WO2017088463A1 - 图像处理方法和装置 - Google Patents
图像处理方法和装置 Download PDFInfo
- Publication number
- WO2017088463A1 WO2017088463A1 PCT/CN2016/086602 CN2016086602W WO2017088463A1 WO 2017088463 A1 WO2017088463 A1 WO 2017088463A1 CN 2016086602 W CN2016086602 W CN 2016086602W WO 2017088463 A1 WO2017088463 A1 WO 2017088463A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- point
- edge
- edge feature
- image
- feature image
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- the embodiments of the present invention relate to the field of video technologies, and in particular, to an image processing method and apparatus.
- the edge feature of the image is a basic feature of the image, which is often applied to image processing and analysis techniques such as higher-level feature description, image recognition, image segmentation, image enhancement and image compression.
- image processing and analysis techniques such as higher-level feature description, image recognition, image segmentation, image enhancement and image compression.
- image processing and analysis techniques such as higher-level feature description, image recognition, image segmentation, image enhancement and image compression.
- Embodiments of the present invention provide an image processing method and apparatus for removing text portions in a logo area image.
- an embodiment of the present invention provides an image processing method, including:
- edge feature image of the logo area image has a first interval point, removing each edge point on the right side of the first interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- an embodiment of the present invention provides an image processing apparatus, including:
- An edge extraction module configured to acquire an edge feature image of the logo area image
- a first correction module configured to remove each edge point on the right side of the first interval point when the edge feature image of the logo area image has a first interval point
- a second correction module configured to remove each edge point below the second interval point when the edge feature image of the logo area image has a second interval point
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- an embodiment of the present invention provides an image processing apparatus, including:
- the processor, the memory, and the communication interface complete communication with each other through the bus;
- the communication interface is used for information transmission between the image processing device and a communication device of the image storage device or the image transmission device;
- the processor is configured to invoke logic instructions in the memory to perform the following method
- edge feature image of the logo area image has a first interval point, removing each edge point on the right side of the first interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- an embodiment of the present invention provides a computer program, including program code, where the program code is used to perform the following operations:
- the edge feature image of the logo area image has a first interval point
- the first part is removed a respective edge point on the right side of an interval point
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- an embodiment of the present invention provides a storage medium for storing a computer program as described above.
- the image processing method and apparatus after acquiring the edge feature image of the logo area image, when the edge feature image of the logo area image has the first interval point, the first interval point is removed. Each edge point on the right side; when the edge feature image of the logo area image has a second interval point, each edge point below the second interval point is removed.
- the image processing method provided by the embodiment of the present invention can be quickly and accurately removed because there is a space between the icon portion and the text portion in the general logo, and the icon portion is continuous inside and the text portion is generally located below or to the right of the icon portion. The text part of the logo.
- FIG. 1 is a schematic flowchart of an image processing method according to an embodiment of the present invention.
- FIG. 2 is a schematic flowchart diagram of another image processing method according to an embodiment of the present disclosure.
- FIG. 3 is a diagram showing a logo area image before and after processing by an image processing method according to an embodiment of the present invention
- FIG. 4 is a structural block diagram of an image processing apparatus according to an embodiment of the present invention.
- FIG. 5 is a structural block diagram of still another image processing apparatus according to an embodiment of the present invention.
- An embodiment of the present invention provides an image processing method. Referring to FIG. 1, the method includes:
- Step S11 acquiring an edge feature image of the logo area image
- Step S12 when the edge feature image of the logo area image has a first interval point, remove each edge point on the right side of the first interval point;
- Step S13 when the edge feature image of the logo area image has a second interval point, remove each edge point below the second interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- the image processing method provided by the embodiment of the present invention after acquiring the edge feature image of the logo area image, when the edge feature image of the logo area image has the first interval point, the right side of the first interval point is removed. Each edge point; when the edge feature image of the logo area image has a second interval point, each edge point below the second interval point is removed.
- the image processing method provided by the embodiment of the present invention can be quickly and accurately removed because there is a space between the icon portion and the text portion in the general logo, and the icon portion is continuous inside and the text portion is generally located below or to the right of the icon portion. The text part of the logo.
- step S11 may specifically include the following in the figure:
- Step S111 performing pre-processing on a plurality of images including the logo of the logo area to obtain a logo area image in each screen;
- Step S112 performing edge feature extraction on each of the obtained logo area images, and synthesizing the images extracted for each of the logo area images to obtain the edge feature images.
- the preprocessing process in the above step S111 may refer to segmenting the entire television picture including the logo area image, and obtaining an image of the top left corner logo area, and then performing grayscale and grayscale enhancement.
- the edge feature extraction in step S112 is prepared.
- the edge extraction may be performed on each of the logo area images by the Canny algorithm, and the strong and weak edge thresholds may be 200 and 50, respectively.
- the process of synthesizing the images obtained by extracting the edges may specifically: determining, for each edge point of the plurality of edge points included in the image extracted by the edge feature, determining the edge point in each image. Whether the number of occurrences of the same coordinate position is greater than a preset number of times, if not, the edge point is set as a background point; then the remaining edge points in each initial edge feature image are combined to obtain an edge feature image of the target image.
- the foregoing method may further include:
- the edge feature image is scanned from left to right to determine whether the edge feature image has a first interval point.
- the method may further include: scanning the edge feature image from top to bottom to determine whether the edge feature image has a second interval point.
- the advantage of this is that it can automatically determine whether there is a gap in the corresponding logo (there is usually text when there is an interval), thus reducing human intervention.
- the method further includes:
- the step S12 specifically includes:
- the step S13 specifically includes:
- the edge feature image is scanned from top to bottom only when the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio.
- the minimum circumscribed rectangle including each edge point is obtained in advance; whether the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio; and only the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset Scanning is performed at an aspect ratio, which reduces unnecessary scanning and reduces corresponding resource consumption.
- the "long” of the smallest circumscribed rectangle here refers to the length of the minimum circumscribed rectangle in the column direction, specifically, the number of rows at the included pixel points; and "wide” refers to the number of rows.
- the length of the minimum circumscribed rectangle in the row direction specifically, the number of columns of pixels included.
- the minimum circumscribed figure including the respective edge points referred to herein refers to the circumscribing pattern of the contour obtained by aiming at the contour composed of the respective edge points.
- step S12 in the case of acquiring the minimum circumscribed rectangle including each edge point, in the above step S12, only the edge feature image in the minimum circumscribed rectangle (ie, the binarized matrix in the minimum circumscribed rectangle) may be left from the left. Scanning to the right; correspondingly, in step S13, only the edge feature image in the minimum circumscribed rectangle can be scanned from top to bottom.
- the step S12 may specifically include: scanning the edge feature image in the minimum circumscribed rectangle from left to right with the nth/xth column pixel from left to right as a starting column; and or,
- the step S13 may specifically include: scanning the edge feature image in the minimum circumscribed rectangle from top to bottom with the m/y row of pixel points from top to bottom as a starting line;
- n is the total number of columns of the edge feature image
- m is the total number of rows of the edge feature image
- x and y are preset values.
- the icon In practical applications, there is obviously no area for text and icons that need to be scanned. For example, in the vertical direction, the icon is above the text, and the text cannot appear within 1/3 of the height of the area. It is impossible to scan the second interval point in the lower m/3 column pixel. In the horizontal direction, there may be 4 characters, such as Southeast Satellite TV. At this time, the icon only accounts for about 1/5 of the width of the image of the logo area, while Shenzhen Satellite TV is about 1/6, but the text is basically impossible to appear in From the first 1/6 width of the left side, within the first 1/6 width, the first interval point is generally not scanned.
- steps S12 and S13 in the above manner does not cause a situation in which the first interval and the second interval are missed, and the number of pixels to be scanned can be reduced, thereby shortening the scanning time and reducing the required use. Resources to improve the efficiency of text removal.
- the value of x and the value of y may be set according to actual conditions. As a preferred method, the value of x may be 6, and the value of y may be 3.
- the method may further include: scanning the edge feature image obtained after removing the edge points on the right side of the first interval point from right to left, and scanning the At an interval, removing each edge point on the right side of the first interval point;
- the corresponding method may further include: scanning the edge feature image obtained after removing each edge point below the second interval point from bottom to top, and scanning to the second interval point Removing each edge point below the second spacing point.
- the preset number of lines may be determined according to a total number of rows of pixel points of the edge feature image of the logo area image, and correspondingly, the preset number of columns may be according to the pixel points of the edge feature image of the logo area image.
- the total number of columns is determined.
- the total number of pixels of the edge feature image of the logo area image is 50 lines, and when the number of columns is 200, the preset number of rows may be 5, and the preset number of columns may be 7 or 8. .
- the image processing method provided by the embodiment of the present invention is further described below with reference to a specific application scenario. Referring to FIG. 2, the method includes:
- Step S21 acquiring an edge feature image of the logo area image
- Step S22 acquiring a minimum circumscribed rectangle of each edge point in the edge feature image
- Step S23 determining whether the aspect ratio r of the minimum circumscribed rectangle is greater than 1.5; if yes, then proceeding to step S24, if not, then proceeding to step S210;
- Step S24 scanning the edge feature image in the minimum circumscribed rectangle from left to right from the pixel at the n/6th column on the left side to determine whether there is a first interval point; if yes, proceeding to step S28; if not, then Go to step S25.
- each pixel point may be scanned column by column. If no edge point is found in 8 columns of pixels after a column of pixels including edge points, it may be determined that the edge point may be an interval point, and then the scanning is continued. If the edge point is not found again after the column of pixels, the pixel is not the true first interval. If an edge point is found after the column of pixels, the point is considered to be the first interval.
- Step S25 the upper m/3th row of pixel point out edge minimum feature rectangle edge feature image is scanned from top to bottom, to determine whether there is a second interval point; if yes, then go to step S26; If no, the process proceeds to step S210.
- each pixel point may be scanned row by row. If no edge point is found in 5 rows of pixels after a row of pixels including edge points, it may be determined that the point may be an interval point, and then continue scanning, if If the edge point is not found again after the row of pixels, the pixel is not a true second interval. If an edge point is found after the row of pixels, the point is considered to be the second interval.
- Step S26 removing each edge point below the second interval point, and then proceeds to step S27;
- Step S27 scanning the edge feature image obtained after removing the edge point from bottom to top, determining whether there is a second interval point; if yes, then proceeding to step S26, if no, then proceeding to step S210;
- Step S28 removing the respective edge points on the right side of the first interval point, and then moving to step S29;
- Step S29 the edge feature image obtained after the edge point is removed is scanned from right to left to determine whether there is a first interval point; if yes, then go to step S28, if no, then go to step S210;
- Step S210 outputting an edge feature image.
- FIG. 3 The image of the logo area before and after processing by the image processing method provided by the embodiment of the present invention can be referred to FIG. 3, in which the text portion of each logo area image is processed and removed.
- the apparatus may include:
- An edge extraction module 41 configured to acquire an edge feature image of the logo area image
- the first correction module 42 is configured to remove each edge point on the right side of the first interval point when the edge feature image of the logo area image has a first interval point;
- the second correction module 43 is configured to remove each edge point below the second interval point when the edge feature image of the logo area image has a second interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- the edge extraction module 41 is specifically configured to separately preprocess a plurality of images including the logo area image to obtain a logo area image in each screen; and respectively obtain each of the obtained logo area images Perform edge feature extraction to synthesize each extracted image The edge feature image is obtained.
- the first correction module 42 is further configured to scan the edge feature image from left to right before removing each edge point on the right side of the first interval point, and determine whether the edge feature image has a An interval point;
- the second correction module 43 is further configured to scan the edge feature image from top to bottom before removing the edge points below the second interval point to determine whether the edge feature image has a second interval point.
- the image processing apparatus may further include: not shown in the figure:
- the obtaining module 44 is configured to obtain a minimum circumscribed rectangle including each edge point;
- the determining module 45 is configured to scan the edge feature image from left to right only when the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio;
- the first correction module 41 may be specifically configured to scan the edge feature image in the minimum circumscribed rectangle from left to right; and/or,
- the second correction module is configured to scan the edge feature image from top to bottom when the aspect ratio of the minimum circumscribed rectangle is greater than or equal to a preset aspect ratio.
- the preset aspect ratio has a value of 1.5.
- the first correction module 41 may be specifically configured to scan only the edge feature images in the minimum circumscribed rectangle from left to right; and/or,
- the second correction module 42 can be specifically configured to scan the edge feature image in the minimum circumscribed rectangle from top to bottom.
- the first correction module 41 is specifically configured to scan the edge feature image in the minimum circumscribed rectangle from left to right with the nth/xth column pixel from left to right as a starting column; and/or,
- the second modified scan module 42 is specifically configured to scan the edge feature image in the minimum circumscribed rectangle from top to bottom with the m/y row of pixel points from top to bottom as a starting line;
- n is the total number of columns of edge feature images within the minimum circumscribed rectangle
- m is the total number of rows of edge feature images within the minimum circumscribed rectangle
- x and y are both preset values.
- the x is 6, and the y is 3.
- the above image processing apparatus may further include: not shown in the figure:
- a third correction module 46 configured to scan an edge feature image obtained after removing each edge point on the right side of the first interval point from right to left, and remove the first edge when scanning to the first interval point a respective edge point to the right of an interval; and/or,
- a fourth correction module 47 configured to scan an edge feature image obtained after removing each edge point below the second interval point from bottom to top, and remove the second interval when scanning to a second interval point Each edge point below the point.
- the embodiment of the invention further provides a structural block diagram of an image processing apparatus.
- the image processing apparatus includes: a processor 501, a memory 502, a communication interface 503, and a bus 504.
- the processor 501, the memory 502, and the communication interface 503 complete communication with each other through the bus 504;
- the communication interface 503 is used for information transmission between the image processing device and a communication device of the image storage device or the image transmission device;
- the processor 501 is configured to invoke logic instructions in the memory 502 to perform the following methods;
- edge feature image of the logo area image has a first interval point, removing each edge point on the right side of the first interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point For an edge point in the edge feature image, the edge point and the adjacent edge point below it are spaced apart by a background point exceeding a preset number of lines.
- an embodiment of the present invention further discloses a computer program, including program code, where the program code is used to perform the following operations:
- edge feature image of the logo area image has a first interval point, removing each edge point on the right side of the first interval point;
- the first interval point is an edge point in the edge feature image, and the edge point is spaced from the adjacent edge point on the right side by a background point exceeding a preset number of columns; the second interval point Is an edge point in the edge feature image, the edge point and an adjacent edge below it There is a background point between the points that exceeds the preset number of lines.
- the embodiment of the invention discloses a storage medium for storing a computer program as described in the foregoing embodiments.
- the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
- the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
- the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
一种图像处理方法和装置,该方法包括:获取台标区域图像的边缘特征图像(S11);在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点(S12);在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点(S13)。由于一般的台标中,图标部分和文字部分之间存在间隔,且图标部分内部连续且文字部分一般位于图标部分的下方或者右方,通过上述方法能够快速准确的去除台标中的文字部分。
Description
交叉引用
本申请引用于2015年11月24日提交的专利名称为“图像处理方法和装置”的第2015108241848号中国专利申请,其通过引用被全部并入本申请。
本发明实施例涉及视频技术领域,尤其涉及一种图像处理方法和装置。
在实际的图像处理问题中,图像的边缘特征作为图像的一种基本特征,被经常应用到较高层次的特征描述、图像识别、图像分割、图像增强以及图像压缩等的图像处理和分析技术中,从而可对图像作进一步的分析和理解。
通常在图像获取、传输和处理过程中,总会不可避免地存在各种噪声,且噪声与图像边缘的频带混合在一起,这使得提取到的边缘特征图像不够准确。
发明内容
本发明实施例提供了一种图像处理方法和装置,用以去除台标区域图像中的文字部分。
第一方面,本发明实施例提供了一种图像处理方法,包括:
获取台标区域图像的边缘特征图像;
在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点
为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
第二方面,本发明实施例提供了一种图像处理装置,包括:
边缘提取模块,用于获取台标区域图像的边缘特征图像;;
第一修正模块,用于在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
第二修正模块,用于在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
第三方面,本发明实施例提供了一种图像处理装置,包括:
处理器、存储器、通信接口和总线;其中,
所述处理器、存储器、通信接口通过所述总线完成相互间的通信;
所述通信接口用于该图像处理装置与图像储存装置或图像传输装置的通信设备之间的信息传输;
所述处理器用于调用所述存储器中的逻辑指令,以执行如下方法;
获取台标区域图像的边缘特征图像;
在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
第四方面,本发明实施例提供了一种计算机程序,其特征在于,包括程序代码,所述程序代码用于执行如下操作:
获取台标区域图像的边缘特征图像;
在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第
一间隔点右侧的各个边缘点;
在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
针对所标记的多个连通域中的每一个连通域,判断该连通域具有的边缘点的数量是否大于第一预设值;并在判断为否时,将该连通域所具有的各个边缘点均置为背景点。
第五方面,本发明实施例提供了一种存储介质,用于存储如上述所述的计算机程序。
本发明实施例提供的图像处理方法和装置中,在获取台标区域图像的边缘特征图像后,在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点。由于一般的台标中,图标部分和文字部分之间存在间隔,且图标部分内部连续且文字部分一般位于图标部分的下方或者右方,通过本发明实施例提供的图像处理方法能够快速准确的去除台标中的文字部分。
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的一种图像处理方法的流程示意图;
图2为本发明实施例提供的另一种图像处理方法的流程示意图;
图3示出了经本发明实施例提供的图像处理方法处理前后的台标区域图像;
图4为本发明实施例提供的一种图像处理装置的结构框图;
图5为本发明实施例提供的又一种图像处理装置的结构框图。
为使本发明实施例的目的、技术方案和优点更加清楚,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,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
本发明实施例提供了一种图像处理方法,参见图1,该方法包括:
步骤S11,获取台标区域图像的边缘特征图像;
步骤S12,在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
步骤S13,在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
本发明实施例提供的图像处理方法中,在获取台标区域图像的边缘特征图像后,在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点。由于一般的台标中,图标部分和文字部分之间存在间隔,且图标部分内部连续且文字部分一般位于图标部分的下方或者右方,通过本发明实施例提供的图像处理方法能够快速准确的去除台标中的文字部分。
在具体实施时,上述的步骤S11可以具体包括图中为示出的:
步骤S111,对多幅包含所述台标区域图像的画面进行分别预处理,得到每一幅画面中的台标区域图像;
步骤S112,对得到的每一幅台标区域图像分别进行边缘特征提取,将针对各幅台标区域图像提取得到的图像进行合成得到所述边缘特征图像。
这样能够使得所得到的边缘特征图像更为准确,从而能够使得在后续的过程中准确的获得到第一间隔点和第二间隔点,从而准确完成相应的文字去除过程。
具体来说,上述的步骤S111中的预处理过程可以是指对包含台标区域图像的整幅电视画面进行分割,得到左上角台标区域的图像,之后进行灰度化和灰度增强,为步骤S112中的边缘特征提取做准备。
具体来说,上述的步骤S112中,可以通过Canny算法对各幅台标区域图像进行边缘提取,强弱边缘阈值可以分别为200、50。对各幅边缘提取得到的图像进行合成的过程可以具体是指:针对各幅经边缘特征提取得到的图像所包含的多个边缘点中的每一个边缘点,确定该边缘点在各幅图像中的同一坐标位置出现的次数是否大于一个预设次数,如果否,将该边缘点置为背景点;之后将各幅初始边缘特征图像中剩余的边缘点合并得到目标图像的边缘特征图像。
在具体实施时,在上述的步骤S12之前,上述的方法还可以包括:
对所述边缘特征图像从左向右进行扫描,确定所述边缘特征图像是否具有第一间隔点。
在上述的步骤S13之前,上述的方法还可以包括:对所述边缘特征图像从上向下进行扫描,确定所述边缘特征图像是否具有第二间隔点。
这样做的好处是,能够自动的确定相应的台标中是否存在间隔点(存在间隔点时,一般都会存在文字),从而减少人为干预。当然在实际应用中,也可以人为的确定是否存在间隔点,并输入间隔点的坐标位置。
在对所述边缘特征图像扫描之前,所述方法还包括:
获取包含边缘特征图像中的各个边缘点的最小外接矩形;
判断所述最小外接矩形的长宽比是否大于等于预设长宽比;
所述步骤S12具体包括:
仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从左向右进行扫描;和/或,
所述步骤S13具体包括:
仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从上向下进行扫描。
在实现本发明实施例的过程中,发明人发现一个台标区域图像的边缘特征图像对应的最小外接矩形的长宽比非常小,比如小于1.5,则基本可以确定该台标区域图像不包含文字部分。这样也就不可能存在上述的第一间隔点和第二间隔点;相应的,也根本无需对边缘特征图像进行扫描。本发
明实施例中,通过预先获取包含各个边缘点的最小外接矩形;判断所述最小外接矩形的长宽比是否大于等于预设长宽比;并仅在最小外接矩形的长宽比大于等于预设长宽比时才进行扫描,能够减少不必要的扫描,从而降低相应的资源消耗。不难理解的是,这里的最小外接矩形的“长”是指最小外接矩形在列方向的长度,具体来说,可以是指在所包含的像素点的行数;而“宽”则是指最小外接矩形在行方向的长度,具体来说,可以是指所包含的像素点的列数。
不难理解的是,这里所指的包含各个边缘点的最小外接图形是指以各个边缘点所组成的轮廓为目标得到的该轮廓的外接图形。
另外,在具体实施时,在获取包含各个边缘点的最小外接矩形的情况下,上述步骤S12中可以仅对最小外接矩形内的边缘特征图像(即最小外接矩形内的二值化矩阵)从左向右进行扫描;相应的,步骤S13中可以仅对最小外接矩形内的边缘特征图像从上向下进行扫描。
这样能够减少所需扫描的边缘特征图像的区域,从而进一步降低相应的资源消耗。
在具体实施时,上述的步骤S12可以具体包括:以从左向右的第n/x列像素点为起始列对所述最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,
上述的步骤S13可以具体包括:以从上向下的第m/y行像素点为起始行对所述最小外接矩形内的边缘特征图像从上向下进行扫描;
其中,n为所述边缘特征图像的总列数;m为所述边缘特征图像的总行数;x和y均为预设值。
在实际应用中,明显没有文字和图标的区域是不需要进行扫描的,比如在竖直方向上,图标位于文字之上,文字不可能出现在区域高度1/3之内,这样一般在自上而下的前m/3列像素点中不可能扫描到第二间隔点。水平方向上,可能会出现4个文字,如东南卫视等,此时图标只占台标区域图像的宽度的1/5左右,而深圳卫视则在1/6左右,但是文字基本不可能出现在自左侧的前1/6宽度处,则在前1/6宽度内,一般也不会扫描到第一间隔点。采用上述的方式执行步骤S12和步骤S13,并不会导致漏扫描第一间隔点和第二间隔点的情况,并且能够降低所需扫描的像素点的数量,从而缩短扫描时间并降低所需使用的资源,提高文字去除的效率。在
具体实施时,这里的x的取值和y的取值可以根据实际情况设定,作为一种优选的方式,这里的x的取值可以为6,y的取值可以为3。
在具体实施时,在步骤S13之后,上述的方法还可以包括:对在去除所述第一间隔点右侧的各个边缘点之后得到的边缘特征图像从右向左进行扫描,并在扫描到第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
相应的,在步骤S14之后,相应的方法还可以包括:对在去除所述第二间隔点下方的各个边缘点之后得到的边缘特征图像从下向上进行扫描,并在扫描到第二间隔点时,去除所述第二间隔点下方的各个边缘点。
这样可以避免因为单向扫描中出现的误判导致文字部分没有被去除的现象。
在具体实施时,上述的预设行数可以根据台标区域图像的边缘特征图像的像素点的总行数确定,相应的,预设列数可以根据台标区域图像的边缘特征图像的像素点的总列数确定。台标区域图像的边缘特征图像的像素点的总行数为50行,列数为200列时,这里的预设行数的取值可以为5,预设列数的取值可以为7或8。
下面结合具体的应用场景对本发明实施例提供的图像处理方法进行进一步的说明,参见图2,该方法包括:
步骤S21,获取台标区域图像的边缘特征图像;
步骤S22,获取边缘特征图像中的各个边缘点的最小外接矩形;
步骤S23,判断所述最小外接矩形的长宽比r是否大于1.5;若是,则转向步骤S24,若否,则转向步骤S210;
步骤S24,自左侧的第n/6列像素点处对最小外接矩形内的边缘特征图像从左向右进行扫描,判断是否存在第一间隔点;若是,则转向步骤S28;若否,则转向步骤S25。
在具体实施时,可以逐列对各个像素点进行扫描,若在包含边缘点的一列像素之后的8列像素内均没有发现边缘点,则可以确定该边缘点可能为间隔点,之后继续扫描,如果在该列像素点之后没有再发现边缘点,则该像素点并不是真正的第一间隔点,若在该列像素点之后还发现有边缘点,则认为该点是第一间隔点。
步骤S25,对上方的第m/3行像素点出对最小外接矩形内的边缘特征图像从上到下进行扫描,判断是否存在第二间隔点;若是,则转向步骤S26;
若否,则转向步骤S210。
在具体实施时,可以逐行对各个像素点进行扫描,若在包含边缘点的一行像素之后的5行像素内均没有发现边缘点,则可以确定该点可能为间隔点,之后继续扫描,如果在该行像素点之后没有再发现边缘点,则该像素点并不是真正的第二间隔点,若在该行像素点之后还发现有边缘点,则认为该点是第二间隔点。
步骤S26,去除第二间隔点下方的各个边缘点,之后转向步骤S27;
步骤S27,对在去除了边缘点之后得到的边缘特征图像从下向上进行扫描,判断是否存在第二间隔点;若是,则转向步骤S26,若否,则转向步骤S210;
步骤S28,去除所述第一间隔点右侧的各个边缘点,之后转向步骤S29;
步骤S29,对在去除了边缘点之后得到的边缘特征图像从右向左进行扫描,判断是否存在第一间隔点;若是,则转向步骤S28,若否,则转向步骤S210;
步骤S210,输出边缘特征图像。
采用本发明实施例提供的图像处理方法处理前后的台标区域的图像可以参考图3,其中的各个台标区域图像经过处理后文字部分被去除。
基于相同的构思,本发明实施例的另一个方面还提供了一种图像处理装置,参见图4,该装置可以包括:
边缘提取模块41,用于获取台标区域图像的边缘特征图像;;
第一修正模块42,用于在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
第二修正模块43,用于在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
进一步的,边缘提取模块41具体用于对多幅包含所述台标区域图像的画面进行分别预处理,得到每一幅画面中的台标区域图像;对得到的每一幅台标区域图像分别进行边缘特征提取,将提取得到的各幅图像进行合成
得到所述边缘特征图像。
进一步的,第一修正模块42,还用于在去除所述第一间隔点右侧的各个边缘点之前,对所述边缘特征图像从左向右进行扫描,确定所述边缘特征图像是否具有第一间隔点;
第二修正模块43,还用于在去除所述第二间隔点下方的各个边缘点之前,对所述边缘特征图像从上向下进行扫描,确定所述边缘特征图像是否具有第二间隔点。
进一步的,所述图像处理装置可以还包括图中未示出的:
获取模块44,用于获取包含各个边缘点的最小外接矩形;
判断模块45,用于仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从左向右进行扫描;
此时,第一修正模块41可以具体用于对最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,
所述第二修正模块,仅用于在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从上向下进行扫描。
进一步的,所述预设长宽比的值为1.5。
进一步的,第一修正模块41可以具体用于仅对最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,
第二修正模块42可以具体用于对最小外接矩形内的边缘特征图像从上向下进行扫描。
进一步的,第一修正模块41具体用于以从左向右的第n/x列像素点为起始列对所述最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,第二修正扫描模块42可以具体用于以从上向下的第m/y行像素点为起始行对所述最小外接矩形内的边缘特征图像从上向下进行扫描;
其中,n为最小外接矩形内的边缘特征图像的总列数;m为最小外接矩形内的边缘特征图像的总行数;x和y均为预设值。
进一步的,所述x为6,所述y为3。
进一步的,上述的图像处理装置还可以包括图中未示出的:
第三修正模块46,用于对在去除所述第一间隔点右侧的各个边缘点之后得到的边缘特征图像从右向左进行扫描,并在扫描到第一间隔点时,去除所述第一间隔点右侧的各个边缘点;和/或,
第四修正模块47,用于对在去除所述第二间隔点下方的各个边缘点之后得到的边缘特征图像从下向上进行扫描,并在扫描到第二间隔点时,去除所述第二间隔点下方的各个边缘点。
本发明实施例还提供了一种图像处理装置的结构框图。参照图5,所述图像处理装置,包括:处理器(processor)501、存储器(memory)502、通信接口(Communications Interface)503和总线504;
其中,
所述处理器501、存储器502、通信接口503通过所述总线504完成相互间的通信;
所述通信接口503用于该图像处理装置与图像储存装置或图像传输装置的通信设备之间的信息传输;;
所述处理器501用于调用所述存储器502中的逻辑指令,以执行如下方法;
获取台标区域图像的边缘特征图像;
在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
参加图1,本发明实施例还公开一种计算机程序,包括程序代码,所述程序代码用于执行如下操作:
获取台标区域图像的边缘特征图像;
在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;
在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;
其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘
点之间间隔有超过预设行数的背景点。
本发明实施例公开一种存储介质,用于存储如前述实施例所述的计算机程序。
本领域普通技术人员可以理解:实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成,前述的程序可以存储于一计算机可读取存储介质中,该程序在执行时,执行包括上述方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下,即可以理解并实施。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件。基于这样的理解,上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品可以存储在计算机可读存储介质中,如ROM/RAM、磁碟、光盘等,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是:以上实施例仅用以说明本发明实施例的技术方案,而非对其限制;尽管参照前述实施例对本发明实施例进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。
Claims (21)
- 一种图像处理方法,其特征在于,包括:获取台标区域图像的边缘特征图像;在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
- 如权利要求1所述的方法,其特征在于,所述获取台标区域图像的边缘特征图像,包括:对多幅包含所述台标区域图像的画面进行分别预处理,得到每一幅画面中的台标区域图像;对得到的每一幅台标区域图像分别进行边缘特征提取,将提取得到的各个图像进行合成得到所述边缘特征图像。
- 如权利要求1所述的方法,其特征在于,所述去除所述第一间隔点右侧的各个边缘点之前,所述方法还包括:对所述边缘特征图像从左向右进行扫描,确定所述边缘特征图像是否具有第一间隔点;所述去除所述第二间隔点下方的各个边缘点之前,所述方法还包括:对所述边缘特征图像从上向下进行扫描,确定所述边缘特征图像是否具有第二间隔点。
- 如权利要求3所述的方法,其特征在于,在对所述边缘特征图像扫描之前,所述方法还包括:获取包含各个边缘点的最小外接矩形;判断所述最小外接矩形的长宽比是否大于等于预设长宽比;所述对边缘特征图像从左向右进行扫描具体包括:仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从左向右进行扫描;和/或,所述对边缘特征图像从上向下进行扫描具体包括:仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从上向下进行扫描。
- 如权利要求4所述的方法,其特征在于,所述预设长宽比的值为1.5。
- 如权利要求3所述的方法,其特征在于,在对所述边缘特征图像扫描之前,所述方法还包括:获取包含各个边缘点的最小外接矩形;所述对边缘特征图像从左向右进行扫描具体包括:仅对最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,所述对边缘特征图像从上向下进行扫描包括:仅对最小外接矩形内的边缘特征图像从上向下进行扫描。
- 如权利要求6所述的方法,其特征在于,所述对最小外接矩形内的边缘特征图像从左向右进行扫描具体为:以从左向右的第n/x列像素点为起始列对所述最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,所述对所述边缘特征图像从上向下进行扫描,包括:以从上向下的第m/y行像素点为起始行对所述最小外接矩形内的边缘特征图像从上向下进行扫描;其中,n为最小外接矩形内的边缘特征图像的总列数;m为最小外接矩形内的边缘特征图像的总行数;x和y均为预设值。
- 如权利要求7所述的方法,其特征在于,所述x为6,所述y为3。
- 如权利要求3-8任一项所述的方法,其特征在于,所述方法还包括:对在去除所述第一间隔点右侧的各个边缘点之后得到的边缘特征图像从右向左进行扫描,并在扫描到第一间隔点时,去除所述第一间隔点右侧的各个边缘点;和/或,对在去除所述第二间隔点下方的各个边缘点之后得到的边缘特征图像从下向上进行扫描,并在扫描到第二间隔点时,去除所述第二间隔点下方的各个边缘点。
- 一种图像处理装置,其特征在于,包括:边缘提取模块,用于获取台标区域图像的边缘特征图像;第一修正模块,用于在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;第二修正模块,用于在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
- 如权利要求10所述的装置,其特征在于,所述边缘提取模块具体用于对多幅包含所述台标区域图像的画面进行分别预处理,得到每一幅画面中的台标区域图像;对得到的每一幅台标区域图像分别进行边缘特征提取,将提取得到的各个图像进行合成得到所述边缘特征图像。
- 如权利要求10所述的装置,其特征在于,第一修正模块,还用于在去除所述第一间隔点右侧的各个边缘点之前,对所述边缘特征图像从左向右进行扫描,确定所述边缘特征图像是否具有第一间隔点;第二修正模块,还用于在去除所述第二间隔点下方的各个边缘点之前,对所述边缘特征图像从上向下进行扫描,确定所述边缘特征图像是否具有第二间隔点。
- 如权利要求12所述的装置,其特征在于,还包括:获取模块,用于获取包含各个边缘点的最小外接矩形;判断模块,用于仅在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从左向右进行扫描;所述第一修正模块具体用于对最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,所述第二修正模块,仅用于在所述最小外接矩形的长宽比大于等于预设长宽比时对边缘特征图像从上向下进行扫描。
- 如权利要求13所述的装置,其特征在于,所述预设长宽比的值为1.5。
- 如权利要求12所述的装置,其特征在于,还包括:获取模块,用于获取包含各个边缘点的最小外接矩形;所述第一修正模块具体用于仅对最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,所述第二修正模块具体用于对最小外接矩形内的边缘特征图像从上向下进行扫描。
- 如权利要求15所述的装置,其特征在于,所述第一修正模块具体用于以从左向右的第n/x列像素点为起始列对所述最小外接矩形内的边缘特征图像从左向右进行扫描;和/或,所述第二修正扫描模块具体用于以从上向下的第m/y行像素点为起始行对所述最小外接矩形内的边缘特征图像从上向下进行扫描;其中,n为最小外接矩形内的边缘特征图像的总列数;m为最小外接矩形内的边缘特征图像的总行数;x和y均为预设值。
- 如权利要求16所述的装置,其特征在于,所述x为6,所述y为3。
- 如权利要求11-17任一项所述的装置,其特征在于,第三修正模块,用于对在去除所述第一间隔点右侧的各个边缘点之后得到的边缘特征图像从右向左进行扫描,并在扫描到第一间隔点时,去除所述第一间隔点右侧的各个边缘点;和/或,第四修正模块,用于对在去除所述第二间隔点下方的各个边缘点之后得到的边缘特征图像从下向上进行扫描,并在扫描到第二间隔点时,去除所述第二间隔点下方的各个边缘点。
- 一种图像处理装置,其特征在于,包括:处理器、存储器、通信接口和总线;其中,所述处理器、存储器、通信接口通过所述总线完成相互间的通信;所述通信接口用于该图像处理装置与图像储存装置或图像传输装置的通信设备之间的信息传输;所述处理器用于调用所述存储器中的逻辑指令,以执行如下方法;获取台标区域图像的边缘特征图像;在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点。
- 一种计算机程序,其特征在于,包括程序代码,所述程序代码用于执行如下操作:获取台标区域图像的边缘特征图像;在所述台标区域图像的边缘特征图像具有第一间隔点时,去除所述第一间隔点右侧的各个边缘点;在所述台标区域图像的边缘特征图像具有第二间隔点时,去除所述第二间隔点下方的各个边缘点;其中,所述第一间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其右侧的相邻边缘点之间间隔有超过预设列数的背景点;所述第二间隔点为所述边缘特征图像中的一个边缘点,该边缘点与其下方的相邻边缘点之间间隔有超过预设行数的背景点,针对所标记的多个连通域中的每一个连通域,判断该连通域具有的边缘点的数量是否大于第一预设值;并在判断为否时,将该连通域所具有的各个边缘点均置为背景点。
- 一种存储介质,用于存储如权利要求20所述的计算机程序。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US15/246,268 US20170148170A1 (en) | 2015-11-24 | 2016-08-24 | Image processing method and apparatus |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510824184.8 | 2015-11-24 | ||
| CN201510824184.8A CN105869140A (zh) | 2015-11-24 | 2015-11-24 | 图像处理方法和装置 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US15/246,268 Continuation US20170148170A1 (en) | 2015-11-24 | 2016-08-24 | Image processing method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017088463A1 true WO2017088463A1 (zh) | 2017-06-01 |
Family
ID=56623733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/086602 Ceased WO2017088463A1 (zh) | 2015-11-24 | 2016-06-21 | 图像处理方法和装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105869140A (zh) |
| WO (1) | WO2017088463A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119788968A (zh) * | 2024-12-23 | 2025-04-08 | 山东神戎电子股份有限公司 | 一种云台的扫描控制方法、装置及介质 |
| CN119810068A (zh) * | 2024-12-20 | 2025-04-11 | 北京航空航天大学 | 一种面向多种微生物图像的轮廓快速标记和查找方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472260B (zh) * | 2018-10-31 | 2021-07-27 | 成都索贝数码科技股份有限公司 | 一种基于深度神经网络的移除图像内台标和字幕的方法 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002095663A2 (en) * | 2001-05-23 | 2002-11-28 | Koninklijke Philips Electronics N.V. | Text discrimination method and related apparatus |
| CN101950366A (zh) * | 2010-09-10 | 2011-01-19 | 北京大学 | 一种台标检测和识别的方法 |
| CN102446272A (zh) * | 2011-09-05 | 2012-05-09 | Tcl集团股份有限公司 | 一种台标分割及识别的方法、装置及电视机 |
| CN102567727A (zh) * | 2010-12-13 | 2012-07-11 | 中兴通讯股份有限公司 | 一种背景目标替换方法和装置 |
| CN102831611A (zh) * | 2012-08-21 | 2012-12-19 | 北京捷成世纪科技股份有限公司 | 一种电视节目中挂角广告的提取方法及装置 |
| US20130136350A1 (en) * | 2011-11-28 | 2013-05-30 | Industrial Technology Research Institute | Apparatus and method for foreground detection |
| CN105869139A (zh) * | 2015-11-24 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | 图像处理方法和装置 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4280355B2 (ja) * | 1999-05-06 | 2009-06-17 | 富士通株式会社 | 文字認識装置 |
| US20020065635A1 (en) * | 1999-12-02 | 2002-05-30 | Joseph Lei | Virtual reality room |
| CN1265324C (zh) * | 2003-11-06 | 2006-07-19 | 上海交通大学 | 基于相邻边缘点距离统计的文字图象分割方法 |
| CN100384245C (zh) * | 2005-12-27 | 2008-04-23 | 天津三星电子显示器有限公司 | 数字电视机增设中文台标标识的方法 |
| CN102801657A (zh) * | 2012-09-03 | 2012-11-28 | 鲁赤兵 | 一种复合型微博系统和方法 |
| CN103544467B (zh) * | 2013-04-23 | 2017-09-05 | Tcl集团股份有限公司 | 一种台标检测识别的方法及其装置 |
-
2015
- 2015-11-24 CN CN201510824184.8A patent/CN105869140A/zh active Pending
-
2016
- 2016-06-21 WO PCT/CN2016/086602 patent/WO2017088463A1/zh not_active Ceased
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002095663A2 (en) * | 2001-05-23 | 2002-11-28 | Koninklijke Philips Electronics N.V. | Text discrimination method and related apparatus |
| CN101950366A (zh) * | 2010-09-10 | 2011-01-19 | 北京大学 | 一种台标检测和识别的方法 |
| CN102567727A (zh) * | 2010-12-13 | 2012-07-11 | 中兴通讯股份有限公司 | 一种背景目标替换方法和装置 |
| CN102446272A (zh) * | 2011-09-05 | 2012-05-09 | Tcl集团股份有限公司 | 一种台标分割及识别的方法、装置及电视机 |
| US20130136350A1 (en) * | 2011-11-28 | 2013-05-30 | Industrial Technology Research Institute | Apparatus and method for foreground detection |
| CN102831611A (zh) * | 2012-08-21 | 2012-12-19 | 北京捷成世纪科技股份有限公司 | 一种电视节目中挂角广告的提取方法及装置 |
| CN105869139A (zh) * | 2015-11-24 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | 图像处理方法和装置 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119810068A (zh) * | 2024-12-20 | 2025-04-11 | 北京航空航天大学 | 一种面向多种微生物图像的轮廓快速标记和查找方法 |
| CN119788968A (zh) * | 2024-12-23 | 2025-04-08 | 山东神戎电子股份有限公司 | 一种云台的扫描控制方法、装置及介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105869140A (zh) | 2016-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10572728B2 (en) | Text image processing method and apparatus | |
| US10582124B2 (en) | Target image quality enhancement using a guide image | |
| JP6262176B2 (ja) | 文書画像における縦線および横線の検出および削除 | |
| US12198353B2 (en) | Methods and systems for automatically generating backdrop imagery for a graphical user interface | |
| CN111275034B (zh) | 从图像中提取文本区域的方法、装置、设备和存储介质 | |
| EP3610453B1 (en) | Synthetic long exposure image with optional enhancement using a guide image | |
| CN111461070B (zh) | 文本识别方法、装置、电子设备及存储介质 | |
| WO2017088462A1 (zh) | 图像处理方法和装置 | |
| RU2721188C2 (ru) | Улучшение контраста и снижение шума на изображениях, полученных с камер | |
| WO2017076040A1 (zh) | 应用于连拍过程中的图像处理方法和装置 | |
| CN111445424A (zh) | 图像处理和移动终端视频处理方法、装置、设备和介质 | |
| CN109272526B (zh) | 图像处理方法、系统及电子设备 | |
| WO2017088463A1 (zh) | 图像处理方法和装置 | |
| CN114648751B (zh) | 一种处理视频字幕的方法、装置、终端及存储介质 | |
| JP6963038B2 (ja) | 画像処理装置および画像処理方法 | |
| CN114079815B (zh) | 字幕保护方法、系统、终端设备及存储介质 | |
| CN113658196A (zh) | 红外图像中船舶的检测方法、装置、电子设备和介质 | |
| US20170148170A1 (en) | Image processing method and apparatus | |
| CN116883272A (zh) | 一种保持增强与马赛克增强结合的数据处理方法及装置 | |
| CN111046727B (zh) | 视频特征提取方法及装置、电子设备及存储介质 | |
| CN114841906A (zh) | 一种图像合成方法、装置、电子设备和存储介质 | |
| CN106934814B (zh) | 一种基于图像的背景信息识别方法及装置 | |
| CN105869123A (zh) | 图像处理方法和装置 | |
| CN105869139A (zh) | 图像处理方法和装置 | |
| US20170147895A1 (en) | Method and device for digit separation |
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: 16867690 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: 16867690 Country of ref document: EP Kind code of ref document: A1 |