WO2016155536A1 - 生成合成图片的方法及装置 - Google Patents

生成合成图片的方法及装置 Download PDF

Info

Publication number
WO2016155536A1
WO2016155536A1 PCT/CN2016/076950 CN2016076950W WO2016155536A1 WO 2016155536 A1 WO2016155536 A1 WO 2016155536A1 CN 2016076950 W CN2016076950 W CN 2016076950W WO 2016155536 A1 WO2016155536 A1 WO 2016155536A1
Authority
WO
WIPO (PCT)
Prior art keywords
sub
foreground
display
area
curve
Prior art date
Application number
PCT/CN2016/076950
Other languages
English (en)
French (fr)
Inventor
张宇
杜志军
王楠
丁威
何强
Original Assignee
阿里巴巴集团控股有限公司
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
Priority to JP2017551134A priority Critical patent/JP6768695B2/ja
Priority to SG11201707783VA priority patent/SG11201707783VA/en
Priority to KR1020177031276A priority patent/KR102107887B1/ko
Priority to KR1020207009637A priority patent/KR102215766B1/ko
Priority to PL19205490T priority patent/PL3618003T3/pl
Priority to EP16771291.8A priority patent/EP3279866B1/en
Application filed by 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Priority to ES16771291T priority patent/ES2819868T3/es
Priority to EP19205490.6A priority patent/EP3618003B1/en
Priority to PL16771291T priority patent/PL3279866T3/pl
Publication of WO2016155536A1 publication Critical patent/WO2016155536A1/zh
Priority to US15/716,332 priority patent/US10692261B2/en
Priority to US16/749,060 priority patent/US10878609B2/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/002D [Two Dimensional] image generation
    • G06T11/60Editing figures and text; Combining figures or text
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/103Formatting, i.e. changing of presentation of documents
    • G06F40/106Display of layout of documents; Previewing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/166Editing, e.g. inserting or deleting
    • G06F40/186Templates
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/002D [Two Dimensional] image generation
    • G06T11/20Drawing from basic elements, e.g. lines or circles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/02Affine transformations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/194Segmentation; Edge detection involving foreground-background segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/002D [Two Dimensional] image generation
    • G06T11/001Texturing; Colouring; Generation of texture or colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20212Image combination
    • G06T2207/20221Image fusion; Image merging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators

Definitions

  • the present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for generating a composite picture.
  • Internet-based promotions often take the form of displaying or spreading images on web pages, social platforms. Always using the same picture is likely to cause psychological fatigue for the user, and it is necessary to change the displayed picture frequently to achieve better results.
  • the image used for the promotion is usually a picture generated by synthesizing the background image and the foreground element.
  • a single template is often used to combine the background image and the foreground elements into one picture, that is, the foreground elements are drawn on a fixed background image according to a fixed position.
  • Changing the image requires the artist to regenerate the template, or modify the background image, or modify the foreground elements, which is time-consuming and inefficient, and it is difficult to meet the needs of some promotional activities to generate a large number of composite images in a short time.
  • the present application provides a method for generating a composite picture, including:
  • Sub-regions are divided for foreground elements on the background image; each sub-region is used to display at least one foreground element;
  • a corresponding foreground element is drawn within the sub-area according to the display shape.
  • the application also provides an apparatus for generating a composite picture, comprising:
  • a background image determining unit configured to determine a background image of the composite image based on the background atlas
  • a sub-area dividing unit configured to divide a sub-area for the foreground element on the background image; each sub-area is configured to display at least one foreground element;
  • a display shape determining unit configured to determine a display shape of a foreground element of the sub-area within the sub-area
  • a foreground element drawing unit configured to draw a corresponding foreground element in the sub-area according to the display shape.
  • the sub-area is dynamically generated by selecting a background image and
  • the display shape of the foreground element can automatically generate a large number of composite images having a changed background image, a changed area layout, and a changed foreground element display shape in a short time, thereby improving the generation efficiency of the composite picture.
  • FIG. 1 is a flowchart of a method for generating a composite picture in the embodiment of the present application
  • Figure 3 is a layout diagram of another seed area in an example of the present application.
  • FIG. 4 is a schematic view showing a display shape of a character line in an example of the present application.
  • FIG. 5 is a schematic view showing a display shape of a foreground image in an example of the present application.
  • FIG. 6 is a hardware structural diagram of a computing device to which an embodiment of the present application is applied;
  • FIG. 7 is a logical structural diagram of an apparatus for generating a composite picture in the embodiment of the present application.
  • the embodiment of the present application proposes a new method for generating a composite picture, which uses an automatically changing background image, an automatically changed foreground element layout and position to generate a composite picture, and can generate a large number of different composite pictures in a short time, Solve the problems of the prior art.
  • the flow of the embodiment of the present application is as shown in FIG. 1 .
  • Step 110 Determine a background image of the composite picture based on the background atlas.
  • the preset background atlas includes at least one background image, and a background image is selected from the background image set, and the background image of the composite image is generated according to the selected background image.
  • a background image from the background image set in a variety of ways. For example, you can alternately select each background image in the background image set, or you can randomly select a background image in the background image set; the number of times the composite image can be used. When the background image is reselected when a predetermined value is reached, the background image can be reselected with a certain period of time.
  • a plurality of ways can also be used to generate a background image of a composite picture based on the selected background.
  • the selected background image may be directly used as the background image of the composite image, or the selected background image may be subjected to special processing (such as Gaussian blur processing, illumination processing, or mask processing), and then used as a background image of the composite image; Special processing is performed using fixed algorithms and parameters, and special processing can be performed using randomly varying or periodically varying algorithms and/or parameters.
  • the manner of selecting the background image and the manner of generating the background image of the composite image may be arbitrarily combined, which is not limited in this embodiment.
  • Step 120 dividing a sub-region for the foreground element on the background image; each sub-region is for displaying at least one foreground element.
  • the manner in which the sub-regions are divided on the background image may be determined according to the relationship between the foreground elements of the respective sub-regions and the requirements of the actual application scenario. If all the foreground elements can be arbitrarily displayed at any position on the background image, a corresponding number of sub-regions can be generated according to the number of foreground elements, and the position and size of each sub-region can be randomly determined. If all or part of the foreground element's display needs to satisfy certain conditions (such as a certain positional relationship or a certain size proportional relationship), the associated foreground element may be displayed in the same sub-area, or the foreground element associated with the display may be displayed. The division of each sub-area imposes corresponding constraints.
  • a configuration file may be preset, and restrictions on sub-area division are described in the configuration file to meet the display requirement of the foreground element, and the configuration file includes the number of sub-areas and the positional relationship of at least part of the sub-areas.
  • the layout algorithm uses the configuration file to automatically generate the specific location of each sub-area. Specifically, after obtaining the number and positional relationship of the sub-areas from the configuration file, the area that can be dynamically changed on the background image of each sub-area is calculated according to the positional relationship, and the vertex position of the sub-area is determined in the dynamically changeable area. And size.
  • the specific layout algorithm can be implemented by referring to the prior art, and details are not described herein.
  • the configuration file may further include a shape, a maximum value, and/or a minimum value of the sub-area.
  • the shape and size of the sub-area and the positional relationship with other sub-areas may be considered to allocate each sub-area to be dynamic. Changing area. In the dynamically changeable area, the vertex position and size of the sub-area can be arbitrarily determined under the condition that the configuration file is satisfied.
  • the configuration file specifies that three sub-regions are divided, and sub-region one, sub-region two, and sub-region three are arranged in order from top to bottom, and then a running layout algorithm generates a sub-region layout as shown in FIG. 2, and another operation The layout algorithm generates a sub-area layout as shown in FIG.
  • step 130 the display shape of the foreground element of the sub-area is determined within the sub-area.
  • the foreground element can be a foreground image or a text line;
  • the text line can be one to multiple text units, and the text unit is a component of a text line, which can be words (such as Chinese characters, English words), letters, numbers, and/or Or symbol, can also be a combination of two or three of words, letters or numbers.
  • a different shape can be used to display the foreground element of the sub-region (ie, the foreground element displayed within the sub-region).
  • a set including shapes of original shapes, circles, squares, and the like may be set, from which a display shape as a foreground element is randomly or alternately selected; in this implementation, if the foreground element is a text line, each can be The text is displayed as the selected shape, and the text can also be arranged in the selected shape.
  • a plurality of curve functions are preset; the range of values of the parameters in the preset curve function, the preset range of the parameters may be different depending on the applied curve function, and the preset range should be such that the parameter The display curve generated after being applied to the curve function is partially located in the sub-area.
  • a curve function may be selected among a plurality of preset curve functions; the parameter of the curve function is determined within a preset range, and a display curve is generated; according to the text unit of the text line
  • the number extracts a corresponding number of points on the display curve as vertex positions for each text unit. For example, for a character line including 6 Chinese characters using the display curve shown in FIG. 4, the portion 6 of the display curve whose abscissa is located in the sub-area may be equally divided, and the starting point of each aliquot is the abscissa, The point on the abscissa on the display curve is the vertex position of each Chinese character.
  • the line of text will appear as the shape of the displayed curve, see Figure 4.
  • the foreground element adopting the display curve is a foreground image
  • at least one curve function may be selected in a preset curve function; the parameter of the selected curve function is determined within a preset range to generate at least one display curve; and the display curve is extracted
  • the point is the vertex position of the foreground image, and the generated display curve is used as the display boundary of the foreground image.
  • the straight lines are respectively used as the left and right borders (or upper and lower boundaries) of the foreground image; two curve functions can also be selected to generate two intersecting display curves, respectively as the upper and left boundaries of the foreground image, and the lower boundary of the foreground image and The right boundary uses the lower and right boundaries of the sub-region. In this case, the intersection of the two display curves is taken as the extracted vertex position.
  • the text line is drawn on the foreground image.
  • the display shape of the character line is determined on the foreground image on which the character line is displayed, in other words, the foreground image in which the character line is displayed is used as the sub-area when the display shape of the character line is determined.
  • Step 140 Draw a corresponding foreground element in the sub-area according to the display shape of the foreground element.
  • the foreground image if the display shape is different from the original shape or size of the foreground image, the foreground image may be subjected to affine transformation, perspective transformation, and/or scaling transformation according to the determined display shape, and then drawn in the sub-region. .
  • the OCR Optical Character Recognition
  • the texture can be horizontal and vertical stripes of different intervals, or It is a variety of curved stripes; it can be a background image in the area where the text and the stripes overlap, or it can be a certain color fusion of the foreground text and the background image.
  • This embodiment does not limit the specific processing manner.
  • the method in this embodiment can be applied to any computing device, such as a server, a virtual machine, a personal computer, a tablet computer, a mobile phone, and the like.
  • the method in this embodiment may be partially applied to the server, and partially applied to the client, and the server and the client cooperate to complete the generation of the synthesized picture.
  • a composite picture is generated from a background image, a foreground image, and a line of text.
  • the material for synthesizing the picture is saved on the server, and includes a background atlas composed of a plurality of background images, each foreground image, each character line, and the like, wherein the foreground image includes an image that can dynamically change the position on the background image, such as a logo.
  • a line of text can be an image that is generated for each unit of text and the order in which the images are displayed, or text, which can be converted to an image using a system font when drawing lines of text.
  • information such as a profile for dividing the sub-region on the background image, a plurality of curve functions for determining the shape of the foreground element display, and a preset range of values of the parameters thereof are preset on the server.
  • a background image is randomly selected from the background image set, and the background image is randomly selected.
  • Gaussian blurring is used as the background image of the composite image. Different parameters can make the same background image display images of different feature information, which effectively reduces the commonality of the background image while maintaining the appearance.
  • the layout algorithm is called, and according to the positional relationship of the sub-areas in the configuration file and the size range of each sub-area, the dynamically changeable area of each sub-area is calculated, and the sub-area is randomly determined in the dynamically changeable area.
  • the vertex position and the actual size (within the size range in the configuration file).
  • the sub-areas for displaying the foreground image and/or the line of text are dynamically divided to determine at which position in the background image the foreground element to be presented is placed.
  • the entire background image determines the overall style of the composite picture, and the position and size of each sub-area determines the composite picture layout.
  • the foreground element of each sub-area may be a text line, which may be a single to multiple foreground image, or a combination of a text line and a foreground image.
  • a text line which may be a single to multiple foreground image, or a combination of a text line and a foreground image.
  • one of the saved curve functions is randomly selected from the saved curve functions for the text line, and the parameter value is randomly determined within the parameter value range of the curve function, and the parameter value is applied to the character value.
  • the curve function generates a display curve.
  • Text can be obtained by extracting point coordinates on the display curve The vertex coordinates of each text unit in the line. Based on the vertex coordinates of each character unit, the text unit is processed by deformation and texture, and then the corresponding position on the background image is drawn at a certain size.
  • one of the saved curve functions is randomly selected from the saved curve functions, the parameter value is randomly determined within the parameter value range of the curve function, and the parameter value is applied to the curve function to generate the first display curve.
  • the shaded portion is the display shape of the foreground image, and the upper and lower boundaries of the shaded portion are each a display curve.
  • an embodiment of the present application further provides an apparatus for generating a composite picture.
  • the device can be implemented by software, or can be implemented by hardware or a combination of hardware and software.
  • the CPU Central Process Unit
  • the device in which the device for generating a composite picture is located typically includes other hardware such as a board for implementing network communication functions.
  • FIG. 7 is a diagram of an apparatus for generating a composite picture, including a background image determining unit, a sub-area dividing unit, a display shape determining unit, and a foreground element drawing unit, where the background image determining unit is configured to be based on a background image.
  • a set a background image of the composite picture is determined;
  • the sub-area dividing unit is configured to divide the sub-area for the foreground element on the background image; each sub-area is for displaying at least one foreground element;
  • the display shape determining unit is configured to determine the sub-area a display shape of the foreground element of the sub-area;
  • the foreground element drawing unit is configured to draw the corresponding foreground element in the sub-area according to the display shape.
  • the sub-area dividing unit may further include a location relationship acquiring module, a dynamic area calculating module, and a sub-area location and size module, where: a location relationship acquiring module, configured to obtain the number of sub-areas and at least from the configuration file. a positional relationship of the partial sub-areas; the dynamic area calculation module is configured to calculate, according to the positional relationship, an area that can be dynamically changed on the background image of each sub-area; the sub-area position and size module is configured to determine in the dynamically changeable area The vertex position and size of the sub-area.
  • a location relationship acquiring module configured to obtain the number of sub-areas and at least from the configuration file. a positional relationship of the partial sub-areas
  • the dynamic area calculation module is configured to calculate, according to the positional relationship, an area that can be dynamically changed on the background image of each sub-area
  • the sub-area position and size module is configured to determine in the dynamically changeable area The vertex position and size of the sub-area.
  • the foreground element includes a foreground image
  • the display shape determining unit includes a first curve function selection module, a first display curve generation module, and a foreground image shape module, wherein: the first curve function selection module is configured to Selecting at least one curve function among the preset plurality of curve functions; the first display curve generating module is configured to determine a parameter of the curve function within a preset range, and generate at least one display curve; the foreground image shape module is configured to display the curve The upper extracted point is used as the vertex position of the foreground image, and the display curve is used as the display boundary of the foreground image.
  • the foreground element includes a foreground image; the foreground element drawing unit is specifically configured to: after performing affine transformation, perspective transformation, and/or scaling transformation on the foreground image according to the display shape, drawing the Within the sub-area.
  • the foreground element includes a text line;
  • the display shape determining unit includes a second curve function selecting module, a second display curve generating module, and a character line shape module, wherein: the second curve function selecting module is used to pre- Selecting a curve function among the plurality of curve functions; the second display curve generating module is configured to determine a parameter of the curve function within a preset range, and generate a display curve; the character line shape module is configured to use the text unit in the text line The number extracts a corresponding number of points on the display curve as vertex positions for each text unit.
  • the foreground element drawing unit is specifically configured to: after adding texture and/or deformation to each text unit of the text line according to the display shape, and drawing in the sub-area.
  • the apparatus in the embodiment of the present application may be implemented by being distributed on two or more devices, such as being distributed on a client device and a server.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other Memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape storage or other magnetic storage device or any other non-transportable medium, available for Stores information that can be accessed by the computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application 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, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Processing Or Creating Images (AREA)
  • Controls And Circuits For Display Device (AREA)
  • Image Processing (AREA)
  • Editing Of Facsimile Originals (AREA)

Abstract

一种生成合成图片的方法及装置,该方法包括:基于背景图集,确定合成图片的背景图像(110);在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素(120);在子区域内确定所述子区域的前景元素的显示形状(130);按照所述显示形状在所述子区域内绘制对应的前景元素(140)。能够在短时间内自动生成大量合成图片,提高了生成效率。

Description

生成合成图片的方法及装置
本申请要求2015年03月30日递交的申请号为201510144685.1、发明名称为“生成合成图片的方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及图像处理技术领域,尤其涉及一种生成合成图片的方法及装置。
背景技术
基于互联网的推广活动经常采用在网页、社交平台上展示或扩散图片的形式。始终采用同一张图片容易造成用户的心理疲劳,需要经常变化展示的图片来达到更好的效果。
用于推广活动的图片通常是合成背景图像和前景元素而生成的图片。现有技术中,往往采用单一模板的方式来将背景图像和前景元素合成为一张图片,即将前景元素按照固定的位置绘制在固定的一张背景图像上。更改图片需要美工人员重新生成模板、或者修改背景图像、或者修改前景元素,耗时长效率低,难以满足一些推广活动在短时间内生成大量合成图片的需求。
发明内容
有鉴于此,本申请提供一种生成合成图片的方法,包括:
基于背景图集,确定合成图片的背景图像;
在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素;
在子区域内确定所述子区域的前景元素的显示形状;
按照所述显示形状在所述子区域内绘制对应的前景元素。
本申请还提供了一种生成合成图片的装置,包括:
背景图像确定单元,用于基于背景图集,确定合成图片的背景图像;
子区域划分单元,用于在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素;
显示形状确定单元,用于在子区域内确定所述子区域的前景元素的显示形状;
前景元素绘制单元,用于按照所述显示形状在所述子区域内绘制对应的前景元素。
由以上技术方案可见,本申请的实施例中,通过选择背景图像,动态生成子区域和 前景元素的显示形状,能够在短时间内自动生成大量具有变化的背景图像、变化的区域布局和变化的前景元素显示形状的合成图片,提高了合成图片的生成效率。
附图说明
图1是本申请实施例中生成合成图片的方法的流程图;
图2是本申请一个例子中一种子区域布局图;
图3是本申请一个例子中另一种子区域布局图;
图4是本申请一个例子中一种文字行的显示形状示意图;
图5是本申请一个例子中一种前景图像的显示形状示意图;
图6是应用本申请实施例的计算设备的一种硬件结构图;
图7是本申请实施例中的一种生成合成图片的装置的逻辑结构图。
具体实施方式
本申请的实施例提出一种新的生成合成图片的方法,采用自动变化的背景图像、自动变化的前景元素的布局和位置来生成合成图片,能够在短时间内生成大量不同的合成图片,以解决现有技术存在的问题。本申请实施例的流程如图1所示。
步骤110,基于背景图集,确定合成图片的背景图像。
通常而言,在合成图片中包括较大区域未被前景元素遮挡的背景图像。未被前景元素遮挡的背景图像区域越大,越易于利用根据背景图像生成的参数来识别合成图片。变化的背景图像将提高合成图片的识别难度。本实施例中,预置背景图集,其中包括至少一张背景图,从背景图集中选择一张背景图,根据选择的背景图来生成合成图片的背景图像。
可以采用多种方式从背景图集中选择一张背景图,例如,可以轮流选择背景图集中的每一张背景图,也可以随机选择背景图集中的一张背景图;可以在合成图片的使用次数达到某个预定值时重新选择背景图,也可以以一定时间为周期来重新选择背景图。
类似的,也可以采用多种方式来根据选择的背景生成合成图片的背景图像。例如,可以直接将选择的背景图作为合成图片的背景图像,也可以将选择的背景图经过特殊处理(如高斯模糊处理、光照处理或蒙版处理)后,再作为合成图片的背景图像;可以采用固定的算法和参数来进行特殊处理,也可以采用随机变化或周期变化的算法和/或参数来进行特殊处理。
选择背景图的方式和生成合成图片背景图像的方式可以任意组合,本实施例中不做限定。
步骤120,在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素。
在背景图像上划分子区域的方式可以根据各个子区域的前景元素之间的关系和实际应用场景的需求来确定。如果全部前景元素可以任意显示在背景图像上的任意位置,则可以按照前景元素的个数来产生对应个数的子区域,随机确定每个子区域的位置和大小。如果全部或部分前景元素的显示需要满足某些条件(如某一种位置关系或某一种大小比例关系),则可以将关联的前景元素在同一个子区域内显示,或者对显示关联的前景元素的各个子区域的划分施加相应的限制条件。
在一种实现中,可以预置配置文件,在配置文件中描述对子区域划分的限制条件,以满足前景元素的显示要求,配置文件中包括子区域的个数和至少部分子区域的位置关系,由布局算法利用配置文件来自动生成每个子区域的具体位置。具体而言,从配置文件中获得子区域的个数和位置关系后,根据位置关系计算每个子区域在背景图像上可动态变化的区域,在可动态变化的区域内确定该子区域的顶点位置和大小。具体的布局算法可参照现有技术实现,不再赘述。配置文件中还可以包括子区域的形状、大小的最大值和/或最小值等等,此时需要考虑子区域的形状、大小,和与其他子区域的位置关系,来分配各个子区域可动态变化的区域。在可动态变化的区域内,在满足配置文件的条件下可以任意确定子区域的顶点位置和大小。
例如,配置文件中指定划分3个子区域,并且按照从上到下依次排列子区域一、子区域二和子区域三,则某次运行布局算法生成如图2所示的子区域布局,另一次运行布局算法生成如图3所示的子区域布局。
回到图1,在步骤130,在子区域内确定该子区域的前景元素的显示形状。
前景元素可以是前景图像,也可以是文字行;文字行可以是一个到多个文字单位,文字单位是文字行的组成部分,可以是字词(如汉字、英文单词)、字母、数字和/或符号,也可以是字词、字母或数字中两者或三者的组合。
在子区域内,可以采用不同的形状来显示该子区域的前景元素(即在该子区域内显示的前景元素)。例如,可以设置一个包括原有形状、圆形、方形等形状的集合,从中随机或轮流选择一种作为前景元素的显示形状;在这种实现方式中,如果前景元素是文字行,可以将每个文字显示为选择的形状,也可以将文字排列为所选择的形状。
在另一种实现中,预置若干个曲线函数;预设曲线函数中参数的取值范围,参数的预设范围可以因所适用曲线函数的不同而不同,该预设范围应使得将该参数应用于曲线函数后所生成的显示曲线有部分位于该子区域内。
如果采用该显示曲线的前景元素是文字行,可以在预置的若干个曲线函数中选择一个曲线函数;在预设范围内确定该曲线函数的参数,生成显示曲线;根据文字行中文字单位的数目在显示曲线上抽取对应数目的点作为每个文字单位的顶点位置。例如,对采用图4所示的显示曲线的包括6个汉字的文字行,可以将显示曲线的横坐标位于该子区域内的部分6等分,以每个等分的起点为横坐标,以该横坐标在显示曲线上的点作为每个汉字的顶点位置。这样,文字行将显示为该显示曲线的形状,请参见图4。
如果采用该显示曲线的前景元素是前景图像,可以在预置的曲线函数中选择至少一个曲线函数;在预设范围内确定所选择曲线函数的参数,生成至少一条显示曲线;在显示曲线上抽取点作为前景图像的顶点位置,以所生成的显示曲线作为前景图像的显示边界。例如,可以选择一条曲线函数,以不同的参数生成两条平行的显示曲线,分别作为前景图像的上下边界(或左右边界),而以抽取的两个点所在的平行于纵轴(或横轴)的直线分别作为前景图像的左右边界(或上下边界);也可以选择两条曲线函数,生成两条相交的显示曲线,分别作为前景图像的上边界和左边界,而前景图像的下边界和右边界则采用该子区域的下边界和右边界,此时需将两条显示曲线的交点作为抽取的顶点位置。
在一些应用场景中,在前景图像绘制在背景图像上后,再在前景图像上绘制文字行。在这种情况下,在显示文字行的前景图像上确定文字行的显示形状,换言之,可以看做以显示文字行的前景图像作为确定该文字行显示形状时的子区域。
步骤140,按照前景元素的显示形状在子区域内绘制对应的前景元素。
对前景图像,如果显示形状与前景图像的原始形状或大小不同,则可以根据所确定的显示形状,对前景图像进行仿射变换、透视变换、和/或缩放变换后,绘制在该子区域内。此外,还可以对前景图像进行颜色变换、旋转、拉伸等处理。本实施例对具体的变换处理方式不做限定。
对文字行,为了降低利用文本检测算法定位文字区域,通过OCR(Optical Character Recognition,光学字符识别)方法分割识别文字,用文字中的关键词屏蔽图片的可能性,可以根据所确定的显示形状,为每个文字添加纹理和/或形变后,再绘制在该子区域内。形变可以是针对文字单位的旋转、拉伸等操作;纹理可以是不同间隔的横竖条纹,也可 以是各种曲线条纹;在文字和条纹交叠的区域显示的可以是背景图像,也可以是前景文字和背景图像的某种颜色融合。本实施例对具体的处理方式不做限定。
可见,本申请的实施例中通过选择背景图像,动态生成子区域和前景元素的显示形状,能够在短时间内生成大量具有变化的背景图像、变化的区域布局和变化的前景元素形状的合成图片,在提高产生合成图片的效率的同时降低了图片多样化的成本。
需要说明的是,本实施例中的方法可以应用在任何计算设备上,如服务器、虚拟机、个人电脑、平板电脑、手机等设备。在客户端/服务器(C/S)模式的应用中,本实施例中的方法可以部分应用在服务器上,部分应用在客户端上,由服务器和客户端协同完成合成图片的生成。
在本申请的一个应用示例中,合成图片由背景图像、前景图像和文字行生成。在服务器上保存用来合成图片的素材,包括由多张背景图组成的背景图集、各个前景图像、各个文字行等,其中,前景图像包括在背景图像上可以动态改变位置的图像,如logo(徽标);文字行可以是将每个文字单位生成一张图像以及这些图像的显示顺序,也可以是文本,在进行文字行绘制时再利用系统字库来将文本转化为图像。此外,在服务器上预置将用来在背景图像上划分子区域的配置文件、用来确定前景元素显示形状的多个曲线函数及其参数的预设取值范围等信息。
当服务器需要生成合成图片时(如接收到客户端获取合成图片的请求、改变合成图片的周期到等等),从背景图集中随机选择一张背景图,对该背景图用随机选择的参数进行高斯模糊处理后将其作为合成图片的背景图像。不同的参数都可以使同一张背景图展现出来不同特征信息的图像,有效降低了背景图像的共性,同时保持美观。
在确定背景图像后,调用布局算法,根据配置文件中子区域的位置关系、各个子区域的大小范围,计算出每个子区域可动态变化的区域,在可动态变化的区域内随机决定该子区域的顶点位置和实际大小(在配置文件中的大小范围内)。从而动态划分出用于显示前景图像和/或文字行的各个子区域,来决定将要展现的前景元素放置在背景图像中的哪个位置。整个背景图像确定合成图片的整体风格,各子区域的位置和大小确定合成图片排版。
每个子区域的前景元素可以是文字行,可以是单张到多张前景图像,还可以是文字行与前景图像的组合。在子区域中绘制前景元素时,对文字行,从保存的多个曲线函数中随机选择其中的一个曲线函数,在该曲线函数的参数取值范围内随机确定参数值,将参数值应用于该曲线函数生成显示曲线。通过在显示曲线上抽取点坐标,可以得到文字 行中每个文字单位的顶点坐标。基于每个文字单位的顶点坐标,将该文字单位经过形变和纹理等处理后,以一定的大小绘制在背景图像上对应的位置。
对前景图像,从保存的多个曲线函数中随机选择其中的一个曲线函数,在该曲线函数的参数取值范围内随机确定参数值,将参数值应用于该曲线函数生成第一条显示曲线,将该显示曲线平移一定距离后作为第二条显示曲线(或者说以另一个参数值生成第二条显示曲线),在第一条显示曲线上抽取两个点作为前景图像的两个顶点位置;将这两个点平移到第二条显示曲线上来作为前景图像的另外两个顶点位置,以两个顶点位置之间的第一条显示曲线和另外两个顶点位置之间的第二条显示曲线作为前景图像的两个显示边界,例如图5所示,其中的阴影部分为前景图像的显示形状,阴影部分的上边界和下边界各为一条显示曲线。在确定前景图像的显示形状后,按照显示形状对前景图像进行变形处理,绘制在背景图像中的对应位置。
经过上述步骤,即可生成具有变化的背景图像、变化的布局和变化的前景元素形状及展现形式的合成图片。
与上述流程实现对应,本申请的实施例还提供了一种生成合成图片的装置。该装置可以通过软件实现,也可以通过硬件或者软硬件结合的方式实现。以软件实现为例,作为逻辑意义上的装置,是通过所在计算设备的CPU(Central Process Unit,中央处理器)将对应的计算机程序指令读取到内存中运行形成的。从硬件层面而言,除了图6所示的CPU、内存以及非易失性存储器之外,生成合成图片的装置所在的设备通常还包括用于实现网络通信功能的板卡等其他硬件。
图7所示为本实施例提供的一种生成合成图片的装置,包括背景图像确定单元、子区域划分单元、显示形状确定单元和前景元素绘制单元,其中:背景图像确定单元用于基于背景图集,确定合成图片的背景图像;子区域划分单元用于在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素;显示形状确定单元用于在子区域内确定所述子区域的前景元素的显示形状;前景元素绘制单元用于按照所述显示形状在所述子区域内绘制对应的前景元素。
可选的,所述子区域划分单元可以进一步包括位置关系获取模块、动态区域计算模块和子区域位置及大小模块,其中:位置关系获取模块,用于从配置文件中获取子区域的个数和至少部分子区域的位置关系;动态区域计算模块用于根据所述位置关系计算每个子区域在背景图像上可动态变化的区域;子区域位置及大小模块用于在所述可动态变化的区域内确定所述子区域的顶点位置和大小。
一种实现中,所述前景元素包括前景图像;所述显示形状确定单元包括第一曲线函数选择模块、第一显示曲线生成模块和前景图像形状模块,其中:第一曲线函数选择模块用于在预置的若干个曲线函数中选择至少一个曲线函数;第一显示曲线生成模块用于在预设范围内确定所述曲线函数的参数,生成至少一条显示曲线;前景图像形状模块用于在显示曲线上抽取点作为所述前景图像的顶点位置,以所述显示曲线作为所述前景图像的显示边界。
可选的,所述前景元素包括前景图像;所述前景元素绘制单元具体用于:根据所述显示形状,对前景图像进行仿射变换、透视变换、和/或缩放变换后,绘制在所述子区域内。
可选的,所述前景元素包括文字行;所述显示形状确定单元包括第二曲线函数选择模块、第二显示曲线生成模块和文字行形状模块,其中:第二曲线函数选择模块用于在预置的若干个曲线函数中选择一个曲线函数;第二显示曲线生成模块用于在预设范围内确定所述曲线函数的参数,生成显示曲线;文字行形状模块用于根据文字行中文字单位的数目在显示曲线上抽取对应数目的点作为每个文字单位的顶点位置。
可选的,所述前景元素绘制单元具体用于:根据所述显示形状,为文字行的每个文字单位添加纹理和/或形变后,绘制在所述子区域内。
需要说明的是,本申请实施例中的装置可以分散在两个或多个设备上实现,如分散在客户端设备和服务器上实现。
以上所述仅为本申请的较佳实施例而已,并不用以限制本申请,凡在本申请的精神和原则之内,所做的任何修改、等同替换、改进等,均应包含在本申请保护的范围之内。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他 内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白,本申请的实施例可提供为方法、系统或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且,本申请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、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。

Claims (14)

  1. 一种生成合成图片的方法,其特征在于,包括:
    基于背景图集,确定合成图片的背景图像;
    在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素;
    在子区域内确定所述子区域的前景元素的显示形状;
    按照所述显示形状在所述子区域内绘制对应的前景元素。
  2. 根据权利要求1所述的方法,其特征在于,所述基于背景图集,确定合成图片的背景图像,包括:
    在若干张背景图中选择其中的一张;
    将选择的背景图进行高斯模糊处理、光照处理和/或蒙版处理后,作为合成图片的背景图像。
  3. 根据权利要求1所述的方法,其特征在于,所述在背景图像上为前景元素划分子区域,包括:
    从配置文件中获取子区域的个数和至少部分子区域的位置关系;
    根据所述位置关系计算每个子区域在背景图像上可动态变化的区域;
    在所述可动态变化的区域内确定所述子区域的顶点位置和大小。
  4. 根据权利要求1所述的方法,其特征在于,所述前景元素包括前景图像;
    所述在子区域内确定所述子区域的前景元素的显示形状,包括:
    在预置的若干个曲线函数中选择至少一个曲线函数;
    在预设范围内确定所述曲线函数的参数,生成至少一条显示曲线;
    在显示曲线上抽取点作为所述前景图像的顶点位置,以所述显示曲线作为所述前景图像的显示边界。
  5. 根据权利要求1或4所述的方法,其特征在于,所述前景元素包括前景图像;
    所述按照显示形状在所述子区域内绘制对应的前景元素,包括:根据所述显示形状,对前景图像进行仿射变换、透视变换、和/或缩放变换后,绘制在所述子区域内。
  6. 根据权利要求1所述的方法,其特征在于,所述前景元素包括文字行;
    所述在子区域内确定所述子区域的前景元素的显示形状,包括:
    在预置的若干个曲线函数中选择一个曲线函数;
    在预设范围内确定所述曲线函数的参数,生成显示曲线;
    根据文字行中文字单位的数目在显示曲线上抽取对应数目的点作为每个文字单位 的顶点位置。
  7. 根据权利要求6所述的方法,其特征在于,所述前景元素包括显示在前景图像上的文字行;
    所述在子区域内确定所述子区域的前景元素的显示形状,包括:在显示文字行的前景图像上确定所述文字行的显示形状。
  8. 根据权利要求1、6或7所述的方法,其特征在于,所述按照显示形状在所述子区域内绘制对应的前景元素,包括:根据所述显示形状,为文字行的每个文字单位添加纹理和/或形变后,绘制在所述子区域内。
  9. 一种生成合成图片的装置,其特征在于,包括:
    背景图像确定单元,用于基于背景图集,确定合成图片的背景图像;
    子区域划分单元,用于在背景图像上为前景元素划分子区域;每个子区域用于显示至少一个前景元素;
    显示形状确定单元,用于在子区域内确定所述子区域的前景元素的显示形状;
    前景元素绘制单元,用于按照所述显示形状在所述子区域内绘制对应的前景元素。
  10. 根据权利要求9所述的装置,其特征在于,所述子区域划分单元包括:
    位置关系获取模块,用于从配置文件中获取子区域的个数和至少部分子区域的位置关系;
    动态区域计算模块,用于根据所述位置关系计算每个子区域在背景图像上可动态变化的区域;
    子区域位置及大小模块,用于在所述可动态变化的区域内确定所述子区域的顶点位置和大小。
  11. 根据权利要求9所述的装置,其特征在于,所述前景元素包括前景图像;
    所述显示形状确定单元包括:
    第一曲线函数选择模块,用于在预置的若干个曲线函数中选择至少一个曲线函数;
    第一显示曲线生成模块,用于在预设范围内确定所述曲线函数的参数,生成至少一条显示曲线;
    前景图像形状模块,用于在显示曲线上抽取点作为所述前景图像的顶点位置,以所述显示曲线作为所述前景图像的显示边界。
  12. 根据权利要求9或11所述的装置,其特征在于,所述前景元素包括前景图像;
    所述前景元素绘制单元具体用于:根据所述显示形状,对前景图像进行仿射变换、 透视变换、和/或缩放变换后,绘制在所述子区域内。
  13. 根据权利要求9所述的装置,其特征在于,所述前景元素包括文字行;
    所述显示形状确定单元包括:
    第二曲线函数选择模块,用于在预置的若干个曲线函数中选择一个曲线函数;
    第二显示曲线生成模块,用于在预设范围内确定所述曲线函数的参数,生成显示曲线;
    文字行形状模块,用于根据文字行中文字单位的数目在显示曲线上抽取对应数目的点作为每个文字单位的顶点位置。
  14. 根据权利要求9或13所述的装置,其特征在于,所述前景元素绘制单元具体用于:根据所述显示形状,为文字行的每个文字单位添加纹理和/或形变后,绘制在所述子区域内。
PCT/CN2016/076950 2015-03-30 2016-03-22 生成合成图片的方法及装置 WO2016155536A1 (zh)

Priority Applications (11)

Application Number Priority Date Filing Date Title
SG11201707783VA SG11201707783VA (en) 2015-03-30 2016-03-22 Method and apparatus for generating a synthesized picture
KR1020177031276A KR102107887B1 (ko) 2015-03-30 2016-03-22 합성 화상을 생성하는 방법 및 장치
KR1020207009637A KR102215766B1 (ko) 2015-03-30 2016-03-22 합성 화상을 생성하는 방법 및 장치
PL19205490T PL3618003T3 (pl) 2015-03-30 2016-03-22 Sposób i aparat do generowania syntetycznego zdjęcia
EP16771291.8A EP3279866B1 (en) 2015-03-30 2016-03-22 Method and apparatus for generating synthetic picture
JP2017551134A JP6768695B2 (ja) 2015-03-30 2016-03-22 合成された絵を生成するための方法及び装置
ES16771291T ES2819868T3 (es) 2015-03-30 2016-03-22 Método y aparato para generar imagen sintética
EP19205490.6A EP3618003B1 (en) 2015-03-30 2016-03-22 Method and apparatus for generating synthetic picture
PL16771291T PL3279866T3 (pl) 2015-03-30 2016-03-22 Sposób i urządzenie do wytwarzania syntetycznego zdjęcia
US15/716,332 US10692261B2 (en) 2015-03-30 2017-09-26 Efficient images synthesis
US16/749,060 US10878609B2 (en) 2015-03-30 2020-01-22 Efficient image synthesis

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510144685.1A CN106157341B (zh) 2015-03-30 2015-03-30 生成合成图片的方法及装置
CN201510144685.1 2015-03-30

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/716,332 Continuation US10692261B2 (en) 2015-03-30 2017-09-26 Efficient images synthesis

Publications (1)

Publication Number Publication Date
WO2016155536A1 true WO2016155536A1 (zh) 2016-10-06

Family

ID=57004223

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/076950 WO2016155536A1 (zh) 2015-03-30 2016-03-22 生成合成图片的方法及装置

Country Status (9)

Country Link
US (2) US10692261B2 (zh)
EP (2) EP3618003B1 (zh)
JP (1) JP6768695B2 (zh)
KR (2) KR102215766B1 (zh)
CN (1) CN106157341B (zh)
ES (2) ES2819868T3 (zh)
PL (2) PL3618003T3 (zh)
SG (1) SG11201707783VA (zh)
WO (1) WO2016155536A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118555461A (zh) * 2024-07-29 2024-08-27 浙江天猫技术有限公司 视频生成方法、装置、设备、系统及计算机程序产品

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106161346B (zh) 2015-03-30 2019-09-20 阿里巴巴集团控股有限公司 图片合成方法及装置
CN106157341B (zh) 2015-03-30 2019-05-14 阿里巴巴集团控股有限公司 生成合成图片的方法及装置
CN108573515B (zh) * 2017-03-10 2022-03-01 阿里巴巴集团控股有限公司 一种合图生成方法及装置、合图模板生成方法及装置
CN107608733B (zh) * 2017-09-19 2021-04-02 阿里巴巴(中国)有限公司 图片显示方法、装置和终端设备
CN107967341A (zh) * 2017-12-08 2018-04-27 广东欧珀移动通信有限公司 一种图片显示方法、终端设备及存储介质
CN110533744B (zh) * 2018-05-25 2023-02-28 阿里巴巴集团控股有限公司 合成图片的方法、设备、系统和移动终端
CN109145266B (zh) * 2018-07-25 2022-03-25 珠海市圈宝网络科技有限公司 一种从图片快速生成动态pdf文件的方法
CN109240689B (zh) * 2018-08-15 2022-08-09 腾讯科技(深圳)有限公司 一种应用图标的生成方法、装置、服务器及介质
CN108924518B (zh) * 2018-08-27 2020-10-09 上海蒙彤文化传播有限公司 推介视频中合成方法及相关产品
CN111402364A (zh) * 2018-12-27 2020-07-10 北京字节跳动网络技术有限公司 一种图像生成方法、装置、终端设备及存储介质
CN110068586B (zh) * 2019-04-10 2020-06-12 中国石油大学(北京) 扫描电镜照片的制图方法及装置
CN110163285B (zh) * 2019-05-23 2021-03-02 阳光保险集团股份有限公司 票证识别训练样本合成方法和计算机存储介质
CN110647705A (zh) * 2019-08-14 2020-01-03 平安普惠企业管理有限公司 图片合成方法、装置、设备及存储介质
CN110619312B (zh) * 2019-09-20 2022-08-23 百度在线网络技术(北京)有限公司 定位元素数据的增强方法、装置、设备及存储介质
CN110838084B (zh) * 2019-09-24 2023-10-17 咪咕文化科技有限公司 一种图像的风格转移方法、装置、电子设备及存储介质
CN110688506A (zh) * 2019-09-30 2020-01-14 北京金山安全软件有限公司 一种模板生成方法、装置、电子设备及存储介质
CN110992297A (zh) * 2019-11-11 2020-04-10 北京百度网讯科技有限公司 多商品图像合成方法、装置、电子设备及存储介质
CN111222301A (zh) * 2020-01-07 2020-06-02 天津麒麟信息技术有限公司 一种3d文字绘制方法、系统、可读存储介质及设备
CN111723585B (zh) * 2020-06-08 2023-11-28 中国石油大学(华东) 一种风格可控的图像文本实时翻译与转换方法
KR20220005820A (ko) * 2020-07-07 2022-01-14 삼성전자주식회사 그래픽 효과를 적용하기 위한 전자 장치 및 그에 관한 방법
CN112804516B (zh) * 2021-04-08 2021-07-06 北京世纪好未来教育科技有限公司 一种视频播放方法、装置、可读存储介质、电子设备
CN114863245B (zh) * 2022-05-26 2024-06-04 中国平安人寿保险股份有限公司 图像处理模型的训练方法和装置、电子设备及介质
CN115334296A (zh) * 2022-07-01 2022-11-11 深圳市安博斯技术有限公司 一种立体图像显示方法和显示装置
KR102618644B1 (ko) * 2023-08-28 2023-12-27 주식회사 리콘랩스 3차원 모델을 이용한 합성 이미지 출력 방법 및 장치

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101174305A (zh) * 2006-10-31 2008-05-07 富士施乐株式会社 图像处理装置、图像形成装置和计算机可读介质
CN101442600A (zh) * 2008-12-11 2009-05-27 深圳华为通信技术有限公司 动态处理图像的方法、装置及终端
CN102158644A (zh) * 2009-12-25 2011-08-17 卡西欧计算机株式会社 图像合成装置和图像合成方法
CN102262787A (zh) * 2010-05-31 2011-11-30 卡西欧计算机株式会社 图像合成装置
CN102938863A (zh) * 2012-11-27 2013-02-20 乐视致新电子科技(天津)有限公司 基于Android系统的智能电视图标主题替换方法和装置

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0566759A (ja) * 1991-09-09 1993-03-19 Casio Comput Co Ltd 修飾文字出力装置
JP3449563B2 (ja) * 1993-09-10 2003-09-22 アルプス電気株式会社 画像データ編集方法
JPH10191020A (ja) 1996-12-20 1998-07-21 Canon Inc 被写体画像切出し方法及び装置
JP3045087B2 (ja) * 1996-12-27 2000-05-22 日本電気株式会社 画像合成装置
JP2001121775A (ja) * 1999-08-19 2001-05-08 Tokyo Denshi Sekkei Kk 画像データ生成装置、画像出力システムおよび端末
JP4337251B2 (ja) 2000-09-04 2009-09-30 コニカミノルタビジネステクノロジーズ株式会社 画像処理装置、画像処理方法および画像処理プログラムを記録したコンピュータ読取可能な記録媒体
GB2378340A (en) * 2001-07-31 2003-02-05 Hewlett Packard Co Generation of an image bounded by a frame or of overlapping images
JP2003058878A (ja) 2001-08-17 2003-02-28 Ricoh Co Ltd 合成画像形成プログラム
GB0124155D0 (en) 2001-10-08 2001-11-28 Segmentis Ltd Graphical user interface
US7110137B2 (en) * 2002-04-30 2006-09-19 Microsoft Corporation Mixed raster content files
JP4236659B2 (ja) 2005-11-02 2009-03-11 シャープ株式会社 画像符号化装置、画像符号化方法、画像符号化プログラムおよび記録媒体
CN101093644A (zh) * 2006-06-19 2007-12-26 深圳安凯微电子技术有限公司 一种支持多输出格式下画中画功能的lcd控制电路及方法
WO2008133357A1 (en) 2007-04-25 2008-11-06 Nexmore Systems Inc Photo synthesis service system and method
GB0818561D0 (en) 2008-10-09 2008-11-19 Isis Innovation Visual tracking of objects in images, and segmentation of images
US8584012B1 (en) 2008-10-10 2013-11-12 Adobe Systems Incorporated Methods and systems for displaying text on a path
CN101853498B (zh) * 2009-03-31 2012-01-11 华为技术有限公司 图像合成方法及图像处理装置
CN101998045A (zh) * 2009-08-11 2011-03-30 佛山市顺德区顺达电脑厂有限公司 可合成场景信息的影像处理装置
JP2013021607A (ja) * 2011-07-13 2013-01-31 Ricoh Co Ltd 画像データ処理装置、画像形成装置、プログラム及び記録媒体
US8731315B2 (en) * 2011-09-12 2014-05-20 Canon Kabushiki Kaisha Image compression and decompression for image matting
JP2013186521A (ja) 2012-03-06 2013-09-19 Casio Comput Co Ltd 画像処理装置、画像処理方法及びプログラム
JP2014096757A (ja) * 2012-11-12 2014-05-22 Sony Corp 画像処理装置および画像処理方法、並びにプログラム
JP5553423B1 (ja) * 2013-01-31 2014-07-16 株式会社精美堂 カレンダー及びその作成方法、並びにカレンダー作成システム
KR102089624B1 (ko) * 2013-09-02 2020-03-16 삼성전자주식회사 이미지를 합성하기 위한 방법 및 그 전자 장치
CN103491351A (zh) * 2013-09-29 2014-01-01 东南大学 违章建筑物的智能视频监控方法
US20150109323A1 (en) 2013-10-18 2015-04-23 Apple Inc. Interactive black and white image editing
US9519950B2 (en) * 2013-12-20 2016-12-13 Furyu Corporation Image generating apparatus and image generating method
CN106157341B (zh) 2015-03-30 2019-05-14 阿里巴巴集团控股有限公司 生成合成图片的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101174305A (zh) * 2006-10-31 2008-05-07 富士施乐株式会社 图像处理装置、图像形成装置和计算机可读介质
CN101442600A (zh) * 2008-12-11 2009-05-27 深圳华为通信技术有限公司 动态处理图像的方法、装置及终端
CN102158644A (zh) * 2009-12-25 2011-08-17 卡西欧计算机株式会社 图像合成装置和图像合成方法
CN102262787A (zh) * 2010-05-31 2011-11-30 卡西欧计算机株式会社 图像合成装置
CN102938863A (zh) * 2012-11-27 2013-02-20 乐视致新电子科技(天津)有限公司 基于Android系统的智能电视图标主题替换方法和装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118555461A (zh) * 2024-07-29 2024-08-27 浙江天猫技术有限公司 视频生成方法、装置、设备、系统及计算机程序产品

Also Published As

Publication number Publication date
PL3279866T3 (pl) 2020-11-16
KR20200037887A (ko) 2020-04-09
US10878609B2 (en) 2020-12-29
ES2873115T3 (es) 2021-11-03
EP3279866A4 (en) 2018-12-12
JP6768695B2 (ja) 2020-10-14
PL3618003T3 (pl) 2021-08-09
US10692261B2 (en) 2020-06-23
JP2018510429A (ja) 2018-04-12
KR102107887B1 (ko) 2020-05-08
US20180018800A1 (en) 2018-01-18
KR20170131669A (ko) 2017-11-29
US20200160577A1 (en) 2020-05-21
EP3279866A1 (en) 2018-02-07
EP3279866B1 (en) 2020-08-12
CN106157341B (zh) 2019-05-14
EP3618003A1 (en) 2020-03-04
CN106157341A (zh) 2016-11-23
EP3618003B1 (en) 2021-02-24
ES2819868T3 (es) 2021-04-19
KR102215766B1 (ko) 2021-02-17
SG11201707783VA (en) 2017-10-30

Similar Documents

Publication Publication Date Title
WO2016155536A1 (zh) 生成合成图片的方法及装置
US10304162B1 (en) Automatic image inpainting using local patch statistics
US20190340649A1 (en) Generating and providing augmented reality representations of recommended products based on style compatibility in relation to real-world surroundings
JP4696635B2 (ja) 画像領域の高凝縮要約画像を生成する方法、装置およびプログラム
CN106651877B (zh) 实例分割方法及装置
JP2018510429A5 (zh)
US20150116355A1 (en) Reference image slicing
WO2023036160A1 (zh) 视频处理方法、装置、计算机可读存储介质及计算机设备
CN109684005B (zh) 图形界面中组件相似度确定方法及装置
CN112419183B (zh) 缩放图像还原方法、装置、计算机设备及存储介质
CN109816743A (zh) 生成标识图案的方法和终端设备
CN113538502A (zh) 图片裁剪方法、装置、电子设备及存储介质
CN114332895A (zh) 文本图像合成方法、装置、设备、存储介质和程序产品
US11657511B2 (en) Heuristics-based detection of image space suitable for overlaying media content
CN110942056A (zh) 服饰关键点定位方法、装置、电子设备及介质
US10586364B2 (en) Methods and systems for decorating and embellishing a digital object layout
CN116584100A (zh) 适合于覆盖媒体内容的图像空间检测
CN109582191B (zh) 一种菜单内容显示方法及装置
JP6148426B1 (ja) 画像処理装置、画像処理方法及び画像処理プログラム
CN105843949B (zh) 一种图像显示方法与装置
CN117392276A (zh) 图像处理方法、设备及存储介质

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: 16771291

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 11201707783V

Country of ref document: SG

ENP Entry into the national phase

Ref document number: 2017551134

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20177031276

Country of ref document: KR

Kind code of ref document: A

REEP Request for entry into the european phase

Ref document number: 2016771291

Country of ref document: EP