • the gray value of each pixel in the grayscale image of the scaled original image is compared with the grayscale average value of all the pixels in the grayscale image of the scaled original image, and the scaled original image is Converting the grayscale image into a first black and white image;
  • the pixel gray value in the grayscale image of the scaled original image is greater than or equal to the grayscale average value of all pixels in the grayscale image of the scaled original image, the pixel is marked as the first state;
  • the pixel gray value in the grayscale image of the scaled original image is smaller than the grayscale average value of all the pixels in the grayscale image of the scaled original image, the pixel is marked as the second state.
  • the pixel gray value in the grayscale image of the zoomed primary image is greater than or equal to the grayscale average value of all the pixels in the grayscale image of the zoomed primary image, the pixel is marked as the first status;
  • the pixel gray value in the grayscale image of the scaled primary image is smaller than the grayscale average of all pixels in the grayscale image of the scaled primary image, the pixel is marked as the second state.
  • the second black and white image is The corresponding zoom image is a final image that satisfies a preset condition
  • the scaled image corresponding to the second black and white image is not satisfied Preset conditions.
  • an embodiment of the present invention further provides an image processing apparatus, where the apparatus includes:
  • the acquiring module is configured to acquire original information and location information of the original image
  • the searching module is configured to search, in the pre-stored image library, a primary selected image that is the same as the original image location information;
  • the screening module is configured to compare an image characteristic of the original image with an image characteristic of the primary selected image, and select a finalized image that meets a preset condition from the primary selected image;
  • the acquiring module is further configured to perform image fusion on the original image and the final image to obtain an improved original image.
  • the acquiring module is configured to size and scale the original image and the primary selected image to obtain a zoomed original image and a zoomed primary selected image;
  • the conversion module is configured to convert the grayscale image of the scaled original image and the grayscale image of the scaled primary image into a corresponding black and white image according to a preset policy; wherein the grayscale of the original image is scaled
  • the black and white image corresponding to the image is a first black and white image
  • the black and white image corresponding to the gray image of the zoomed primary image is a second black and white image;
  • the acquiring module is further configured to compare a first comparison value of the first black and white image with a second comparison value of the second black and white image, and obtain, from the zoomed primary selected image, a final condition that satisfies a preset condition Select an image.
  • the conversion module is configured to compare a gray value of each pixel in the grayscale image of the scaled original image with a grayscale average value of all pixels in the grayscale image of the scaled original image, Converting the grayscale image of the scaled original image into a first black and white image;
  • the zoomed primary image is converted into a second black and white image.
  • the marking module is configured to: when the pixel gray value in the grayscale image of the scaled original image is greater than or equal to the grayscale average value of all pixels in the grayscale image of the scaled original image, The pixel is marked as the first state;
  • the pixel gray value in the grayscale image of the scaled original image is smaller than the grayscale average value of all the pixels in the grayscale image of the scaled original image, the pixel is marked as the second state.
  • the marking module is configured to: when the pixel gray value in the grayscale image of the zoomed primary image is greater than or equal to the grayscale average value of all the pixels in the grayscale image of the zoomed primary image, The pixel is marked in a first state;
  • the pixel gray value in the grayscale image of the zoomed primary image is smaller than the grayscale average of all the pixels in the grayscale image of the zoomed primary image, the pixel is marked as the second state.
  • the acquiring module is configured to: when the number of bits of the first comparison value of the first black and white image and the second comparison value of the second black and white image are different from the first preset threshold,
  • the scaled image corresponding to the second black and white image is a final image that meets a preset condition
  • the scaling image corresponding to the second black and white image is not met.
  • the image processing method and device thereof and the storage medium according to the embodiments of the present invention obtain the original image and the location information by using the terminal device, and then find an image having the same position information in an image library such as a network, and perform the searched image. Further screening and obtaining the image most similar to the image acquired by the terminal device, and finally performing image fusion to obtain the image with the best effect is stored in the terminal device, fully utilizing resources such as the network, and increasing the hardware cost, so that the image captured by the terminal device
  • the advantages of combining multiple images make the camera effect of the terminal device improved.
  • FIG. 1 is a schematic flow chart of an image processing method according to Embodiment 1 of the present invention.
  • FIG. 2 is a schematic flowchart of a method for obtaining a final image according to Embodiment 1 of the present invention
  • Embodiment 3 is a grayscale image after gradation transformation of a color image according to Embodiment 1 of the present invention.
  • FIG. 5 is a schematic flow chart of a method for converting a grayscale image into a black and white image according to Embodiment 1 of the present invention
  • FIG. 6 is a schematic structural diagram of an image processing apparatus according to Embodiment 2 of the present invention.
  • the basic idea of the embodiment of the present invention is: in the terminal device, the terminal device is first used by itself. Configuration, open the positioning function, and then take photos with the terminal device. Then, the photographs are initially screened out from the network according to the positioning information to reduce the subsequent workload, and then the desired high-quality images are further obtained from the images initially screened by the network, and finally the obtained high-quality images are merged with the original images. , get better image data, and finally achieve a greater improvement in the camera photo effect.
  • an embodiment of the present invention provides an image processing method, which may include:
  • the terminal device having the photographing function is used to take a photograph to obtain an original image.
  • the positioning function of the terminal device such as the GPS positioning function, is opened before the photographing, and the position information of the original image is acquired while taking the photograph.
  • the location information of the original image may be latitude and longitude coordinates or a specific place name or the like.
  • the positioning function is used to acquire the location information of the original image capturing location for acquiring the same image as the original image location information.
  • the pre-stored image library may be an image that is found from the network.
  • the user can connect to the network through the terminal device and search for the same image from the network as the location information of the original image. It is also possible to directly search for an image of the same location information on the network by using the original image location information in the background, and the primary image is obtained by the above method.
  • the pre-stored image library may also be an image with location information stored in a storage function device such as a server, a cloud disk, a personal computer, or a mobile hard disk.
  • the acquired primary images can be stored in a specific server. For example, from the network The primary image is obtained. Considering the limitation of the storage space of the terminal device, the primary image obtained from the network can be stored in a specific server for further screening and comparison with the original image.
  • the image characteristics of the original image are compared with the image characteristics of the primary image to obtain a final image that satisfies a preset condition.
  • the original image and the primary selected image are both colored images, and the image characteristics are utilized.
  • the original image and the primary selected image are firstly scaled, and then the scaled original image and the primary selected image are converted.
  • the grayscale image is converted into a corresponding black and white image, and finally the corresponding black and white image is analyzed to obtain an image satisfying the preset condition.
  • the image that satisfies the preset condition refers to an image that is further filtered from the primary image and that is closest to the original image.
  • step S103 may include: S1031 to S1034:
  • S1013 Scaling the original image and the primary selected image to obtain a zoomed original image and a zoomed primary selected image.
  • most of the current image ratio is 4:3, the statistics of the integrated information and the speed of the search, and the original image captured by the terminal device and the primary image obtained from the pre-stored image library are uniformly scaled to 16 ⁇ 12 size image, a 16 ⁇ 12 size image consisting of 192 Pixel composition.
  • the original image taken by the scaled terminal device here and the primary image obtained from the pre-stored image library are still color images.
  • S1032 Perform gradation transformation on the scaled original image and the scaled primary image to obtain a grayscale image of the scaled original image and a grayscale image of the scaled primary image.
  • each image will obtain 192 gray values.
  • each pixel in the color image is composed of three primary colors of red, green, and blue, directly processing the color image increases computational complexity, so the color image is first converted into a grayscale image.
  • the color image can be converted into a grayscale image by the following five methods:
  • Gray (R ⁇ 30+G ⁇ 59+B ⁇ 11)/100
  • the above operator >> represents a right shift operation, a right shift of one bit corresponds to division by 2, and a right shift of n bits corresponds to division by 2 nth power. Since the shift algorithm does not use a direct division process, the algorithm is faster than the integer algorithm. Here, shifting 8 bits to the right is equivalent to dividing the floating-point operation by the 8th power of 2. Therefore, it is necessary to multiply the coefficient of the floating-point algorithm by the 8th power of 2 to maintain the result of the original floating-point operation.
  • the above example uses a coefficient of 8-bit precision, multiplying the coefficients of the floating-point algorithm by the power of 8 of 2, which is 256.
  • the shift algorithm can be obtained by the floating point algorithm by the above transformation, wherein the shift algorithm is preferable to the 8-bit precision and the coefficient of 2 to 20-bit precision.
  • R, G, and B in the original RGB (R, G, B) are uniformly replaced by Gray to form a new color space RGB (Gray, Gray, Gray).
  • Figure 3 shows the color image. Grayscale image obtained after gradation transformation.
  • the method of converting the above color image into a grayscale image is applied to the scaled original image and the scaled primary image to obtain a grayscale image corresponding to the scaled original image and the scaled primary image.
  • the black and white image corresponding to the grayscale image of the scaled original image is a first black and white image
  • the black and white image corresponding to the grayscale image of the zoomed primary image is a second black and white image
  • FIG. 4 is an image obtained by converting the grayscale image shown in FIG. 3 into a black and white image.
  • step S1033 includes S10331 and S10332:
  • step S10331 includes:
  • the pixel gray value in the grayscale image of the scaled original image is greater than or equal to the grayscale average of all the pixels in the grayscale image of the scaled original image, the pixel is marked as the first state.
  • the pixel gray value in the grayscale image of the scaled original image is smaller than the grayscale average value of all the pixels in the grayscale image of the scaled original image, the pixel is marked as the second state.
  • the first state is represented by “1”
  • the second state is represented by "0”
  • the black color is represented by "0”
  • the white color is represented by "1” whereby the grayscale image of the original image is converted into a binary first black and white image.
  • step S10332 includes:
  • the pixel gray value in the grayscale image of the scaled primary image is greater than or equal to the grayscale average of all pixels in the grayscale image of the zoomed primary image, the pixel is marked as the first state.
  • the pixel gray value in the grayscale image of the scaled primary image is smaller than the grayscale average of all pixels in the grayscale image of the scaled primary image, the pixel is marked as the second state.
  • the grayscale image of the zoomed primary image is converted into the binary second black and white image.
  • the black and white outlines should be similar, by comparing the second ratio of the first alignment value of the first black and white image of the original image to the second black and white image of the zoomed primary image. For the value, you can get a final image that meets the preset conditions.
  • the grayscale image of the original image After scaling the grayscale image of the original image to obtain the binary first black and white image, it is recorded as a hexadecimal first alignment value.
  • the gray image obtained by scaling the primary image is obtained by two After the second black and white image is encoded, it is recorded as a hexadecimal second alignment value.
  • the first alignment value and the second alignment value are used to compare the first black and white image of the scaled original image with the second black and white image of the scaled primary image to determine a first black and white image of the scaled original image and a zoom primary The similarity of the second black and white image of the image.
  • step S1034 includes:
  • a zoom image corresponding to the second black and white image when a number of bits different from a first alignment value of the first black and white image and a second alignment value of the second black and white image is less than or equal to a first preset threshold A final image to meet the preset conditions.
  • the scaled image corresponding to the second black and white image is not satisfied Preset conditions.
  • the first preset threshold may be set to 10.
  • the original image is similar to the primary image when the first alignment value of the first black and white image of the original image is different from the second alignment value of the second black and white image of the zoomed primary image by 10 or less. Selecting the primary selected image as a final image; when the first alignment value of the first black and white image of the original image is scaled, the second alignment value of the second black and white image of the zoomed primary image is different from the number of digits greater than 10
  • the primary image is not selected as the terminal image.
  • the number of acquired terminal images that satisfy the preset condition may be one or several.
  • S104 Image fusion of the original image and the final image that meets a preset condition to obtain an improved original image.
  • the original image captured by the terminal device is merged with one or several final images selected from the pre-stored image library to obtain an improved original image, and the image is obtained. Stored in the terminal device.
  • image fusion The purpose of image fusion is to synthesize information of multiple images of the same scene, and the result is more suitable.
  • image fusion algorithms including pixel-level image fusion method, weighted average method and wavelet transform method.
  • Image-level image fusion is the lowest level of image fusion, but this level has the highest fusion accuracy and can provide other levels. Integrate details that are not available. Since the current algorithm is mature, it will not be detailed here.
  • An embodiment of the present invention provides an image processing method, which uses a terminal device to acquire an original image and its location information, and then finds an image having the same location information in an image library such as a network, and further filters the found image to obtain a terminal.
  • the image with the most approximate image acquired by the device is finally stored in the terminal device by image fusion, and the resources such as the network are fully utilized, and the hardware cost is increased, so that the image captured by the terminal device is combined with multiple images.
  • the advantage of the terminal device is improved.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to execute the image processing method according to the first embodiment of the present invention.
  • an embodiment of the present invention provides an image processing apparatus, where the apparatus includes: an obtaining module 601, a searching module 602, and a screening module 603;
  • the acquiring module 601 is configured to acquire original information and location information of the original image
  • the searching module 602 is configured to search, in the pre-stored image library, a primary selected image that is the same as the original image location information;
  • the screening module 603 is configured to compare an image characteristic of the original image with an image characteristic of the primary selected image, and select a finalized image that meets a preset condition from the primary selected image;
  • the acquiring module 601 is further configured to perform image fusion on the original image and the final image to obtain an improved original image.
  • the device further includes: a conversion module 604;
  • the acquiring module 601 is configured to size and scale the original image and the primary selected image to obtain a zoomed original image and a zoomed primary selected image;
  • the conversion module 604 is configured to convert the grayscale image of the scaled original image and the grayscale image of the scaled primary image into a corresponding black and white image according to a preset policy; wherein the gray of the original image is scaled
  • the black and white image corresponding to the degree image is a first black and white image
  • the black and white image corresponding to the gray image of the zoomed primary image is a second black and white image;
  • the obtaining module 601 is further configured to compare a first comparison value of the first black and white image with a second comparison value of the second black and white image, and obtain a preset condition from the zoomed primary selected image. Final image.
  • the conversion module 604 is configured to compare a gray value of each pixel in the grayscale image of the scaled original image with a grayscale average value of all pixels in the grayscale image of the scaled original image, Converting the grayscale image of the scaled original image into a first black and white image;
  • the zoomed primary image is converted into a second black and white image.
  • the device further includes: a marking module 605;
  • the marking module 605 is configured to mark the pixel as a grayscale average value of all pixels in the grayscale image of the scaled original image when the grayscale image of the scaled image of the original image is greater than or equal to First state
  • the pixel gray value in the grayscale image of the scaled original image is smaller than the grayscale average value of all the pixels in the grayscale image of the scaled original image, the pixel is marked as the second state.
  • the marking module 605 is configured to: when the pixel gray value in the grayscale image of the zoomed primary image is greater than or equal to the grayscale average value of all the pixels in the grayscale image of the zoomed primary image, The pixel is marked in a first state;
  • the pixel gray value in the grayscale image of the zoomed primary image is smaller than the grayscale average of all the pixels in the grayscale image of the zoomed primary image, the pixel is marked as the second state.
  • the acquiring module 601 is configured to: when the number of bits of the first comparison value of the first black and white image and the second comparison value of the second black and white image are different from the first preset threshold, The scaled image corresponding to the second black and white image is a final image that meets a preset condition;
  • the scaling image corresponding to the second black and white image is not met.
  • the obtaining module 601, the searching module 602, the screening module 603, the converting module 604, and the marking module 605 may each be a central processing unit (CPU) and a microprocessor located in the image processing device 6.
  • CPU central processing unit
  • MPU Micro Processor Unit
  • DSP Digital Signal Processor
  • FPGA Field Programmable Gate Array
  • An embodiment of the present invention provides an image processing apparatus, which uses an end device to acquire an original image and position information thereof, and then finds an image having the same position information in an image library such as a network, and further filters the searched image to obtain a terminal.
  • the image with the most approximate image acquired by the device is finally stored in the terminal device by image fusion, and the resources such as the network are fully utilized, and the hardware cost is increased, so that the image captured by the terminal device is combined with multiple images.
  • the advantage of the terminal device is improved.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • the original image and the location information thereof are obtained by using the terminal device, and then the image with the same location information in the image library such as the network is searched, and the searched image is further filtered to obtain the image that is most similar to the image acquired by the terminal device.
  • the image is finally image-fused to obtain the image with the best effect and stored in the terminal device, making full use of resources such as the network, without the increase of hardware cost, so that the image captured by the terminal device combines the advantages of multiple images, so that the terminal device takes photos. Improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Image Processing (AREA)

Abstract

本发明实施例公开了一种图像处理方法，所述方法包括：获取原始图像及所述原始图像的位置信息；在预存储图像库中查找与所述原始图像位置信息相同的初选图像；将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。本发明实施例同时还公开了一种图像处理装置及存储介质。

Description

一种图像处理方法及其装置、存储介质 技术领域
本发明涉及通信技术领域，尤其涉及一种图像处理方法及其装置、存储介质。
背景技术
随着网络与各种智能终端设备的普及，利用手机、平板电脑等智能终端设备拍照已经成为用户最常用的获取图像的手段。智能终端设备不断更新，拍照的功能也随之不断更新，在拍照功能推陈出新的同时，如何合理整合资源，提升拍照的效果成为了最核心的关键点。
现有技术中，通过提升现有光学设备来改善智能终端设备的拍照效果，但是受体积等因素的限制，通过改进现有光学设备来提升智能终端设备的拍照效果的方法，成本较高，并且效果是有限的。另外，常用的通过对软件算法的优化对智能终端设备所拍摄的图像效果进行提升的方法，其对图像效果的提升一般只能对单一的效果进行改进，并且仅通过算法对用户当前所拍摄的图像进行处理，没有利用其他合理资源对图像综合质量进行提升。
发明内容
为解决上述技术问题，本发明实施例期望提供一种图像处理方法及其装置、存储介质，不增加硬件成本的同时，利用网络等资源使终端设备拍照效果得到提升。
本发明实施例的技术方案是这样实现的：
第一方面，本发明实施例提供了一种图像处理方法，所述方法包括：
获取原始图像及所述原始图像的位置信息；
在预存储图像库中查找与所述原始图像位置信息相同的初选图像；
将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；
将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。
上述方案中，将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像；
将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像；
根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像；其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
上述方案中，将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像；
将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
上述方案中，当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
上述方案中，当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
上述方案中，当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像；
当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
第二方面，本发明实施例还提供了一种图像处理装置，所述装置包括：
所述获取模块，配置为获取原始图像及所述原始图像的位置信息；
所述查找模块，配置为在预存储图像库中查找与所述原始图像位置信息相同的初选图像；
所述筛选模块，配置为将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；
所述获取模块，还配置为将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。
上述方案中，所述获取模块，配置为将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像；
以及，将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像；
所述转换模块，配置为根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像；其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
所述获取模块，还配置为将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
上述方案中，所述转换模块，配置为将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像；
以及，将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
上述方案中，所述标记模块，配置为当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
以及，当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
上述方案中，所述标记模块，配置为当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
以及，当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
上述方案中，所述获取模块，配置为当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像；
以及，当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
本发明实施例所述的图像处理方法及其装置、存储介质，利用终端设备获取到原始图像及其位置信息，然后查找到网络等图像库中具有相同位置信息的图像，对查找到的图像进行进一步筛选得到与终端设备获取到的图像最为近似的图像，最后进行图像融合得到效果最优的图像存入终端设备，充分利用了网络等资源，无硬件成本的增加，使得终端设备拍摄到的图像融合了多幅图像的优点，使得终端设备拍照效果得到提高。
附图说明
图1为发明实施例一提供的图像处理方法流程示意图；
图2为发明实施例一提供的获取终选图像的方法流程示意图；
图3为发明实施例一提供的将彩色图像经过灰度变换后的灰度图像；
图4为发明实施例一提供的将灰度图像经过转换后的黑白图像；
图5为发明实施例一提供的将灰度图像转换成黑白图像的方法流程示意图；
图6为发明实施例二提供的图像处理装置结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。
本发明实施例的基本思想是：在终端设备中，首先利用终端设备自有 的配置，打开定位功能，之后用终端设备进行拍照。然后将所拍照片按照定位信息从网络初步筛选出图像以减少后续工作量，之后从网络初步筛选出的图像中再进一步得到所需的优质图像，最后利用获取到的优质图像与原始图像进行融合，得到更好的图像数据，最终实现摄像头拍照效果的较大提升。
实施例一
参见图1，其示出了本发明实施例提供一种图像处理方法，所述方法可以包括：
S101、获取原始图像及所述原始图像的位置信息。
具体的，使用具有拍照功能的终端设备进行拍照，获取原始图像。在拍照之前打开终端设备的定位功能，如GPS定位功能，在拍照的同时获取到拍摄原始图像的位置信息。所述原始图像的位置信息可以是经纬度坐标或具体地点名称等。
利用定位功能获取原始图像拍摄地点具体的位置信息用于获取与原始图像位置信息相同的图像。
S102、在预存储图像库中查找与所述原始图像位置信息相同的初选图像。
优选的，预存储的图像库可以是从网络查找到的的图像。用户可以通过终端设备连接网络，从网络搜索与拍摄原始图像的位置信息相同的图像。也可以通过后台直接利用原始图像位置信息在网络搜索出相同位置信息的图像，通过上述方法得到的即为初选图像。其中，预存储的图像库还可以是服务器、云盘、个人电脑、移动硬盘等具有存储功能的设备中存储的带有位置信息的图像。
可以将所获取到的初选图像储存在具体的服务器中。例如，从网络获 取到了初选图像，考虑到终端设备存储空间的限制，可以将从网络获取到的初选图像储存在具体的服务器中，以便与原始图像做进一步筛选与比对。
S103、将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像。
利用所述原始图像的图像特性与所述初选图像的图像特性进行对比，用以获取满足预设条件的终选图像。
需要说明的是，获取到原始图像与初选图像后，需要利用图像特性对原始图像与初选图像进行一个对比，进行进一步的筛选。进一步筛选的目的是为了选取与原始图像所拍摄的图像最接近的图像。
原始图像与初选图像均为彩色的图像，对图像特性的利用，本发明实施例是通过将原始图像与初选图像先进行尺寸缩放，然后将经过尺寸缩放后的原始图像与初选图像转换成灰度图，再将所述的灰度图转换成相对应的黑白图，最后对相对应的黑白图进行分析，获取满足预设条件的图像。
这里，满足预设条件的图像是指从初选图像中进一步筛选出的与原始图像最接近的图像。
具体的，参见图2，步骤S103可以包括：S1031至S1034：
S1031、将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像。
为了兼容不同尺寸的图像，首先需要对终端设备拍摄的原始图像与从预存储图像库中获取到的初选图像进行尺寸缩放，将上述图像缩放至统一的尺寸。
优选的，目前大部分的图像比例为4:3，综合信息的统计量以及搜索的速度等因素，将终端设备所拍摄的原始图像与从预存储图像库中获取到的初选图像统一缩放到16×12大小的图像，一个16×12大小的图像由192个 像素组成。
这里经过缩放的终端设备所拍摄的原始图像和从与预存储图像库中获取到的初选图像仍然是彩色图像。
S1032、将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像。
需要说明的是，对原始图像与初选图像的每一个像素进行灰度变换，则每一幅图像都会得到192个灰度值。
由于彩色图像中每一个像素都是由红、绿、蓝三原色组成的颜色，直接对彩色图像进行处理会增加计算复杂度，因此先将彩色图像转换成灰度图像。
假设彩色图像中某一个像素点的颜色为RGB(R，G，B)，那么，可以通过以下五种方法将彩色图像转换成灰度图像：
1、浮点算法：Gray＝R×0.3+G×0.59+B×0.11；
2、整数算法：Gray＝(R×30+G×59+B×11)/100；
3、移位算法：Gray＝(R×76+G×151+B×28)＞＞8；
4、平均值法：Gray＝(R+G+B)/3；
5、仅取绿色：Gray＝G。
需要说明的是，上述运算符＞＞表示右移运算，右移一位相当于除以2，右移n位相当于除以2的n次方。移位算法由于没有采用直接的除法过程，算法速度比整数算法快。这里采用右移8位，相当于将浮点运算除以了2的8次方，因此，需要将浮点算法的系数乘以2的8次方来保持原浮点运算的结果。上述示例采用的是8位精度的系数，将浮点算法的系数分别乘以2的8次幂，即256。
上述浮点算法中三个系数分别乘以256后，系数变换为：
0.3×256＝76.8≈76；0.59×256＝151.04≈151；0.11×256＝28.16≈28
通过上述变换就可以由浮点算法得到移位算法，其中，移位算法除了8位精度，2至20位精度的系数都是可取的。
通过上述任一种方法求得Gray后，将原来的RGB(R，G，B)中的R，G，B统一用Gray替换，形成新的颜色空间RGB(Gray，Gray，Gray)。用新的颜色空间RGB(Gray，Gray，Gray)将原来的RGB(R，G，B)替换，原来的彩色图就变成了灰度图，如图3所示，图3为彩色图像经过灰度变换后得到的灰度图像。
将上述彩色图像转换成灰度图像的方法应用于经过尺寸缩放后的缩放原始图像与缩放初选图像，得到缩放原始图像与缩放初选图像所对应的灰度图像。
S1033、根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像。
其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
需要说明的是，对缩放原始图像与缩放初选图像需要分别进行黑白图像的转换，如图4所示，图4为将图3所示的灰度图转换成黑白图后的图像。
具体的，参见图5，步骤S1033包括S10331和S10332：
S10331、将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像。
具体的，步骤S10331包括：
当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态。
当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
在本发明实施例中，所述第一状态用“1”表示，所述第二状态用“0”表示。用“0”表示黑色，用“1”表示白色，由此，缩放原始图像的灰度图像就转换成了一个二进制的第一黑白图像。
S10332、将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
具体的，步骤S10332包括：
当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态。
当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
可以理解地，与上述缩放原始图像的灰度图像转换成第一黑白图像的方法相同，将缩放初选图像的灰度图像转换成二进制的第二黑白图像。
S1034、将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
需要说明的是，如果两张图片很相似，其黑白轮廓应该是相近的，通过比较缩放原始图像的第一黑白图像的第一比对值与缩放初选图像的第二黑白图像的第二比对值，可以获取满足预设条件的终选图像。
缩放原始图像的灰度图像得到二进制的第一黑白图像后，将其记录为一个十六进制的第一比对值。同样的，缩放初选图像的灰度图像得到的二 进制第二黑白图像后，将其记录为一个十六进制的第二比对值。
上述第一比对值与第二比对值用于将缩放原始图像的第一黑白图像与缩放初选图像的第二黑白图像进行对比，以确定缩放原始图像的第一黑白图像与缩放初选图像的第二黑白图像的相似性。
具体的，步骤S1034包括：
当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像。
当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
优选的，第一预设阈值可以设为10。当缩放原始图像的第一黑白图像的第一比对值与缩放初选图像的第二黑白图像的第二比对值不相同的位数小于等于10时，说明原始图像与初选图像很相似，将该初选图像选择为终选图像；当缩放原始图像的第一黑白图像的第一比对值与缩放初选图像的第二黑白图像的第二比对值不相同的位数大于10时，说明原始图像与初选图像相似度不高，不选择该初选图像为终端图像。这里，获取的满足预设条件的终端图像数量有可能是一幅也有可能是几幅。
S104、将所述原始图像与所述满足预设条件的终选图像进行图像融合，获取改善后的原始图像。
需要说明的是，将终端设备所拍摄到的原始图像与从预存储的图像库中筛选出的一幅或几幅终选图像进行图像融合，得到一幅改善后的原始图像，并将该图像储存在终端设备中。
图像融合的目的是综合同一个场景的多个图像的信息，其结果是更适 合人的视觉和计算机视觉的一幅图像。目前图像融合算法比较多，包括像素级图像融合方法、加权平均法以及小波变换法，其中像素级的图像融合是最低层次的图像融合，但该层次的融合准确性最高，能够提供其他层次上的融合所不具备的细节信息。由于目前算法比较成熟在此就不再做详述。
本发明实施例提供了一种图像处理方法，利用终端设备获取到原始图像及其位置信息，然后查找到网络等图像库中具有相同位置信息的图像，对查找到的图像进行进一步筛选得到与终端设备获取到的图像最为近似的图像，最后进行图像融合得到效果最优的图像存入终端设备，充分利用了网络等资源，无硬件成本的增加，使得终端设备拍摄到的图像融合了多幅图像的优点，使得终端设备拍照效果得到提高。
本发明实施例还提供了一种计算机存储介质，所述计算机存储介质中存储有计算机程序，所述计算机程序用于执行本发明实施例中实施例一所述的图像处理方法。
实施例二
参见图6，其示出了本发明实施例提供一种图像处理装置，所述装置包括：获取模块601、查找模块602和筛选模块603；其中,
所述获取模块601，配置为获取原始图像及所述原始图像的位置信息；
所述查找模块602，配置为在预存储图像库中查找与所述原始图像位置信息相同的初选图像；
所述筛选模块603，配置为将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；
所述获取模块601，还配置为将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。
进一步地，所述装置还包括：转换模块604；
所述获取模块601，配置为将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像；
以及，将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像；
所述转换模块604，配置为根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像；其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
所述获取模块601，还配置为将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
进一步地，所述转换模块604，配置为将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像；
以及，将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
进一步地，所述装置还包括：标记模块605；
所述标记模块605，配置为当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
以及，当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
进一步地，所述标记模块605，配置为当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
以及，当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
进一步地，所述获取模块601，配置为当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像；
以及，当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
具体的，本发明实施例提供的图像处理装置的说明可以参考实施例一的图像处理方法的说明，本发明实施例在此不再赘述。
在实际应用中，所述获取模块601、查找模块602、筛选模块603、转换模块604和标记模块605均可由位于图像处理装置6中的中央处理器(Central Processing Unit，CPU)、微处理器(Micro Processor Unit，MPU)、数字信号处理器(Digital Signal Processor，DSP)、或现场可编程门阵列(Field Programmable Gate Array，FPGA)等实现。
本发明实施例提供了一种图像处理装置，利用终端设备获取到原始图像及其位置信息，然后查找到网络等图像库中具有相同位置信息的图像，对查找到的图像进行进一步筛选得到与终端设备获取到的图像最为近似的图像，最后进行图像融合得到效果最优的图像存入终端设备，充分利用了网络等资源，无硬件成本的增加，使得终端设备拍摄到的图像融合了多幅图像的优点，使得终端设备拍照效果得到提高。
本领域内的技术人员应明白，本发明的实施例可提供为方法、***、或计算机程序产品。因此，本发明可采用硬件实施例、软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述，仅为本发明的较佳实施例而已，并非用于限定本发明的保护范围。
工业实用性
本发明实施例利用终端设备获取到原始图像及其位置信息，然后查找到网络等图像库中具有相同位置信息的图像，对查找到的图像进行进一步筛选得到与终端设备获取到的图像最为近似的图像，最后进行图像融合得到效果最优的图像存入终端设备，充分利用了网络等资源，无硬件成本的增加，使得终端设备拍摄到的图像融合了多幅图像的优点，使得终端设备拍照效果得到提高。

Claims (13)

  1. 一种图像处理方法，所述方法包括：
    获取原始图像及所述原始图像的位置信息；
    在预存储图像库中查找与所述原始图像位置信息相同的初选图像；
    将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；
    将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。
  2. 根据权利要求1所述的方法，其中，所述将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像，包括：
    将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像；
    将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像；
    根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像；其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
    将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
  3. 根据权利要求2所述的方法，其中，所述根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像，包括：
    将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原 始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像；
    将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
  4. 根据权利要求3所述的方法，其中，所述将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像，包括：
    当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
    当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
  5. 根据权利要求3所述的方法，其中，所述将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像，包括：
    当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
    当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
  6. 根据权利要求2所述的方法，其中，所述将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像，包括：
    当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相 同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像；
    当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
  7. 一种图像处理装置，包括：获取模块、查找模块和筛选模块；其中
    所述获取模块，配置为获取原始图像及所述原始图像的位置信息；
    所述查找模块，配置为在预存储图像库中查找与所述原始图像位置信息相同的初选图像；
    所述筛选模块，配置为将所述原始图像的图像特性与所述初选图像的图像特性进行对比，从所述初选图像中筛选出满足预设条件的终选图像；
    所述获取模块，还配置为将所述原始图像与所述终选图像进行图像融合，获取改善后的原始图像。
  8. 根据权利要求7所述的装置，其中，所述装置还包括：转换模块；
    所述获取模块，配置为将所述原始图像与所述初选图像进行尺寸缩放，获取缩放原始图像与缩放初选图像；
    以及，将所述缩放原始图像与所述缩放初选图像进行灰度变换，得到所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像；
    所述转换模块，配置为根据预设策略，将所述缩放原始图像的灰度图像与所述缩放初选图像的灰度图像转换为对应的黑白图像；其中，所述缩放原始图像的灰度图像对应的黑白图像为第一黑白图像，所述缩放初选图像的灰度图像对应的黑白图像为第二黑白图像；
    所述获取模块，还配置为将所述第一黑白图像的第一比对值与第二黑白图像的第二比对值进行对比，从所述缩放初选图像中获取满足预设条件的终选图像。
  9. 根据权利要求8所述的装置，其中，
    所述转换模块，配置为将所述缩放原始图像的灰度图像中每一个像素的灰度值与所述缩放原始图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放原始图像的灰度图像转换成第一黑白图像；
    以及，将所述缩放初选图像的灰度图像中每一个像素的灰度值与所述缩放初选图像的灰度图像中所有像素的灰度平均值进行对比，将所述缩放初选图像的灰度图像转换成第二黑白图像。
  10. 根据权利要求9所述的装置，其中，所述装置还包括：标记模块；
    所述标记模块，配置为当所述缩放原始图像的灰度图像中像素灰度值大于等于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
    以及，当所述缩放原始图像的灰度图像中像素灰度值小于所述缩放原始图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
  11. 根据权利要求9所述的装置，其中，
    所述标记模块，配置为当所述缩放初选图像的灰度图像中像素灰度值大于等于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第一状态；
    以及，当所述缩放初选图像的灰度图像中像素灰度值小于所述缩放初选图像的灰度图像中所有像素的灰度平均值时，将所述像素标记为第二状态。
  12. 根据权利要求8所述的装置，其中，
    所述获取模块，配置为当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数小于等于第一预设阈值时，与所述第二黑白图像相对应的缩放图像为满足预设条件的终选图像；
    以及，当所述第一黑白图像的第一比对值与第二黑白图像的第二比对值不相同的位数大于第一预设阈值时，所述第二黑白图像相对应的缩放图像不满足预设条件。
  13. 一种计算机存储介质，所述计算机存储介质中存储有计算机程序，所述计算机程序用于执行前述权利要求1至6任一项所述的图像处理方法。
PCT/CN2016/107004 2016-06-14 2016-11-23 一种图像处理方法及其装置、存储介质 WO2017215194A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610414797.9A CN107507158A (zh) 2016-06-14 2016-06-14 一种图像处理方法和装置
CN201610414797.9 2016-06-14

Publications (1)

Publication Number Publication Date
WO2017215194A1 true WO2017215194A1 (zh) 2017-12-21

Family

ID=60663436

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/107004 WO2017215194A1 (zh) 2016-06-14 2016-11-23 一种图像处理方法及其装置、存储介质

Country Status (2)

Country Link
CN (1) CN107507158A (zh)
WO (1) WO2017215194A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473249A (zh) * 2019-07-12 2019-11-19 平安普惠企业管理有限公司 一种网页用户界面与设计稿的对比方法、装置及终端设备
CN110648340A (zh) * 2019-09-29 2020-01-03 惠州学院 一种基于二进制及水平集处理图像的方法及装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112532856B (zh) * 2019-09-17 2023-10-17 中兴通讯股份有限公司 一种拍摄方法、装置和***
WO2021115483A1 (zh) * 2019-12-13 2021-06-17 华为技术有限公司 一种图像处理方法及相关装置
CN114697543B (zh) * 2020-12-31 2023-05-19 华为技术有限公司 一种图像重建方法、相关装置及***

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070271256A1 (en) * 2006-05-16 2007-11-22 Shih-Fu Chang Active context-based concept fusion
CN101566994A (zh) * 2008-04-22 2009-10-28 王磊 一种图像、视频检索方法
CN102915326A (zh) * 2012-08-30 2013-02-06 杭州藕根科技有限公司 一种基于gps和图像搜索技术的移动终端景物辨识***
CN103440318A (zh) * 2013-08-29 2013-12-11 王靖洲 移动终端的景观识别***
CN103514265A (zh) * 2013-09-04 2014-01-15 一派视觉（北京）数字科技有限公司 全景交互数字增强体验式智慧旅游***和方法
CN104537608A (zh) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 一种图像处理的方法及其装置
CN105046676A (zh) * 2015-08-27 2015-11-11 上海斐讯数据通信技术有限公司 一种基于智能终端的图像融合方法及设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070271256A1 (en) * 2006-05-16 2007-11-22 Shih-Fu Chang Active context-based concept fusion
CN101566994A (zh) * 2008-04-22 2009-10-28 王磊 一种图像、视频检索方法
CN102915326A (zh) * 2012-08-30 2013-02-06 杭州藕根科技有限公司 一种基于gps和图像搜索技术的移动终端景物辨识***
CN103440318A (zh) * 2013-08-29 2013-12-11 王靖洲 移动终端的景观识别***
CN103514265A (zh) * 2013-09-04 2014-01-15 一派视觉（北京）数字科技有限公司 全景交互数字增强体验式智慧旅游***和方法
CN104537608A (zh) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 一种图像处理的方法及其装置
CN105046676A (zh) * 2015-08-27 2015-11-11 上海斐讯数据通信技术有限公司 一种基于智能终端的图像融合方法及设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473249A (zh) * 2019-07-12 2019-11-19 平安普惠企业管理有限公司 一种网页用户界面与设计稿的对比方法、装置及终端设备
CN110648340A (zh) * 2019-09-29 2020-01-03 惠州学院 一种基于二进制及水平集处理图像的方法及装置
CN110648340B (zh) * 2019-09-29 2023-03-17 惠州学院 一种基于二进制及水平集处理图像的方法及装置

Also Published As

Publication number Publication date
CN107507158A (zh) 2017-12-22

Similar Documents

Publication Publication Date Title
WO2017215194A1 (zh) 一种图像处理方法及其装置、存储介质
US20220222786A1 (en) Image processing method, smart device, and computer readable storage medium
TWI624182B (zh) 高動態範圍影像的編碼、解碼及表示
JP4706415B2 (ja) 撮像装置、画像記録装置およびプログラム
WO2018082185A1 (zh) 图像处理方法和装置
US20220189029A1 (en) Semantic refinement of image regions
TW202008313A (zh) 圖像打光方法和裝置
US20130222645A1 (en) Multi frame image processing apparatus
CN111131688B (zh) 一种图像处理方法、装置及移动终端
CN113810641B (zh) 视频处理方法、装置、电子设备和存储介质
WO2014187265A1 (zh) 一种照片拍摄处理方法、设备和计算机存储介质
CN113518210A (zh) 图像自动白平衡的方法及装置
US8995784B2 (en) Structure descriptors for image processing
Nam et al. Modelling the scene dependent imaging in cameras with a deep neural network
CN107038695A (zh) 一种图像融合方法及移动设备
WO2023151511A1 (zh) 模型训练方法、图像去摩尔纹方法、装置及电子设备
Liu et al. Progressive complex illumination image appearance transfer based on CNN
CN114723610A (zh) 图像智能处理方法、装置、设备及存储介质
CN114449199B (zh) 视频处理方法、装置、电子设备和存储介质
JP6977483B2 (ja) 画像処理装置、画像処理方法、画像処理システムおよびプログラム
WO2024067461A1 (zh) 图像处理方法、装置、计算机设备和存储介质
CN111383289A (zh) 图像处理方法、装置、终端设备及计算机可读存储介质
WO2017101570A1 (zh) 照片的处理方法及处理***
US10026201B2 (en) Image classifying method and image displaying method
KR20140138046A (ko) 픽처를 처리하기 위한 방법 및 디바이스

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16905306

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16905306

Country of ref document: EP

Kind code of ref document: A1