CN101923710A - Image tilt correction method and device - Google Patents

Abstract

Translated fromChinese

本发明提供一种图像倾斜校正方法及装置。图像倾斜校正方法，包括：对获取的图像进行灰度处理，以获得灰度图像；对所述灰度图像进行投影处理，以判断所述灰度图像是否倾斜；若所述灰度图像倾斜，则对所述灰度图像进行倾斜校正处理。通过对灰度图像进行投影处理，以判断出灰度图像是否倾斜，若灰度图像处于倾斜状态则对该灰度图像进行倾斜校正处理，而对于没有倾斜的灰度图像不进行倾斜校正处理，提高了图像倾斜校正方法的校正效率。

The invention provides an image tilt correction method and device. The image tilt correction method includes: performing grayscale processing on the acquired image to obtain a grayscale image; performing projection processing on the grayscale image to determine whether the grayscale image is tilted; if the grayscale image is tilted, Then, tilt correction processing is performed on the grayscale image. By performing projection processing on the gray-scale image to determine whether the gray-scale image is tilted, if the gray-scale image is in a tilted state, the tilt correction process is performed on the gray-scale image, and no tilt correction process is performed on the gray-scale image without tilt. The correction efficiency of the image tilt correction method is improved.

Description

Translated fromChinese

图像倾斜校正方法及装置Image tilt correction method and device

技术领域technical field

本发明涉及图像处理技术领域，尤其涉及一种图像倾斜校正方法及装置。The present invention relates to the technical field of image processing, in particular to an image tilt correction method and device.

背景技术Background technique

目前，随着智能交通系统的发展，图像处理技术被广泛的应用于智能交通系统中。在智能交通系统中，通常采用图像识别技术对车辆的车牌进行图像识别，从而实现自动获得车辆的车牌号。At present, with the development of intelligent transportation systems, image processing technology is widely used in intelligent transportation systems. In the intelligent transportation system, the image recognition technology is usually used to recognize the license plate of the vehicle, so as to realize the automatic acquisition of the license plate number of the vehicle.

由于不同道路环境的影响，行驶在道路上的车辆会出现倾斜的情况。为了准确的获得车辆的车牌信息，现有技术中的车牌图像识别系统，需要对所有检测到的车辆的车牌进行图像校正处理，使车牌的图像能够便于图像识别系统识别出车牌的号码。Due to the influence of different road environments, vehicles driving on the road will appear inclined. In order to accurately obtain the license plate information of the vehicle, the license plate image recognition system in the prior art needs to perform image correction processing on the license plate of all detected vehicles, so that the image of the license plate can facilitate the image recognition system to recognize the number of the license plate.

由上可知，现有技术中的图像校正处理方法对所有检测到的图像均进行校正处理，而对于没有发生倾斜的车辆也进行图像校正处理，大大增加了图像校正处理的负担，影响了对车牌发生倾斜的车辆进行图像校正处理的速度，降低了图像校正处理的校正效率。因此，现有技术中的图像校正方法的处理效率低。It can be seen from the above that the image correction processing method in the prior art performs correction processing on all detected images, and also performs image correction processing on vehicles that do not tilt, which greatly increases the burden of image correction processing and affects the detection of license plates. The speed at which the image correction process is performed by the tilted vehicle reduces the correction efficiency of the image correction process. Therefore, the processing efficiency of the image correction method in the prior art is low.

发明内容Contents of the invention

本发明提供一种图像倾斜校正方法及装置，用以解决现有技术中图像倾斜校正方法效率低的缺陷，实现提高图像倾斜校正方法的校正效率。The present invention provides an image tilt correction method and device, which are used to solve the defect of low efficiency of the image tilt correction method in the prior art, and improve the correction efficiency of the image tilt correction method.

本发明提供一种图像倾斜校正方法，包括：The present invention provides an image tilt correction method, comprising:

对获取的图像进行灰度处理，以获得灰度图像；Perform grayscale processing on the acquired image to obtain a grayscale image;

对所述灰度图像进行投影处理，以判断所述灰度图像是否倾斜；performing projection processing on the grayscale image to determine whether the grayscale image is tilted;

若所述灰度图像倾斜，则对所述灰度图像进行倾斜校正处理。If the grayscale image is tilted, performing tilt correction processing on the grayscale image.

本发明提供一种图像倾斜校正装置，包括：The present invention provides an image tilt correction device, comprising:

灰度处理模块，用于对获取的图像进行灰度处理，以获得灰度图像；A grayscale processing module, configured to perform grayscale processing on the acquired image to obtain a grayscale image;

投影处理模块，用于对所述灰度图像进行投影处理，以判断所述灰度图像是否倾斜；A projection processing module, configured to perform projection processing on the grayscale image to determine whether the grayscale image is tilted;

校正处理模块，用于若所述灰度图像倾斜，则对所述灰度图像进行倾斜校正处理。The correction processing module is configured to perform tilt correction processing on the grayscale image if the grayscale image is skewed.

本发明提供的图像倾斜校正方法及装置，通过对灰度图像进行投影处理，以判断出灰度图像是否倾斜，若灰度图像处于倾斜状态则对该灰度图像进行倾斜校正处理，而对于没有倾斜的灰度图像不进行倾斜校正处理，提高了图像倾斜校正方法的校正效率。The image tilt correction method and device provided by the present invention can judge whether the gray-scale image is tilted by performing projection processing on the gray-scale image, and if the gray-scale image is in a tilted state, perform tilt correction processing on the gray-scale image. The tilted grayscale image is not subjected to tilt correction processing, which improves the correction efficiency of the image tilt correction method.

附图说明Description of drawings

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性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

图1为本发明图像倾斜校正方法实施例的流程图；Fig. 1 is a flow chart of an embodiment of the image tilt correction method of the present invention;

图2为本发明图像倾斜校正方法实施例中步骤102的具体流程图；FIG. 2 is a specific flowchart ofstep 102 in an embodiment of the image tilt correction method of the present invention;

图3为本发明图像倾斜校正方法实施例中步骤103的具体流程图；FIG. 3 is a specific flowchart ofstep 103 in an embodiment of the image tilt correction method of the present invention;

图4为本发明图像倾斜校正装置实施例的结构示意图。FIG. 4 is a schematic structural diagram of an embodiment of an image tilt correction device according to the present invention.

图5为本发明图像倾斜校正装置实施例中投影处理模块的结构示意图；5 is a schematic structural diagram of the projection processing module in the embodiment of the image tilt correction device of the present invention;

图6为本发明图像倾斜校正装置实施例中校正处理模块的结构示意图。FIG. 6 is a schematic structural diagram of a correction processing module in an embodiment of an image tilt correction device according to the present invention.

具体实施方式Detailed ways

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。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work fall within the protection scope of the present invention.

图1为本发明图像倾斜校正方法实施例的流程图。如图1所示，本实施例图像倾斜校正方法，包括：FIG. 1 is a flowchart of an embodiment of an image tilt correction method of the present invention. As shown in Figure 1, the image tilt correction method in this embodiment includes:

步骤101、对获取的图像进行灰度处理，以获得灰度图像。Step 101. Perform grayscale processing on the acquired image to obtain a grayscale image.

具体而言，本实施例中的步骤101对获取的图像信息进行处理，使处理后的图像变为灰度图像。本实施例以智能交通系统中对车辆车牌进行检测为例进行说明，通过道路上设置的摄像头等图像获取设备，获得道路上行驶的车辆车牌的图像信息，然后，通过步骤101对车牌的图像信息进行灰度处理，以得到车牌图像的灰度图像。Specifically,step 101 in this embodiment processes the acquired image information to make the processed image into a grayscale image. In this embodiment, the detection of vehicle license plates in the intelligent transportation system is taken as an example for illustration. Through image acquisition devices such as cameras installed on the road, the image information of the vehicle license plates running on the road is obtained, and then the image information of the license plates is processed bystep 101. Perform grayscale processing to obtain a grayscale image of the license plate image.

步骤102、对灰度图像进行投影处理，以判断灰度图像是否倾斜。Step 102: Perform projection processing on the grayscale image to determine whether the grayscale image is tilted.

具体而言，通过步骤101获得车牌的灰度图像后，通过步骤102对获得的灰度图像进行投影处理，根据投影获得的图像信息该判断灰度图像是否是倾斜状态。Specifically, after the grayscale image of the license plate is obtained throughstep 101, projection processing is performed on the obtained grayscale image throughstep 102, and it is judged whether the grayscale image is in an inclined state according to the image information obtained through projection.

步骤103、若灰度图像倾斜，则对灰度图像进行倾斜校正处理。Step 103, if the grayscale image is skewed, perform skew correction processing on the grayscale image.

具体而言，当灰度图像通过步骤102投影处理得知该灰度图像为倾斜的图像后，则通过步骤103对该灰度图像进行倾斜校正处理。例如：当通过步骤102得知获得的车牌的灰度图像为倾斜状态后，则可以判断检测到的车辆的车牌为倾斜的车牌，需要对倾斜的车牌进行倾斜校正处理，则通过步骤103对车牌的灰度图像进行校正处理，以获得无倾斜角度的车牌的灰度图像，以便后续程序根据无倾斜角度的灰度图像获得车牌号。Specifically, after the grayscale image is projected instep 102 and it is known that the grayscale image is an oblique image, the grayscale image is subjected to oblique correction processing instep 103 . For example: afterstep 102 learns that the grayscale image of the license plate obtained is an inclined state, then it can be judged that the license plate of the detected vehicle is an inclined license plate, and it is necessary to carry out inclination correction processing to the inclined license plate, then bystep 103, the license plate is corrected. The grayscale image of the license plate is corrected to obtain the grayscale image of the license plate without inclination angle, so that the subsequent program can obtain the license plate number based on the gray image without inclination angle.

其中，本实施例图像倾斜校正方法可以应用于智能交通系统的车牌识别系统中，也可以用于其他需要对图像进行倾斜校正处理的场合。Wherein, the image tilt correction method of this embodiment can be applied to the license plate recognition system of the intelligent transportation system, and can also be used in other occasions that require tilt correction processing on the image.

本实施例图像倾斜校正方法，通过对灰度图像进行投影处理，以判断出灰度图像是否倾斜，若灰度图像处于倾斜状态则对该灰度图像进行倾斜校正处理，而对于没有倾斜的灰度图像不进行倾斜校正处理，提高了图像倾斜校 正方法的校正效率。另外，本实施例图像倾斜校正方法仅对处于倾斜状态的图像进行倾斜校正处理，而非倾斜的的图像无需进行倾斜校正处理，从而有效的避免非倾斜的图像出现图像信息损失，有利于提高图像整个处理过程的效率。The method for correcting the image inclination in this embodiment is to judge whether the grayscale image is tilted by performing projection processing on the grayscale image. The high-degree image is not subjected to tilt correction processing, which improves the correction efficiency of the image tilt correction method. In addition, the image inclination correction method in this embodiment only performs inclination correction processing on images in an inclining state, and does not need to perform inclination correction processing on non-inclined images, thereby effectively avoiding image information loss in non-inclined images, and is conducive to improving efficiency of the entire process.

基于上述技术方案，可选的，如图2所示，本实施例中的步骤102具体包括如下步骤：Based on the above technical solution, optionally, as shown in FIG. 2,step 102 in this embodiment specifically includes the following steps:

步骤1021、对灰度图像进行二值化处理，以得到二值化图像。具体的，步骤1021对步骤101获得的灰度图像进行二值化处理，从而将灰度图像转化为二值化图像。例如：车牌的绘图图像经过二值化处理后，车牌号将变为白色，而背景将变为黑色，从而形成黑白的二值化图像。Step 1021, perform binarization processing on the grayscale image to obtain a binarized image. Specifically,step 1021 performs binarization processing on the grayscale image obtained instep 101, thereby converting the grayscale image into a binarized image. For example: after the drawing image of the license plate is binarized, the license plate number will become white, while the background will become black, thus forming a black and white binary image.

步骤1022、对二值化图像进行垂直投影，以获得二值化图像的投影长度。具体的，通过步骤1021将获得灰度图像的二值化图像，步骤1022将对二值化图像进行垂直投影，从而可以获得该二值化图像的投影长度。例如：将车牌的二值化图像进行垂直投影后，会在X轴方向上形成黑白间隔的投影，而投影长度可以是白色投影的总长度、或是白色投影之间的黑色投影的总长度。Step 1022, vertically project the binarized image to obtain the projection length of the binarized image. Specifically,step 1021 will obtain the binarized image of the grayscale image, andstep 1022 will vertically project the binarized image, so that the projection length of the binarized image can be obtained. For example: after the binarized image of the license plate is vertically projected, black and white interval projections will be formed in the X-axis direction, and the projection length can be the total length of the white projections, or the total length of the black projections between the white projections.

步骤1023、将投影长度与预设的投影长度阀值进行比较。具体的，通过步骤1022将二值化图像进行垂直投影后，将获得该二值化图像的白色投影区域的长度以及黑色投影区域的长度。由于二值化图像的投影包括黑白两部分，则投影长度阀值也对应包括有黑色长度阀值和白色长度阀值。其中，黑色长度阀值为处于非倾斜状态的图像进行投影处理后得到的黑色区域的长度值，而白色长度阀值为处于非倾斜状态的图像进行投影处理后得到的白色区域的长度值。对该二值化图像的于白色投影区域的长度可以与投影长度阀值的白色长度阀值进行比较；对于该二值化图像的黑色投影区域的长度可以与投影长度阀值的黑色长度阀值进行比较。Step 1023, comparing the projection length with a preset projection length threshold. Specifically, after the binarized image is vertically projected throughstep 1022, the length of the white projected area and the length of the black projected area of the binarized image will be obtained. Since the projection of the binarized image includes black and white parts, the projection length threshold also includes a black length threshold and a white length threshold. Wherein, the black length threshold value is the length value of the black area obtained after projection processing of the image in the non-slanted state, and the white length threshold value is the length value of the white area obtained after the projection processing of the image in the non-slanted state. The length of the white projection area of the binarized image can be compared with the white length threshold of the projection length threshold; the length of the black projection area of the binary image can be compared with the black length threshold of the projection length threshold Compare.

步骤1024、若二值化图像的黑色的投影长度小于投影长度阀值的黑色长度阀值，则确定灰度图像为倾斜状态；或者，若二值化图像的白色的投影长 度大于投影长度阀值的白色长度阀值，则确定灰度图像为倾斜状态。具体的，以车牌的二值化图像垂直投影后得到的投影长度进行说明。车牌的二值化图像中，车牌号的图像为白色，而背景的图像为黑色。由于车牌号之间的间隔固定不变，当车牌倾斜时，车牌号的白色投影长度会增长，而车牌号之间的背景区域的黑色投影长度会缩短，从而当车牌的二值化图像的黑色的投影长度小于投影长度阀值的黑色长度阀值，则确定灰度图像为倾斜状态，从而确定车牌为倾斜的。或者，当当车牌的二值化图像的白色的投影长度大于投影长度阀值的白色长度阀值，则确定灰度图像为倾斜状态，从而确定车牌为倾斜的。Step 1024, if the black projection length of the binarized image is less than the black length threshold of the projection length threshold, it is determined that the grayscale image is in a tilted state; or, if the white projection length of the binary image is greater than the projection length threshold The white length threshold of the value determines that the grayscale image is in a tilted state. Specifically, the projection length obtained after the vertical projection of the binarized image of the license plate is used for illustration. In the binarized image of the license plate, the image of the license plate number is white, while the image of the background is black. Since the interval between the license plate numbers is fixed, when the license plate is tilted, the white projection length of the license plate number will increase, while the black projection length of the background area between the license plate numbers will be shortened, so when the black of the binarized image of the license plate If the projection length is less than the black length threshold of the projection length threshold, it is determined that the grayscale image is in a tilted state, thereby determining that the license plate is tilted. Alternatively, when the white projection length of the binarized image of the license plate is greater than the white length threshold of the projection length threshold, it is determined that the grayscale image is in a tilted state, thereby determining that the license plate is tilted.

本实施例图像倾斜校正方法，通过对灰度图像进行投影处理得知该灰度图像的投影长度，然后将投影长度与预设的长度阀值进行比较，便可以方便的根据投影长度得知该灰度图像是否为倾斜的，从而更有利于提高本实施例图像倾斜校正方法的校正效率。In the image tilt correction method of this embodiment, the projection length of the grayscale image is obtained by performing projection processing on the grayscale image, and then the projection length is compared with a preset length threshold, and the projection length can be easily obtained. Whether the grayscale image is tilted is more conducive to improving the correction efficiency of the image tilt correction method of this embodiment.

基于上述技术方案，可选的，如图3所述，本实施例中的步骤103具体包括如下步骤：Based on the above technical solution, optionally, as shown in FIG. 3,step 103 in this embodiment specifically includes the following steps:

步骤1031、获取灰度图像的边缘信息。具体的，通过步骤102得知灰度图像是倾斜的后，需要通过步骤103进行倾斜校正处理。步骤1031将对该灰度图像进行处理，以获取灰度图像的边缘信息。为了更加可靠的获得灰度图像的边缘信息，本实施例中的步骤1031可以通过Canny算子获得灰度图像的边缘信息，由于Canny算子能较大范围提高边缘检测的适用范围，从而更有利于准确可靠的获得灰度图像的边缘信息。Step 1031, acquire edge information of the grayscale image. Specifically, after it is known throughstep 102 that the grayscale image is tilted, it is necessary to perform tilt correction processing throughstep 103 .Step 1031 is to process the grayscale image to obtain edge information of the grayscale image. In order to obtain the edge information of the grayscale image more reliably,step 1031 in the present embodiment can obtain the edge information of the grayscale image through the Canny operator, because the Canny operator can improve the scope of application of the edge detection in a large range, thereby more It is beneficial to obtain the edge information of the grayscale image accurately and reliably.

步骤1032、根据边缘信息计算灰度图像的倾斜角。具体的，通过步骤1031获得灰度图像的边缘信息后，通过步骤1032根据边缘信息计算出该灰度图像的倾斜角。为了更加准确有效的提取灰度图像的倾斜角，本实施例中的步骤1032可以通过Hough变换对灰度图像的两侧的边缘信息进行对照处理，以计算出灰度图像的水平倾斜角度。例如：对于倾斜车牌所对应的边缘信息，通 过Hough变换分别对上下两部分车牌的有效边缘信息进行提取，并进行对照处理，可以快速准确的计算出车牌的水平倾角，有效的避免了车牌中部等图像信息干扰线的影响，提高了提取车牌倾角的正确率。Step 1032, calculate the inclination angle of the grayscale image according to the edge information. Specifically, after the edge information of the grayscale image is obtained throughstep 1031, the inclination angle of the grayscale image is calculated according to the edge information throughstep 1032. In order to extract the inclination angle of the grayscale image more accurately and effectively,step 1032 in this embodiment can compare the edge information on both sides of the grayscale image through Hough transform to calculate the horizontal inclination angle of the grayscale image. For example: for the edge information corresponding to the inclined license plate, the effective edge information of the upper and lower parts of the license plate is extracted respectively through Hough transform, and the comparison process is carried out, so that the horizontal inclination angle of the license plate can be calculated quickly and accurately, and the middle part of the license plate can be effectively avoided. The influence of image information interference line improves the accuracy of extracting the inclination angle of the license plate.

步骤1033、根据倾斜角旋转灰度图像，以输出无倾斜角度的灰度图像。具体的，在通过步骤1032计算出灰度图像对应的倾斜角后，可以通过步骤1033根据倾斜角对灰度图像进行旋转处理，以输出无倾斜角度的灰度图像。为了快速可靠的将灰度图像进行旋转，并减小旋转过程中灰度图像的信息损失，本实施例中的步骤1033可以根据倾斜角，通过双线性插值算法对灰度图像进行旋转校正，通过双线性插值算法对灰度图像旋转后，可以获得无倾斜角度的灰度图像，从而可以方便后续的图像处理过程的进行。Step 1033: Rotate the grayscale image according to the tilt angle to output a grayscale image without tilt angle. Specifically, after the inclination angle corresponding to the grayscale image is calculated instep 1032, the grayscale image may be rotated according to the inclination angle instep 1033 to output a grayscale image without inclination angle. In order to quickly and reliably rotate the grayscale image and reduce the information loss of the grayscale image during the rotation process,step 1033 in this embodiment can perform rotation correction on the grayscale image through a bilinear interpolation algorithm according to the tilt angle, After the grayscale image is rotated by the bilinear interpolation algorithm, a grayscale image without tilt angle can be obtained, which facilitates subsequent image processing.

本实施例图像倾斜校正方法，通过获取灰度图像的边缘信息，并根据边缘信息计算出倾斜角，最后，根据倾斜角旋转灰度图像以获得无倾斜角度的灰度图像，可以快速有效的对需要倾斜校正处理的灰度图像进行处理，更有利于提高本实施例图像倾斜校正方法的校正效率。The image tilt correction method in this embodiment obtains the edge information of the grayscale image, calculates the tilt angle according to the edge information, and finally rotates the grayscale image according to the tilt angle to obtain a grayscale image without tilt angle, which can quickly and effectively correct Processing the grayscale images that require tilt correction processing is more conducive to improving the correction efficiency of the image tilt correction method of this embodiment.

图4为本发明图像倾斜校正装置实施例的结构示意图。如图4所示，本实施例图像倾斜校正装置包括：灰度处理模块1、投影处理模块2和校正处理模块3。FIG. 4 is a schematic structural diagram of an embodiment of an image tilt correction device according to the present invention. As shown in FIG. 4 , the image tilt correction device of this embodiment includes: a gray scale processing module 1 , a projection processing module 2 and a correction processing module 3 .

灰度处理模块1用于对获取的图像进行灰度处理，以获得灰度图像；The grayscale processing module 1 is used to perform grayscale processing on the acquired image to obtain a grayscale image;

投影处理模块2用于对灰度图像进行投影处理，以判断灰度图像是否倾斜；The projection processing module 2 is used to project the grayscale image to determine whether the grayscale image is tilted;

校正处理模块3用于若灰度图像倾斜，则对灰度图像进行倾斜校正处理。The correction processing module 3 is configured to perform tilt correction processing on the grayscale image if the grayscale image is tilted.

具体而言，本实施例中的灰度处理模块1将获取到的图像进行灰度处理；然后，投影处理模块2将对灰度处理模块1处理生成的灰度图像进行投影处理，以判断灰度图像是否倾斜；最后，校正处理模块3将对倾斜的灰度图像进行校正处理，以得到正常状态非倾斜的灰度图像。其中，本实施例图像倾斜校正装置的具体处理过程可以参见本发明图像倾斜校正方法实施例的记 载，在此不再赘述。Specifically, the grayscale processing module 1 in this embodiment performs grayscale processing on the acquired image; then, the projection processing module 2 performs projection processing on the grayscale image generated by the grayscale processing module 1 to determine the grayscale Whether the degree image is tilted; finally, the correction processing module 3 will correct the tilted gray-scale image to obtain a normal non-slanted gray-scale image. Wherein, the specific processing process of the image tilt correction device in this embodiment can refer to the records of the embodiment of the image tilt correction method of the present invention, and will not be repeated here.

本实施例图像倾斜校正装置，通过对灰度图像进行投影处理，以判断出灰度图像是否倾斜，若灰度图像处于倾斜状态则对该灰度图像进行倾斜校正处理，而对于没有倾斜的灰度图像不进行倾斜校正处理，提高了图像倾斜校正方法的校正效率。另外，本实施例图像倾斜校正方法仅对处于倾斜状态的图像进行倾斜校正处理，而非倾斜的的图像无需进行倾斜校正处理，从而有效的避免非倾斜的图像出现图像信息损失，有利于提高图像整个处理过程的效率。The image inclination correction device in this embodiment performs projection processing on the grayscale image to determine whether the grayscale image is inclining. The high-degree image does not undergo tilt correction processing, which improves the correction efficiency of the image tilt correction method. In addition, the image inclination correction method in this embodiment only performs inclination correction processing on images in an inclining state, and does not need to perform inclination correction processing on non-inclined images, thereby effectively avoiding image information loss in non-inclined images, and is conducive to improving efficiency of the entire process.

基于上述技术方案，可选的，如图5所示，本实施例中的投影处理模块2包括：投影子模块21、判断子模块22、第一确定子模块23和第二确定子模块24。Based on the above technical solution, optionally, as shown in FIG. 5 , the projection processing module 2 in this embodiment includes: aprojection submodule 21 , ajudgment submodule 22 , afirst determination submodule 23 and asecond determination submodule 24 .

投影子模块21用于对灰度图像进行投影，以获得灰度图像的投影长度；判断子模块22用于判断投影长度是否小于预设的长度阀值；第一确定子模块23用于若投影长度小于长度阀值，则确定灰度图像为倾斜状态；第二确定子模块24用于若投影长度不小于长度阀值，则确定灰度图像为正常状态。Theprojection submodule 21 is used to project the grayscale image to obtain the projection length of the grayscale image; thejudgment submodule 22 is used to judge whether the projection length is less than a preset length threshold; thefirst determination submodule 23 is used to determine if the projection If the length is less than the length threshold, it is determined that the grayscale image is in a tilted state; thesecond determination sub-module 24 is used to determine that the grayscale image is in a normal state if the projection length is not less than the length threshold.

本实施例图像倾斜校正装置，通过对灰度图像进行投影处理得知该灰度图像的投影长度，然后将投影长度与预设的长度阀值进行比较，便可以方便的根据投影长度得知该灰度图像是否为倾斜的，从而更有利于提高本实施例图像倾斜校正方法的校正效率。The image tilt correction device in this embodiment obtains the projection length of the grayscale image by performing projection processing on the grayscale image, and then compares the projection length with a preset length threshold, and can conveniently know the projection length according to the projection length. Whether the grayscale image is tilted is more conducive to improving the correction efficiency of the image tilt correction method of this embodiment.

基于上述技术方案，可选的，如图6所示，本实施例中的校正处理模块3包括：获取子模块31、计算子模块32和旋转子模块33。Based on the above technical solution, optionally, as shown in FIG. 6 , the correction processing module 3 in this embodiment includes: anacquisition submodule 31 , acalculation submodule 32 and arotation submodule 33 .

获取子模块31用于若所述灰度图像倾斜，则获取所述灰度图像的边缘信息；计算子模块32用于根据所述边缘信息计算所述灰度图像的倾斜角；旋转子模块33，用于根据所述倾斜角旋转所述灰度图像，以输出无倾斜角度的所述灰度图像。Theacquisition submodule 31 is used to obtain the edge information of the grayscale image if the grayscale image is inclined; thecalculation submodule 32 is used to calculate the inclination angle of the grayscale image according to the edge information; therotation submodule 33 , for rotating the grayscale image according to the tilt angle, so as to output the grayscale image without tilt angle.

其中，为了更加可靠的获得灰度图像的边缘信息，本实施例中的获取子 模块31还用于通过Canny算子获得灰度图像的边缘信息；为了更加准确有效的提取灰度图像的倾斜角，计算子模块32还用于通过Hough变换对灰度图像的两侧的边缘信息进行对照处理，以计算出灰度图像的水平倾斜角度；为了快速可靠的将灰度图像进行旋转，并减小旋转过程中灰度图像的信息损失，旋转子模块33还用于根据倾斜角，通过双线性插值算法对灰度图像进行旋转校正。Wherein, in order to obtain the edge information of the grayscale image more reliably, theacquisition sub-module 31 in the present embodiment is also used to obtain the edge information of the grayscale image through the Canny operator; in order to more accurately and effectively extract the inclination angle of the grayscale image , thecalculation sub-module 32 is also used to compare the edge information on both sides of the grayscale image through Hough transform to calculate the horizontal tilt angle of the grayscale image; in order to quickly and reliably rotate the grayscale image, and reduce For the information loss of the grayscale image during the rotation, therotation sub-module 33 is also used to correct the rotation of the grayscale image through a bilinear interpolation algorithm according to the tilt angle.

本实施例图像倾斜校正装置，通过获取灰度图像的边缘信息，并根据边缘信息计算出倾斜角，最后，根据倾斜角旋转灰度图像以获得无倾斜角度的灰度图像，可以快速有效的对需要倾斜校正处理的灰度图像进行处理，更有利于提高本实施例图像倾斜校正方法的校正效率。The image tilt correction device in this embodiment obtains the edge information of the grayscale image, calculates the tilt angle according to the edge information, and finally rotates the grayscale image according to the tilt angle to obtain a grayscale image without tilt angle, which can quickly and effectively correct Processing the grayscale images that require tilt correction processing is more conducive to improving the correction efficiency of the image tilt correction method of this embodiment.

最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，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。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (9)

1. an image tilt correction method is characterized in that, comprising:

The image that obtains is carried out gray scale handle, to obtain gray level image;

Described gray level image is carried out projection process, whether tilt to judge described gray level image;

If described gray level image tilts, then described gray level image is carried out slant correction and handle.

2. whether image tilt correction method according to claim 1 is characterized in that, described described gray level image is carried out projection process, tilt to judge described gray level image, is specially:

Described gray level image is carried out binary conversion treatment, to obtain binary image;

Described binary image is carried out vertical projection, to obtain the projected length of described binary image;

Described projected length and the projected length threshold values of presetting are compared;

If the projected length of the black of described binary image, determines then that described gray level image is a heeling condition less than the black length threshold values of described projected length threshold values; Perhaps, if the projected length of the white of described binary image, determines then that described gray level image is a heeling condition greater than the white length threshold values of described projected length threshold values.

3. image tilt correction method according to claim 1 and 2 is characterized in that, describedly described gray level image is carried out slant correction handles, and is specially:

Obtain the marginal information of described gray level image;

Calculate the pitch angle of described gray level image according to described marginal information;

Rotate described gray level image according to described pitch angle, with the described gray level image at the no angle of inclination of output.

4. image tilt correction method according to claim 3 is characterized in that, the described marginal information of obtaining described gray level image is specially: the marginal information that obtains described gray level image by the Canny operator.

5. image tilt correction method according to claim 3, it is characterized in that, described pitch angle of calculating described gray level image according to described marginal information, be specially: the described marginal information of the both sides by the described gray level image of Hough transfer pair is carried out control treatment, to calculate the horizontal tilt angle of described gray level image.

6. image tilt correction method according to claim 3 is characterized in that, describedly rotates described gray level image according to described pitch angle, is specially: according to described pitch angle, by the bilinear interpolation algorithm described gray level image is rotated correction.

7. an image inclination means for correcting is characterized in that, comprising:

The gray scale processing module is used for that the image that obtains is carried out gray scale and handles, to obtain gray level image;

Whether the projection process module is used for described gray level image is carried out projection process, tilt to judge described gray level image;

The treatment for correcting module is used for then described gray level image being carried out slant correction and handling if described gray level image tilts.

8. image inclination means for correcting according to claim 7 is characterized in that, described projection process module comprises:

The projection submodule is used for described gray level image is carried out projection, to obtain the projected length of described gray level image;

Judge submodule, be used to judge that whether described projected length is less than the pre-set length threshold values;

First determines submodule, is used for if described projected length, determines then that described gray level image is a heeling condition less than described length threshold values;

Second determines submodule, is used for if described projected length is not less than described length threshold values, determines that then described gray level image is a normal condition.

9 according to claim 7 or 8 described image inclination means for correctings, it is characterized in that described treatment for correcting module comprises:

Obtain submodule, be used for then obtaining the marginal information of described gray level image if described gray level image tilts;

Calculating sub module is used for calculating according to described marginal information the pitch angle of described gray level image;

The gyrator module is used for rotating described gray level image according to described pitch angle, with the described gray level image at the no angle of inclination of output.

10. image inclination means for correcting according to claim 9 is characterized in that, describedly obtains the marginal information that submodule also is used for obtaining by the Canny operator described gray level image;

Described calculating sub module also is used for carrying out control treatment by the described marginal information of the both sides of the described gray level image of Hough transfer pair, to calculate the horizontal tilt angle of described gray level image;

Described gyrator module also is used for by the bilinear interpolation algorithm described gray level image being rotated correction according to described pitch angle.

Images