技术领域technical field
本发明属于二维条码图像处理方法，涉及一种在复杂背景环境中矩阵式二维条码的初步定位方法。The invention belongs to a two-dimensional barcode image processing method, and relates to a preliminary positioning method of a matrix two-dimensional barcode in a complex background environment.
背景技术Background technique
矩阵式二维条形码是一种由中心点到与中心点固定距离的多边形单元所组成的图形二维码，而在水平和垂直方向的二维空间存储信息的条码称为二维码，矩阵式二维条码是近年来应用最为广泛的一种二维码，具有代表性的矩阵式二维条码有：CodeOne、MaxiCode、QRCode、DataMatrix等。一般的二维条码图像处理步骤中，在对二维条码完成了二值化处理之后，就要对条码的区域做一个初步的定位。因为在实际的应用中，图像采集模块所采集的条码图像中往往含有复杂的背景图案，这就给条码的识别带来了很大的困难。对条码进行初定位的目的，一是将图像中的背景噪声图案剔除，二是为后续处理缩小处理范围，提高处理速度。A matrix two-dimensional barcode is a graphic two-dimensional code composed of a center point and a polygonal unit with a fixed distance from the center point, and a barcode that stores information in a two-dimensional space in the horizontal and vertical directions is called a two-dimensional code. Two-dimensional barcodes are the most widely used two-dimensional codes in recent years. Representative matrix two-dimensional barcodes include: CodeOne, MaxiCode, QRCode, DataMatrix, etc. In the general two-dimensional barcode image processing steps, after completing the binarization process on the two-dimensional barcode, it is necessary to make a preliminary positioning of the area of the barcode. Because in practical applications, the barcode images collected by the image acquisition module often contain complex background patterns, which brings great difficulties to the identification of barcodes. The purpose of the initial positioning of the barcode is to remove the background noise pattern in the image, and the second is to narrow the processing range for subsequent processing and improve the processing speed.
目前，已有的针对矩阵式二维条码的区域初步定位主要有三类方法：第一类是扫描定位，也叫投影定位，即从水平和垂直两个方向对图像做投影，通过投影值的坐标来确定条码的大概位置。第二类是基于边缘检测和数学形态学的定位，即先对条码图像做边缘检测，再做形态学处理，最后对条码区域进行筛选。第三类则是基于小波分析和神经网络的定位。At present, there are mainly three types of methods for the preliminary positioning of matrix two-dimensional barcode areas: the first type is scanning positioning, also called projection positioning, that is, the image is projected from the horizontal and vertical directions, and the coordinates of the projected values To determine the approximate location of the barcode. The second type is positioning based on edge detection and mathematical morphology, that is, edge detection is performed on the barcode image first, then morphological processing is performed, and finally the barcode area is screened. The third category is based on wavelet analysis and neural network positioning.
第一类方法较简单，但要求图像的信噪比非常高才行。若图像中存在较大的背景图案，那用第一类方法就几乎没有意义；第二类方法是目前用的最多的方法。第三类方法较为复杂，且存在很高的不确定性。经对现有技术文献的检索发现，对第二类方法使用的较为多，因此本发明主要是在第二类方法的基础上提出自己的初步定位方法。在第二类方法中主要步骤是先对条码图像边缘检测，而后进行形态学的腐蚀与膨胀处理，最后提取条码连通区域。The first type of method is relatively simple, but requires a very high signal-to-noise ratio of the image. If there is a large background pattern in the image, it is almost meaningless to use the first method; the second method is currently the most used method. The third type of method is more complicated and has high uncertainty. After searching the prior art documents, it is found that the second type of method is used more, so the present invention mainly proposes its own preliminary positioning method on the basis of the second type of method. The main steps in the second type of method are to first detect the edge of the barcode image, then perform morphological erosion and expansion processing, and finally extract the connected area of the barcode.
第二类方法中，不同大小的方形结构元素对二维条码图像做形态学处理，图像中的连通域会产生很明显的不同，对条码的提取造成很大的影响。再对做完形态学处理的图进行条码区域的提取，所得到的区域会产生非常大的偏差，当结构元素太小时，对条码的定位会产生缺失，而结构元素太大时，很有可能将复杂背景图案一并计入条码区域。虽然这种方法应用的比较普遍，但只能作为一种实验方法，却不能用于工业应用中。因为这种方法有一个很大的缺陷，就是形态学处理中的结构元素的大小和形状都不能够自适应的选取，而更为关键的是若不能选取合适的结构元素，会严重的影响到处理的效果。In the second type of method, square structural elements of different sizes do morphological processing on the two-dimensional barcode image, and the connected domains in the image will have obvious differences, which will have a great impact on the extraction of the barcode. Then extract the barcode area from the morphologically processed image, and the resulting area will have a very large deviation. When the structural element is too small, the positioning of the barcode will be missing, and when the structural element is too large, it is very likely Incorporate complex background patterns into the barcode area. Although this method is widely used, it can only be used as an experimental method and cannot be used in industrial applications. Because this method has a big defect, that is, the size and shape of the structural elements in the morphological processing cannot be selected adaptively, and more importantly, if the appropriate structural elements cannot be selected, it will seriously affect the The effect of processing.
发明内容Contents of the invention
本发明所要解决的技术问题是，提供一种矩阵式二维条码的初步定位方法，以从复杂背景条件下得到条码的大概区域，提高条码的识别速度和精度，为后续的图像校正和提取信息等步骤做准备。The technical problem to be solved by the present invention is to provide a preliminary positioning method of a matrix two-dimensional barcode to obtain the approximate area of the barcode from complex background conditions, improve the recognition speed and accuracy of the barcode, and provide information for subsequent image correction and extraction. Wait for the steps to prepare.
为解决上述技术问题，本发明采用的技术方案是：一种矩阵式二维条码的初步定位方法，其包括以下步骤：In order to solve the above-mentioned technical problems, the technical solution adopted in the present invention is: a preliminary positioning method of a matrix type two-dimensional barcode, which includes the following steps:
1.1)对二值化后的条码图像进行边缘检测，得到图像的边缘检测图；1.1) Carry out edge detection to the barcode image after binarization, obtain the edge detection figure of image;
1.2)扫描检测图中的边缘点，将所有的边缘点标记；1.2) scan the edge points in the detection map, and mark all the edge points;
1.3)逐个对每个边缘点进行方向扫描，求得每个边缘点的最短距离跳变点；1.3) Carry out direction scanning to each edge point one by one, obtain the shortest distance jump point of each edge point;
1.4）连接图中所有的最短距离跳变点与其对应的边缘点；1.4) All the shortest distance jump points in the connection graph and their corresponding edge points;
1.5)得到连接过后的图像，筛选出连通区域，提取出条码区域。1.5) Obtain the connected image, filter out the connected areas, and extract the barcode area.
请补充下本方案的效果。Please add the effect of this program.
所述步骤1.2)中扫描检测图像中的边缘点，将所有的边缘点标记的步骤如下：In the step 1.2), the edge points in the image are scanned and detected, and the steps of all edge points are marked as follows:
2.1)对检测过后的图像进行扫描，如果被检测的点为白色像素点，且该点上下左右四周存在黑色像素点，则标记该点为图像的边缘点；2.1) Scan the detected image, if the detected point is a white pixel point, and there are black pixels around the point, then mark this point as the edge point of the image;
2.2）重复上述步骤2.1)，找出并标记所有图像中的边缘点。2.2) Repeat the above step 2.1) to find and mark the edge points in all images.
所述步骤1.3)中的具体步骤如下：The concrete steps in described step 1.3) are as follows:
3.1)寻找边缘点附近最近的跳变点，首先从右边方向扫描，若第一个点为黑色像素点，则继续向右边方向扫描，直到扫描到某点为白色像素点为止，记该点为跳变点；若第一个点为白色像素点，则向右扫描到某点为黑像素点，则记该点的前一位置的像素点为跳变点；3.1) To find the nearest jump point near the edge point, first scan from the right direction, if the first point is a black pixel point, continue to scan to the right direction until a certain point is scanned as a white pixel point, record this point as Jump point; if the first point is a white pixel, then scan to the right to a point that is a black pixel, then record the pixel at the previous position of this point as the jump point;
3.2)使用同样的方法对其他的七个方向，分别是该像素点的上、下、左、右上、左上、左下和右下重复扫描跳变点，得到八个跳变点后，取其中一个与该边缘点最近距离的一个点作为当前边缘点的最短距离跳变点，若出现多个点都为最近距离的跳变点时，则取最先扫描到的点作为最短距离跳变点。3.2) Use the same method to scan the jump points repeatedly for the other seven directions, which are the upper, lower, left, upper right, upper left, lower left and lower right of the pixel point. After obtaining eight jump points, take one of them A point closest to the edge point is used as the shortest distance jump point of the current edge point. If multiple points are the shortest distance jump points, the first scanned point is taken as the shortest distance jump point.
所述步骤1.4)中连接图像中所有的最短距离跳变点与其对应的边缘点的步骤如下：The step of connecting all the shortest distance jump points and their corresponding edge points in the image in the step 1.4) is as follows:
4.1)将所有边缘点与它们所对应的最短距离跳变点连接，当跳变点为黑色像素点时，将以这两点为端点的线段上经过的所有的像素点都置为白色，当跳变点也为白色像素点时，则不进行操作。4.1) Connect all edge points with their corresponding shortest distance jump points. When the jump point is a black pixel, set all the pixels passing through the line segment with these two points as endpoints to white. When When the jump point is also a white pixel, no operation is performed.
所述步骤1.5)中的具体步骤如下：对图像进行条码区域的提取，首先画一个与图像边缘距离一定宽度的边框，剔除所有与该边框有接触的连通图案，再求出图像中面积最大的连通图案，剔除所有小于此面积的连通图案，筛选出条码。The specific steps in the step 1.5) are as follows: the image is extracted from the barcode area, first draw a frame with a certain width from the edge of the image, remove all connected patterns that are in contact with the frame, and then find the largest area in the image. Connected patterns, remove all connected patterns smaller than this area, and screen out barcodes.
先分别向左和向右扫描图像，当接触到值为1的像素点时停止扫描，并分别记录这两点的横坐标；再分别向上和向下扫描图像，当接触到值为1的像素点时停止扫描，并分别记录这两点的纵坐标；以这四个点画水平矩形，最后将矩形内的像素点提取出来，从而完成条码的初定位。First scan the image to the left and right respectively, stop scanning when touching a pixel with a value of 1, and record the abscissas of these two points respectively; then scan the image up and down respectively, when touching a pixel with a value of 1 Stop scanning when pointing, and record the vertical coordinates of these two points respectively; draw a horizontal rectangle with these four points, and finally extract the pixels in the rectangle to complete the initial positioning of the barcode.
与现有技术相比，本发明的有益效果是：Compared with prior art, the beneficial effect of the present invention is:
本发明通过在复杂背景条件下的矩阵式二维条码图像中，自适应的将任何大小和规格的条码图像完整的连接起来形成连通区域，并将连通区域标记后提取，此过程不需要考虑选取结构元素的大小和形状，且对图像进行边缘点的检测更为简单，提取而得到条码的大概区域后，可以将条码与复杂背景区分开，避免背景对条码区域进一步处理的影响，提高条码的识别速度和精度，为后续的条码图像校正和提取信息等步骤做准备。In the matrix two-dimensional barcode image under complex background conditions, the present invention adaptively connects barcode images of any size and specification to form a connected area, and extracts the connected area after marking. This process does not need to consider selection The size and shape of the structural elements, and it is easier to detect the edge points of the image. After extracting the approximate area of the barcode, the barcode can be distinguished from the complex background, avoiding the influence of the background on the further processing of the barcode area, and improving the accuracy of the barcode. Recognition speed and accuracy prepare for the subsequent steps of barcode image correction and information extraction.
附图说明Description of drawings
图1为本发明的矩阵式码初步定位方法流程图Fig. 1 is a flow chart of the matrix code preliminary positioning method of the present invention
图2为本发明中判断边缘点时的几种情况（一格为一像素点）Fig. 2 is several situations when judging edge points in the present invention (one grid is one pixel)
图3为本发明中寻找方向跳变点的原理示例图（一格为一像素点）Figure 3 is an example diagram of the principle of finding the direction jump point in the present invention (one grid is one pixel point)
图4为本发明中连接最短距离跳变点像素点的过程（一格为一像素点）Fig. 4 is the process of connecting the pixels of the shortest distance jump point in the present invention (one grid is one pixel)
图5为本发明中标记连通区域过程的原理图（一格为一像素点）Figure 5 is a schematic diagram of the process of marking connected regions in the present invention (one grid is one pixel)
图6为本发明中自适应的条码初步定位标记连通区域并处理效果图。Fig. 6 is an effect diagram of the self-adaptive barcode preliminarily locating and marking connected areas and processing in the present invention.
具体实施方式detailed description
下面结合具体实施例对本发明作进一步的说明。The present invention will be further described below in conjunction with specific examples.
如图1所示，本发明公开一种矩阵式二维条码的初步定位方法，主要的方法包括以下步骤：As shown in Figure 1, the present invention discloses a preliminary positioning method of a matrix two-dimensional barcode, the main method includes the following steps:
在接收到二值化处理过的矩阵式二维条码图像后，首先对图像进行边缘检测。然后第一步就是对检测后图像中的每个像素点进行检测，判断是否边缘点。对边缘点的判断的准则为：如果被检测的点为白色像素点（值为1），且该点上下左右四周存在黑色像素点（值为0），则判断该点为图像的边缘点。如图2中四种情况都可以判断a点为边缘点。After receiving the matrix two-dimensional barcode image processed by binarization, edge detection is first performed on the image. Then the first step is to detect each pixel in the detected image to determine whether it is an edge point. The criterion for judging the edge point is: if the detected point is a white pixel point (value 1), and there are black pixels around the point (value 0), then it is judged as the edge point of the image. In the four situations shown in Figure 2, it can be judged that point a is an edge point.
当确定a点为边缘点后，接下来寻找a附近最近的跳变点，这里解释一下何为寻找与a点距离最近的方向跳变点，以向右方向为例，寻找与a点右方向上距离最近的方向跳变点的规则为：从a点右边第一个点开始向右扫描。若第一个点为黑色像素点，则继续向右扫描，如图3(a)所示，直到扫描到某点为白色像素点为止，记该点为b点，如图3(b)所示。若第一个点为白色像素点，则继续向右扫描，如图3(c)所示，直到扫描到某点为黑色像素点为止，记该点的前一点为b点，如图3(d)所示。这两种情况都可确定b点是a点右方向上第一个发生颜色跳变的点，即b点是与a点右方向上距离最近的方向跳变点。After confirming that point a is an edge point, then look for the nearest jump point near a. Here is an explanation of what it means to find the jump point in the direction closest to point a. Taking the right direction as an example, look for the right direction of point a The rule for the nearest direction jump point is: scan rightward from the first point on the right of point a. If the first point is a black pixel point, continue to scan to the right, as shown in Figure 3(a), until a certain point is scanned to be a white pixel point, record this point as point b, as shown in Figure 3(b) Show. If the first point is a white pixel point, continue to scan to the right, as shown in Figure 3(c), until a certain point is scanned to be a black pixel point, record the previous point of this point as point b, as shown in Figure 3( d) as shown. In both cases, it can be determined that point b is the first point where a color jump occurs in the right direction of point a, that is, point b is the closest direction jump point to the right of point a.
重复上述过程寻找与a点八个方向上距离最近的方向跳变点，八个方向为（a点上、下、左、右、右上（45°方向）、左上（135°方向）、左下（225°方向）和右下（315°方向）），当找到跳变点b点后要记录下a点与b点的距离。若扫描至图像边界处时还未检测到跳变点，那么就将该边界点设为跳变点b，并将a点与b点的距离设为∞。当与a点八个方向上距离最近的方向跳变点全部找到并分别记录下了各个距离值，寻找跳变点的结果如图4(a)为例。Repeat the above process to find the directional jump point closest to point a in eight directions, the eight directions are (point a up, down, left, right, upper right (45° direction), upper left (135° direction), lower left ( 225° direction) and lower right (315° direction)), when the jump point b is found, the distance between point a and point b should be recorded. If no transition point is detected when scanning to the image boundary, then set the boundary point as transition point b, and set the distance between point a and point b as ∞. When the jump points closest to point a in the eight directions are all found and each distance value is recorded, the result of finding the jump point is shown in Figure 4(a) as an example.
接下来第三步就要找出这八个距离值中的最小值，再将这个最小值对应的跳变点找到，并将该边缘点a与该跳变点连接起来，以图4所示为例。从图4(a)中可以看出与a点八个方向上距离最近的方向跳变点分别为b,c,d,e,f,g,h,i，可以判断出八个距离中最短为︱ai︱，因此将a点与i点连接起来，如图4(b)所示。The next third step is to find the minimum value among the eight distance values, then find the jump point corresponding to the minimum value, and connect the edge point a with the jump point, as shown in Figure 4 as an example. From Figure 4(a), it can be seen that the directional jump points closest to point a in the eight directions are b, c, d, e, f, g, h, i respectively, and it can be judged that the shortest of the eight distances is︱ai︱, so connect point a with point i, as shown in Figure 4(b).
对图像中所有的边缘点重复上述寻找跳变点并连接的过程，得到连接后的条码图像，如图6(a)，这时候需要对图像进行条码区域的提取，使用的是目前大多数通用的筛选连通区域的方法，首先画一个与图像边缘距离一定宽度的边框，剔除所有与该边框有接触的连通图案，再求出图像中面积最大的连通图案，剔除所有小于此面积的连通图案，筛选出条码。对连通和筛选区域的标记原理如图5(a)、图5(b)中所示，将所有区域内进行编号的像素进行编号，然后对所有对应编号的像素点个数进行统计，将像素点个数最多的编号区域提取，得到最大连通区域，筛选并提取连通区域的效果如图6(b)。Repeat the above-mentioned process of finding and connecting jump points for all edge points in the image to obtain the connected barcode image, as shown in Figure 6(a). The method of screening connected regions, first draw a border with a certain width from the edge of the image, remove all connected patterns that are in contact with the border, then find the connected pattern with the largest area in the image, and remove all connected patterns that are smaller than this area, Filter out barcodes. The principle of marking connected and filtered regions is shown in Figure 5(a) and Figure 5(b), numbering the numbered pixels in all regions, and then counting the number of all corresponding numbered pixels, and counting the pixels The numbered area with the largest number of points is extracted to obtain the largest connected area, and the effect of filtering and extracting the connected area is shown in Figure 6(b).
筛选连通区域后，已经将大部分的背景剔除，所得到的图像只含有条码部分。分别向左和向右扫描图像，当接触到值为1的像素点时停止扫描，并分别记录这两点的横坐标；同样的过程，再分别向上和向下扫描图像，当接触到值为1的像素点时停止扫描，并分别记录这两点的纵坐标；以这四个点画水平矩形，最后将矩形内的像素点提取出来，如图6(c)所示。这样就完成了二维条码的初定位。After filtering the connected regions, most of the background has been eliminated, and the obtained image only contains the barcode part. Scan the image to the left and to the right, stop scanning when touching a pixel with a value of 1, and record the abscissas of these two points respectively; in the same process, scan the image up and down, respectively, when it touches a pixel with a value of 1, stop scanning, and record the vertical coordinates of these two points respectively; draw a horizontal rectangle with these four points, and finally extract the pixels in the rectangle, as shown in Figure 6(c). In this way, the initial positioning of the two-dimensional barcode is completed.
显然，本发明的上述实施例仅仅是为清楚地说明本发明所作的举例，而并非是对本发明的实施方式的限定。对于所属领域的普通技术人员来说，在上述说明的基础上还可以做出其它不同形式的变化或变动。这里无需也无法对所有的实施方式予以穷举。凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明权利要求的保护范围之内。Apparently, the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, rather than limiting the implementation of the present invention. For those of ordinary skill in the art, on the basis of the above description, other changes or changes in different forms can also be made. It is not necessary and impossible to exhaustively list all the implementation manners here. All modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310140114.1ACN103235951B (en) | 2013-04-22 | 2013-04-22 | A kind of Primary Location method of matrix two-dimensional barcode |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310140114.1ACN103235951B (en) | 2013-04-22 | 2013-04-22 | A kind of Primary Location method of matrix two-dimensional barcode |
| Publication Number | Publication Date |
|---|---|
| CN103235951A CN103235951A (en) | 2013-08-07 |
| CN103235951Btrue CN103235951B (en) | 2016-06-15 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310140114.1AExpired - Fee RelatedCN103235951B (en) | 2013-04-22 | 2013-04-22 | A kind of Primary Location method of matrix two-dimensional barcode |
| Country | Link |
|---|---|
| CN (1) | CN103235951B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870790A (en)* | 2014-04-02 | 2014-06-18 | 胡建国 | Recognition method and device of two-dimensional bar code |
| CN104463067B (en)* | 2014-12-04 | 2017-03-22 | 四川大学 | Method for extracting macro blocks of Grid Matrix two-dimensional bar code |
| CN105184208B (en)* | 2015-09-02 | 2017-10-31 | 福建联迪商用设备有限公司 | A kind of Quick Response Code Primary Location method and system |
| CN116563048B (en)* | 2023-07-05 | 2024-05-03 | 江西科技学院 | Financial reimbursement method, system and computer |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924899A (en)* | 2006-09-26 | 2007-03-07 | 福建榕基软件开发有限公司 | Precise location method of QR code image symbol region at complex background |
| CN101059834A (en)* | 2007-05-31 | 2007-10-24 | 中国农业大学 | QR two-dimensional bar code recognition method based on pickup head for chatting |
| CN102663337A (en)* | 2012-03-16 | 2012-09-12 | 江南大学 | Method for quick Data Matrix two-dimensional barcode identifying under simple condition background |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924899A (en)* | 2006-09-26 | 2007-03-07 | 福建榕基软件开发有限公司 | Precise location method of QR code image symbol region at complex background |
| CN101059834A (en)* | 2007-05-31 | 2007-10-24 | 中国农业大学 | QR two-dimensional bar code recognition method based on pickup head for chatting |
| CN102663337A (en)* | 2012-03-16 | 2012-09-12 | 江南大学 | Method for quick Data Matrix two-dimensional barcode identifying under simple condition background |
| Title |
|---|
| 《Data Matrix二维条形码解码器图像预处理研究》;邹沿新等;《计算机工程与应用》;20091231;第45卷(第34期);正文第183-185、188页* |
| 《基于图象处理的QR码识别》;胡孝鹏等;《航空计算技术》;20070331;第37卷(第2期);正文第99-102页* |
| Publication number | Publication date |
|---|---|
| CN103235951A (en) | 2013-08-07 |
| Publication | Publication Date | Title |
|---|---|---|
| CN106960208B (en) | Method and system for automatically segmenting and identifying instrument liquid crystal number | |
| TWI455034B (en) | Barcode recognion method and a computer product thereof | |
| JP5699788B2 (en) | Screen area detection method and system | |
| CN107301368B (en) | Recognition method of DataMatrix two-dimensional code | |
| CN103258201B (en) | A kind of form lines extracting method of amalgamation of global and local message | |
| CN104794421B (en) | A kind of positioning of QR codes and recognition methods | |
| CN106446894B (en) | A method of based on outline identification ball-type target object location | |
| CN102254144A (en) | Robust method for extracting two-dimensional code area in image | |
| EP3309705A1 (en) | Qr code feature detection method and system | |
| CN102136058A (en) | Bar code image identification method | |
| CN110136069B (en) | Text image correction method and device and electronic equipment | |
| CN104331695B (en) | A kind of circle marker symbol shape quality detection method of robust | |
| CN108615058A (en) | A kind of method, apparatus of character recognition, equipment and readable storage medium storing program for executing | |
| CN108763996B (en) | A method for measuring plane positioning coordinates and direction angle based on two-dimensional code | |
| CN103235951B (en) | A kind of Primary Location method of matrix two-dimensional barcode | |
| CN102831428B (en) | Method for extracting quick response matrix code region in image | |
| TWI438699B (en) | Processing method of barcode and related apparatus thereof | |
| CN113177959A (en) | QR code real-time extraction algorithm in rapid movement process | |
| CN105335744A (en) | One-dimensional code region location based on image backbone extraction strip distribution features | |
| CN108717544B (en) | An automatic detection method of newspaper sample text based on intelligent image analysis | |
| CN119445600A (en) | Method, device, computer equipment and readable storage medium for identifying tables in images | |
| CN118133858B (en) | DM code positioning and identifying method combining deep learning with pixel level detection | |
| CN104166843B (en) | Document image source judgment method based on linear continuity | |
| JP4492258B2 (en) | Character and figure recognition and inspection methods | |
| WO2014020820A1 (en) | Mark reading device and mark reading method |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20160615 | |
| CF01 | Termination of patent right due to non-payment of annual fee |