技术领域technical field
本发明涉及盲文标注领域，特别涉及一种盲文点交互式标注方法及系统。The invention relates to the field of braille marking, in particular to a method and system for interactive marking of braille dots.
背景技术Background technique
视力残疾人士由于视觉障碍，无法像明眼人一样获取明文信息，主要通过触摸盲文点字符号来阅读盲文获取信息。盲文由盲文方组成，每一个盲文方由六点组成，左侧从上到下为123，右侧为456，叫一方，即本文中的盲文方。目前流通的盲文图书数量还较少，无法满足盲人朋友的阅读需求。另一方面，盲文图书馆典藏了很多早期有价值的盲文图书和文献，这些图书由于缺乏盲文的数字化信息，导致再版的人工成本昂贵。而且，在特殊教育领域，盲生试卷的编制和阅卷，还是采用盲文老师手工翻译的方式，耗时费力，缺乏客观性。因此，针对纸质盲文图像的盲文点字自动检测和识别技术具有重要意义。而为了测试盲文点字检测方法的检测性能，或者获取用于机器学习的盲文点字图像样本，都需要对盲文图像中的盲文点进行人工标注。Due to visual impairment, the visually impaired cannot obtain information in plain text like a sighted person. They mainly obtain information by touching Braille symbols to read Braille. Braille is composed of Braille squares, and each Braille square is composed of six dots. The left side is 123 from top to bottom, and the right side is 456. It is called a square, which is the Braille square in this article. At present, the number of Braille books in circulation is still small, which cannot meet the reading needs of blind friends. On the other hand, the Braille library has stored many valuable early books and documents in Braille. Due to the lack of digital information in Braille, these books are expensive to republish. Moreover, in the field of special education, the preparation and marking of test papers for blind students is still done by manual translation by Braille teachers, which is time-consuming and laborious, and lacks objectivity. Therefore, Braille automatic detection and recognition technology for paper Braille images is of great significance. In order to test the detection performance of the Braille detection method, or to obtain a Braille image sample for machine learning, it is necessary to manually label the Braille dots in the Braille image.
盲文俗称“点字”或“凸字”，由法国人路易·布莱尔于1824年发明，是一种依靠触觉感知的文字。盲文图书的一页大概有1000到2000个盲文凸点。盲文的基本组成单位是盲方或者盲符，每个盲方有6个点位，分布在三行两列的矩阵上，根据相应的点位上是否有凸点来代表不同的盲方。盲方根据“国家盲文标准”，按照一定的方距和行距进行排列，组成盲文。Braille, commonly known as "braille" or "raised characters", was invented by the Frenchman Louis Blair in 1824 and is a text that relies on tactile perception. A page of a Braille book has about 1,000 to 2,000 Braille dots. The basic units of Braille are blind squares or blind symbols. Each blind square has 6 dots, which are distributed on a matrix of three rows and two columns. Different blind squares are represented according to whether there are bumps on the corresponding dots. According to the "National Braille Standard", the blind squares are arranged according to a certain square and line spacing to form Braille.
为了节约纸张，盲文图书一般采用双面打印方式，即我们得到的盲文图像即含有当前页的凸点区域，又包含凹点区域。凸点和凹点区域会有一定的错位现象，但是在双面盲文的点字密集区域，凸点和凹点往往交错在一起，导致盲文点字的图像表观呈现多样性特点，凹凸点的外观形态也会发生极大的变化，这给双面盲文的人工标注带来极大的困难和挑战，标注时间成本非常高，而且容易由于人的疲劳导致标注错误。In order to save paper, braille books generally use double-sided printing, that is, the braille image we get contains not only the raised dot area of the current page, but also the concave dot area. There will be a certain dislocation phenomenon in the area of convex points and concave points, but in the dense area of double-sided Braille, the convex points and concave points are often interlaced, resulting in the appearance of Braille images showing diversity, and the appearance of concave and convex points Great changes will also occur, which brings great difficulties and challenges to manual labeling of double-sided Braille. The cost of labeling time is very high, and it is easy to cause labeling errors due to human fatigue.
发明内容Contents of the invention
为了解决上述纸版盲文识别技术不够鲁棒，速度较慢，无法适应多样的盲文打印形式和采集形式的问题，本发明提出了一种盲文点交互式标注方法及系统。In order to solve the problems that the paper-based braille recognition technology is not robust enough, slow in speed, and unable to adapt to various braille printing and collection forms, the present invention proposes a method and system for interactively marking braille dots.
具体地说，本发明公开了一种盲文点交互式标注方法，其中包括：Specifically, the invention discloses a method for interactively marking braille dots, which includes:
步骤1、利用采集设备获取纸版盲文的数字化图像；Step 1, using the acquisition device to obtain the digitized image of the paper Braille;
步骤2、以盲文方为单位对该数字化图像进行交互式盲文点标注；Step 2, carry out interactive braille dot labeling on the digitized image in units of braille squares;
其中该步骤2包括：Wherein the step 2 includes:
步骤21、将该数字化图像显示在屏幕上；Step 21, displaying the digitized image on the screen;
步骤22、通过交互式设备在该数字化图像上选取某一个盲文的盲文方位置；Step 22, select a braille square position of a certain braille on the digitized image through an interactive device;
步骤23、将属于该盲文方位置的盲文方标识显示在屏幕上；Step 23, displaying the Braille party identification belonging to the position of the Braille party on the screen;
步骤24、通过交互设备为该盲文方标识内的盲文点进行标注，并在屏幕上实时显示已标注完成的盲文点；Step 24, mark the braille dots in the braille party logo through the interactive device, and display the marked braille dots on the screen in real time;
步骤25、移动该盲文方位置至下一个盲文方，或执行该步骤22选取下一个盲文的盲文方位置，重复执行该步骤23直到对该数字化图像内全部盲文点完成标注。Step 25. Move the position of the braille square to the next braille square, or perform step 22 to select the position of the next braille square, and repeat step 23 until all the braille dots in the digitized image are marked.
该盲文点交互式标注方法，其中步骤1中该采集设备包括扫描仪、摄像机或盲文图像采集仪器；该纸版盲文包括凸点和/或凹点形式的盲文点。In the method for interactively marking braille dots, in step 1, the acquisition device includes a scanner, a video camera or a braille image acquisition device; the paper version of braille includes braille dots in the form of raised dots and/or concave dots.
该盲文点交互式标注方法，其中该盲文方标识为盲文方对应的6个盲文点或盲文方对应的“日”字形方格，该“日”字形方格的每个交叉点代表一个盲文点位置。The braille dot interactive labeling method, wherein the braille square is identified as 6 braille dots corresponding to the braille square or a "day" shaped square corresponding to the braille square, and each intersection point of the "day" shaped square represents a braille dot Location.
该盲文点交互式标注方法，其中根据中国盲文书写规范和该数字化图像的分辨率，确定盲文方对应的6个盲文点间的间距或“日”字形方格的尺寸比例。In the braille dot interactive labeling method, according to the Chinese Braille writing standard and the resolution of the digitized image, the distance between the six braille dots corresponding to the braille square or the size ratio of the "日"-shaped square is determined.
该盲文点交互式标注方法，其中该交互式设备包括键盘、鼠标、触控板。In the method for interactively marking braille dots, the interactive device includes a keyboard, a mouse, and a touch panel.
本发明还提出了一种盲文点交互式标注系统，其中包括：The present invention also proposes an interactive marking system for braille dots, which includes:
采集模块，用于通过采集设备获取纸版盲文的数字化图像；The collection module is used to obtain the digitized image of the paper version of Braille through the collection device;
标注模块，用于以盲文方为单位对该数字化图像进行交互式盲文点标注；The labeling module is used to carry out interactive braille dot labeling on the digitized image in units of braille squares;
其中该标注模块包括：Among them, the labeling module includes:
盲文方选取模块，将该数字化图像显示在屏幕上，并通过交互式设备在该数字化图像上选取某一个盲文的盲文方位置；The braille square selection module displays the digitized image on the screen, and selects a braille square position on the digitized image through an interactive device;
显示模块，用于将属于该盲文方位置的盲文方标识显示在屏幕上，通过交互设备为该盲文方标识内的盲文点进行标注，并在屏幕上实时显示已标注完成的盲文点；移动该盲文方位置至下一个盲文方，或执行该步骤22选取下一个盲文的盲文方位置，重复执行该步骤23直到对该数字化图像内全部盲文点完成标注。The display module is used to display the braille party logo belonging to the braille party position on the screen, mark the braille dots in the braille party logo through the interactive device, and display the marked braille dots on the screen in real time; move the From the braille square position to the next braille square, or perform step 22 to select the braille square position of the next braille, and repeat step 23 until all the braille points in the digitized image are marked.
该盲文点交互式标注系统，其中该采集设备包括扫描仪、摄像机或盲文图像采集仪器；该纸版盲文包括凸点和/或凹点形式的盲文点。In the Braille dot interactive labeling system, the collection device includes a scanner, a video camera or a Braille image collection device; the paper version of the Braille includes Braille dots in the form of raised dots and/or concave dots.
该盲文点交互式标注系统，其中该盲文方标识为盲文方对应的6个盲文点或盲文方对应的“日”字形方格，该“日”字形方格的每个交叉点代表一个盲文点位置。The braille dot interactive labeling system, wherein the braille square is identified as 6 braille dots corresponding to the braille square or a "day"-shaped square corresponding to the braille square, and each intersection point of the "day"-shaped square represents a braille dot Location.
该盲文点交互式标注系统，其中根据中国盲文书写规范和该数字化图像的分辨率，确定盲文方对应的6个盲文点间的间距或“日”字形方格的尺寸比例。In the Braille dot interactive marking system, according to the Chinese Braille writing standard and the resolution of the digitized image, the spacing between the 6 Braille dots corresponding to the Braille square or the size ratio of the "日"-shaped square is determined.
该盲文点交互式标注系统，其中该交互式设备包括键盘、鼠标、触控板。In the braille dot interactive marking system, the interactive device includes a keyboard, a mouse, and a touch panel.
由此本发明采用以盲文方为单位对该数字化图像进行交互式盲文点标注，提高了标注效率。Therefore, the present invention uses Braille squares as units to carry out interactive Braille dot marking on the digitized image, which improves the marking efficiency.
附图说明Description of drawings
图1为双面盲文图像截图；Figure 1 is a screenshot of a double-sided Braille image;
图2为以点的形式在屏幕上显示盲文方对应盲文点位置的示意图；Fig. 2 is a schematic diagram showing the positions of Braille squares corresponding to Braille dots on the screen in the form of dots;
图3为以“日”字的交叉点形式在屏幕上显示盲文方对应盲文点位置的示意图；Fig. 3 is a schematic diagram showing on the screen the position of the Braille square corresponding to the Braille point in the form of the intersection of the word "日";
图4为已标注完成的盲文方示意图；Figure 4 is a schematic diagram of a marked Braille square;
图5为选择盲文方进行删除的示意图；Fig. 5 is a schematic diagram of selecting a Braille side to delete;
图6为凸点和凹点的标注结果展示图；Figure 6 is a display diagram of the labeling results of bumps and pits;
图7为基于级联分类器的凸点检测结果展示图；Fig. 7 is a display diagram of bump detection results based on cascaded classifiers;
图8为盲文方定位结果示意图；Fig. 8 is a schematic diagram of a braille square positioning result;
图9为初始的计算机盲文点检测结果图；Fig. 9 is an initial computer Braille dot detection result diagram;
图10为本发明主要步骤框图。Fig. 10 is a block diagram of main steps of the present invention.
具体实施方式Detailed ways
为让本发明的上述特征和效果能阐述的更明确易懂，下文特举实施例并配合说明书附图作详细说明如下。其中需要注意的是，本发明附图虽然为灰度图片，但在实际操作中显示的都是彩色图像。In order to make the above-mentioned features and effects of the present invention more clear and understandable, the following specific embodiments are described in detail with reference to the accompanying drawings. It should be noted that although the drawings of the present invention are grayscale pictures, they are all color images displayed in actual operation.
如图10所示，本发明包括，步骤1，盲文图像采集：As shown in Figure 10, the present invention includes, step 1, Braille image collection:
利用采集设备获取纸版盲文的数字化图像。采集方式可以包括扫描仪扫描，摄像机拍照，或者特殊的盲文图像采集仪器等方式。该纸版盲文包括凸点和/或凹点形式的盲文点，纸版盲文可以包括盲文图书或者盲文试卷等，可以是单面印刷或者双面印刷的盲文。单面印刷的盲文每页只包含凸点或者凹点一种形式的盲文点，双面印刷的盲文每页包含凸点和凹点两种形式的盲文点。例如，图1显示了采用扫描仪扫描得到的双面盲文图像的截图，既有凸点又有凹点，在文字密集区，凸点和凹点交互在一起。Acquire digitized images of paper-based Braille using a capture device. The collection method may include scanning by a scanner, photographing by a camera, or a special Braille image collection device, etc. The paper version of Braille includes Braille dots in the form of raised dots and/or recessed dots. The paper version of Braille may include Braille books or Braille test papers, and may be single-sided or double-sided printed Braille. Each page of single-sided printed Braille contains only one form of Braille dots: raised dots or recessed dots, and each page of double-sided printed Braille contains two forms of Braille dots: raised dots and recessed dots. For example, Figure 1 shows a screenshot of a double-sided braille image scanned by a scanner, which has both convex and concave dots, and in dense text areas, the convex and concave dots interact together.
步骤2，盲文点交互式标注：Step 2, interactive labeling of Braille dots:
以盲文方为单位对该数字化图像进行交互式盲文点标注，包括以下步骤：The interactive braille dot labeling of the digitized image in units of braille squares includes the following steps:
步骤21，将该数字化图像作为待标注的盲文图像显示在屏幕上。例如，图1显示了一个盲文图像的截图。Step 21, the digitized image is displayed on the screen as a Braille image to be marked. For example, Figure 1 shows a screenshot of a braille image.
步骤22，通过交互式设备的在该数字化图像上选取某一个盲文的盲文方位置，例如通过交互式设备鼠标点击盲文方的左上角来确定该盲文方位置。Step 22, select a braille square position on the digitized image through the interactive device, for example, click on the upper left corner of the braille square with a mouse on the interactive device to determine the position of the braille square.
步骤23，将属于该盲文方位置的盲文方标识显示在屏幕上。其中盲文方标识可为盲文方对应的6个盲文点，或者盲文方对应的“日”字形方格，例如将所选择的盲文方对应的6个盲文点位置显示在屏幕上，可以直接采用6个点来显示盲文方(如图2所示，其中盲文方对应的盲文点位置以浅灰色点标识)，也可以采用“日”字形方格来表示盲文方标识(如图3所示，其中盲文方对应的盲文点位置以浅灰色矩形框标识)，每个交叉点代表一个盲文点位置。盲文方标识对应的盲文点间距信息，可以参考中国盲文书写规范以及扫描图像的分辨率大小，通过统计的方法提前得到盲文点间距、盲文方间距和行距信息。并且在以上在点选盲文方时，可通过鼠标快捷键来区分是标注凸点盲文方还是凹点盲文方，例如点击鼠标左键代表标注凸点盲文方，点击鼠标右键代表标注凹点盲文方；可通过键盘快捷键进行盲文方位置，大小的微调，从而更精确的匹配盲文图像上的某一个盲文方，例如通过“I”、“K”、“J”、“L”四个键进行盲文方位置上下左右的微调，每次移动一个像素或者多个像素，具体移动的像素数课根据图像采集的分辨率决定。Step 23, display the Braille party identification belonging to the Braille party position on the screen. Wherein, the braille square logo can be the 6 braille dots corresponding to the braille square, or the "day" square grid corresponding to the braille square. dots to display the Braille squares (as shown in Figure 2, where the Braille dots corresponding to the Braille dots are marked with light gray dots), or "day" squares can be used to represent the Braille squares (as shown in Figure 3, where the Braille dots The braille dot position corresponding to the square is marked with a light gray rectangle), and each intersection represents a braille dot position. Braille dot spacing information corresponding to the Braille square logo can refer to the Chinese Braille writing specification and the resolution of the scanned image, and the Braille dot spacing, Braille square spacing, and line spacing information can be obtained in advance through statistical methods. And when clicking on the braille square above, you can use the mouse shortcut to distinguish whether to mark the raised point braille square or the concave point braille square. For example, click the left button of the mouse to mark the raised point braille square, and click the right mouse button to mark the concave point braille square ;The position and size of the braille square can be fine-tuned through keyboard shortcuts, so as to more accurately match a certain braille square on the braille image, for example, through the four keys "I", "K", "J", and "L" Fine-tune the position of the braille square up, down, left, and right, and move one or more pixels each time. The specific number of pixels to move depends on the resolution of the image acquisition.
步骤24，通过交互设备为该盲文方标识内的盲文点进行标注(填充)，并在屏幕上实时显示已填充好的盲文点。以标注凸点为例，用交互设备例如是键盘快捷键进行盲文方内盲文点的快速填充，并在屏幕上实时显示已填充好的凸点。凹点盲文方的标注方法类似。例如，根据中国盲文要求，“日”字左边三个点代表1、2、3，右边三个点代表4、5、6。在实际标注时，可采用小键盘的数字键，仅选择某个位置上有凸点的数字。例如，如果该盲文方中仅有1、2、5三个位置有凸点，则仅利用数字键选择1、2、5三个键即可完成该盲文方凸点的填充。同时在屏幕上显示已经填充好的凸点，例如采用黑色点进行标识。图4显示了一个标注好的盲文方，例如左侧盲文方的黑点信息，右侧6个灰色点为移动到的下一个盲文方位置。Step 24: Mark (fill) the Braille dots in the Braille party logo through the interactive device, and display the filled Braille dots on the screen in real time. Taking the labeling of bumps as an example, use interactive devices such as keyboard shortcuts to quickly fill in the braille dots in the braille square, and display the filled bumps on the screen in real time. Dimpled braille squares are marked in a similar way. For example, according to Chinese Braille requirements, the three dots on the left of the word "日" represent 1, 2, 3, and the three dots on the right represent 4, 5, 6. In actual marking, you can use the number keys on the small keyboard to select only the numbers with raised dots at a certain position. For example, if there are only three positions 1, 2, and 5 in the braille square with bumps, then only using the number keys to select the three keys 1, 2, and 5 can complete the filling of the bumps in the braille square. At the same time, the filled bumps are displayed on the screen, for example, marked with black dots. Figure 4 shows a marked braille square, for example, the black dot information of the left braille square, and the six gray dots on the right are the position of the next braille square to move to.
步骤25，该盲文方标注完之后，可以采用快捷键进行盲文方位置的移动，移动到下一个盲文方位置。由于中国盲文的排列遵循了国家标准，盲文方行间距和列间距有固定的范围，可以结合盲文图像采集的分辨率，提前统计该盲文图像中对应的盲文方行间距和列间距，方便在交互式操作时直接进行行列的移动。例如，利用键盘上的“上下左右”方向键进行盲文方位置的单步移动，每次移动距离可以提前根据盲文图像进行统计和确定。也可以采用步骤22，直接点选的方式，选取下一个需要标注的盲文方。这里也可以进一步用快捷键微调盲文方的位置，方法同上步骤23，并在屏幕上显示盲文方。Step 25, after the braille square is marked, the shortcut key can be used to move the position of the braille square to move to the next braille square position. Since the arrangement of Braille in China complies with national standards, the row spacing and column spacing of Braille squares have a fixed range, and the corresponding Braille square row spacing and column spacing in the Braille image can be counted in advance based on the resolution of Braille image collection, which is convenient for interactive Directly move the row and column during the type operation. For example, use the "up, down, left, and right" arrow keys on the keyboard to move the position of the braille square in a single step, and the distance of each movement can be counted and determined in advance based on the braille image. Step 22 can also be used to directly click to select the next braille square to be marked. Here, you can further fine-tune the position of the braille square with shortcut keys, the method is the same as step 23 above, and display the braille square on the screen.
也可以对选取的盲文方进行标注信息的修改。例如选择了已经标注好的盲文方，可以重新通过数字快捷键进行重新标注。It is also possible to modify the marked information of the selected braille square. For example, if you select a marked braille square, you can use the number shortcut keys to re-mark.
也可以删除盲文方。例如，如图5所示，利用鼠标在屏幕上画矩形框的方式来圈定某一盲文方区域，按快捷键，例如DEL进行盲文方删除。或者直接点选某一盲文方，采用Del等键进行盲文方标注信息的删除。Braille squares can also be deleted. For example, as shown in FIG. 5 , use the mouse to draw a rectangular frame on the screen to delineate a certain braille square area, and press a shortcut key, such as DEL, to delete the braille square. Or directly click a certain braille square, and use the key such as Del to delete the marked information of the braille square.
重复步骤22，到步骤25，完成对整张盲文图像盲文点的交互式标注。实际标注时，可以根据需要仅标注凸点，或者仅标注凹点，或者凸点和凹点都进行标注。图6用不同的颜色信息展示了凸点和凹点的标注结果，其中凸点采用黑色，凹点采用白色。Repeat step 22 to step 25 to complete the interactive labeling of the braille dots on the entire braille image. In actual marking, only the convex points, or only the concave points, or both the convex points and the concave points can be marked as required. Figure 6 shows the labeling results of convex and concave points with different color information, where the convex points are black and the concave points are white.
标注结束之后，按快捷键保存该盲文图像的标注信息。例如，点击“S“键进行标注信息的保存，以盲文方的形式，保存盲文方位置信息，以及填充的盲文点的位置信息等。After the annotation is finished, press the shortcut key to save the annotation information of the braille image. For example, click the "S" button to save the annotation information, and save the position information of the braille square and the position information of the filled braille dot in the form of a braille square.
本发明的实验效果。如果按照凸点进行鼠标进行逐个的标注，完成一张盲文图像的标注大概需要2个多小时。而采用了基于盲文方并结合数字键的快捷标注方法，标注一张图像在10分钟以内，极大地提高了人工标注的效率。其他可选的标注方法有，直接交互式的在盲文图像上，利用鼠标选择凸点位置。Experimental effect of the present invention. If the mouse is marked one by one according to the bumps, it will take more than 2 hours to complete the marking of a braille image. However, the fast labeling method based on Braille squares combined with digital keys is adopted, and it takes less than 10 minutes to label an image, which greatly improves the efficiency of manual labeling. Other optional annotation methods include directly interactively selecting the position of the convex point on the braille image with the mouse.
本发明特举以下实施例，进一步详细对上述各步骤进行展开描述。The present invention specifically cites the following examples to further describe the above-mentioned steps in detail.
本发明除上述步骤外还包括：The present invention also comprises except above-mentioned steps:
步骤3盲文点快速检测、步骤4盲文图像自动倾斜校正、步骤5盲文方自适应定位、步骤6盲文点计算机辅助标注和步骤7高精度盲文点和盲文方识别。Step 3 fast detection of braille dots, step 4 automatic tilt correction of braille images, step 5 adaptive positioning of braille squares, step 6 computer-aided marking of braille dots and step 7 high-precision recognition of braille dots and braille squares.
步骤3盲文点快速检测，提出了基于级联分类器的盲文点快速检测方法，包括：Step 3 Fast detection of braille dots, a fast detection method of braille dots based on cascade classifiers is proposed, including:
步骤S1、基于以上步骤1和步骤2，得到了盲文图像的标注信息，包含凸点的位置信息。本发明下面将以凸点检测为例，凹点的检测方法类似。Step S1, based on the above steps 1 and 2, the labeling information of the Braille image is obtained, including the location information of the bumps. In the following, the present invention will take bump detection as an example, and the detection method of pits is similar.
步骤S2、利用标注信息，截取图像得到正负样本。比如以标注的凸点为中心的周围的区域图像作为正例样本，同样大小的背景和凹点区域作为反例样本。Step S2, using the annotation information, intercepting the image to obtain positive and negative samples. For example, the image of the surrounding area centered on the marked convex point is used as a positive sample, and the background and concave point area of the same size are used as a negative sample.
步骤S3、提取样本的特征向量，训练分类器。优选的可以提取样本的Haar小波特征，训练Adaboost级联分类器。在待检测的盲文图像上，采用滑动窗口方式，提取窗口内图像的相应特征，比如haar特征，利用训练好的Adaboost分类器进行是否是凸点的分类判别。Step S3, extracting feature vectors of samples, and training a classifier. Preferably, the Haar wavelet feature of the sample can be extracted, and the Adaboost cascade classifier can be trained. On the braille image to be detected, the sliding window method is used to extract the corresponding features of the image in the window, such as the haar feature, and the trained Adaboost classifier is used to classify whether it is a convex point.
步骤S4、经过步骤S1和步骤S2可以得到初步检测的凸点位置信息，保存整个盲文图像的凸点信息。比如保存文件名，以及对应的凸点坐标信息。本发明针对扫描仪得到的200dpi的盲文图像，利用优选的Haar+Adaboost的方法，检测一张图像在0.5秒以内。同时凸点的平均识别准确率达到99.74％，召回率94.01％。图7展示了一个利用级联分类器检测的凸点识别结果。Step S4, through steps S1 and S2, the position information of the initially detected bumps can be obtained, and the bump information of the entire Braille image is saved. For example, save the file name and the corresponding bump coordinate information. Aiming at the 200dpi braille image obtained by the scanner, the present invention utilizes the preferred Haar+Adaboost method to detect an image within 0.5 seconds. At the same time, the average recognition accuracy rate of bumps is 99.74%, and the recall rate is 94.01%. Figure 7 shows a bump recognition result detected by cascaded classifiers.
其他可选的方案，可以提取样本的灰度特征，或者HOG方向直方图特征，或者LBP二值纹理特征等特征向量，训练SVM或者随机森林等分类器，同样采用滑动窗口方式进行凸点检测。Other optional schemes can extract grayscale features of samples, or HOG direction histogram features, or feature vectors such as LBP binary texture features, train classifiers such as SVM or random forest, and also use sliding window method for bump detection.
其他可选的方式，可以通过图像分割方法，将盲文点进行前景和背景的分割，从而得到盲文点位置。如果是单面图像就可以直接到的凸点或者凹点信息。如果是双面图像，需要进一步利用特征进行区分凸点还是凹点，从而得到盲文图像上的凸点位置信息。In another optional manner, an image segmentation method may be used to segment the foreground and background of the Braille dots, so as to obtain the positions of the Braille dots. If it is a single-sided image, you can directly access the bump or pit information. If it is a double-sided image, it is necessary to further use features to distinguish between convex points and concave points, so as to obtain the position information of the convex points on the Braille image.
步骤4盲文图像倾斜校正。盲文点字倾斜可能有两种情况，一种是由于采集过程造成的，比如盲文纸张放置倾斜，一种是盲文在初期打印时本身就是倾斜的，导致盲文对应的盲文方行和列不是水平和垂直的，为后期盲文方定位和标注带来很大的误差。因此首先需要进行盲文图像倾斜校正。具体步骤如下：Step 4 Braille image skew correction. Braille characters may be tilted in two ways. One is caused by the acquisition process, such as when the braille paper is placed tilted. The other is that the braille itself is tilted when it is printed in the initial stage, resulting in the braille square rows and columns corresponding to the braille not being horizontal and vertical. , which will bring a lot of error to the positioning and labeling of Braille squares in the later stage. Therefore, it is first necessary to correct the tilt of the Braille image. Specific steps are as follows:
步骤S5、基于步骤1、2、3，得到了盲文图像中的凸点位置信息。Step S5, based on steps 1, 2, and 3, the position information of the bumps in the Braille image is obtained.
步骤S6、较优的，首先利用前面得到的凸点位置信息将凸点和背景二值化。比如，在凸点位置使用一个黑色小正方形代替，背景等则设为全白。或者使用黑色的小圆点表示凸点，背景设为全白。Step S6. Preferably, the bumps and the background are binarized first using the bump position information obtained above. For example, use a small black square instead at the bump position, and set the background to all white. Or use small black dots to represent bumps, and set the background to all white.
步骤S7、将该二值化图像以1°为间隔，进行多次旋转，统计每次旋转后水平投影行像素值和为0的行数和竖直投影列像素和为0的列数总和。空白行列数越多则意味着该旋转角度越接近真实倾斜角度，将空白行列数总和最大对应的旋转角度记为α°。比如，从-5°到5°进行多次旋转。Step S7, the binarized image is rotated multiple times at intervals of 1°, and after each rotation, the sum of the number of rows with horizontally projected row pixel value 0 and the vertically projected column pixel value with 0 sum is counted. The greater the number of blank rows and columns, the closer the rotation angle is to the real tilt angle, and the rotation angle corresponding to the maximum sum of the blank rows and columns is recorded as α°. For example, multiple rotations from -5° to 5°.
步骤S8、为了得到更新的角度，再次旋转步骤S7所得的二值化图像，以0.1°为间隔，从(α-0.5)°到(α+0.5)°进行多次旋转。同步骤S7的方法，将投影空白行列数总和最大对应的旋转角度记为β°。Step S8, in order to obtain an updated angle, rotate the binarized image obtained in step S7 again, and perform multiple rotations at intervals of 0.1° from (α-0.5)° to (α+0.5)°. Similar to the method in step S7, the rotation angle corresponding to the maximum sum of the number of projected blank rows and columns is recorded as β°.
步骤S9、角度β°即为所求得的盲文图像倾斜角度，反方向旋转原盲文图像可得到校正后的盲文图像。In step S9, the angle β° is the obtained inclination angle of the braille image, and the corrected braille image can be obtained by rotating the original braille image in the opposite direction.
通过以上由粗到细的旋转图像，可以快速的获取图像的倾斜角度，误差精细到0.1°。By rotating the image above from coarse to fine, the tilt angle of the image can be quickly obtained, and the error is as fine as 0.1°.
其他可选的倾斜校正方法包括，在盲文图像上放置或粘贴一个黑色矩形框，假设该方框的水平线和竖直线与盲文方的行和列平行，通过校正该矩形框进行盲文图像的倾斜校正。Other optional skew correction methods include placing or affixing a black rectangular box over the braille image, assuming that the horizontal and vertical lines of the box are parallel to the rows and columns of the braille square, and skewing the braille image by correcting the rectangle Correction.
其他可选的倾斜校正方法包括，则提取上盲文图像边缘上的凸点，使用最小二乘法拟合直线来进行倾斜校正。可选的还有，人工交互式的标注出某盲文方行的第一行凸点所在位置，或者其他同一行的凸点位置，利用直线拟合的方式，求出直线的倾斜角度，从而进行盲文图像倾斜校正。Other optional tilt correction methods include extracting convex points on the edge of the upper braille image, and using a least square method to fit a straight line to perform tilt correction. Optionally, manually and interactively mark the position of the first line of bumps in a certain Braille square row, or the position of other bumps in the same line, and use the straight line fitting method to find the inclination angle of the straight line, so as to carry out Braille image skew correction.
其他可选的倾斜校正方法包括，检测盲文图像的纸张边缘直线，利用直线的倾斜来校正盲文图像。Other optional skew correction methods include detecting the straight line at the edge of the paper in the braille image, and correcting the braille image by using the tilt of the straight line.
步骤5、盲文方自适应定位。盲文方定位是盲文识别的关键步骤。现有的盲文方定位算法大多利用规则方法，认为盲文方行列线的排列十分规范，采用标准的盲文方网格即可实现盲文方定位。但在实际处理盲文图像时我们发现，由于生产工艺、扫描设备等原因盲文图像中盲文方行列线排列存在着微小误差，其盲文方行距、方距也并不完全一致。具体步骤如下：Step 5. Adaptive positioning of the braille square. Braille square positioning is a key step in braille recognition. Most of the existing braille square positioning algorithms use the rule method. It is considered that the arrangement of the braille square row and column lines is very standardized, and the braille square positioning can be realized by using the standard braille square grid. However, when actually processing braille images, we found that due to the production process, scanning equipment and other reasons, there are small errors in the arrangement of rows and columns of braille squares in braille images, and the line spacing and square spacing of braille squares are not completely consistent. Specific steps are as follows:
步骤S10、优选的，利用步骤1、2、3、4得到凸点的初步检测结果以及倾斜校正后的盲文图像。或者利用传统的图像分割方法，得到凸点的检测结果，和倾斜校正后的盲文图像。Step S10. Preferably, step 1, 2, 3, and 4 are used to obtain the preliminary detection results of bumps and the Braille image after tilt correction. Or use the traditional image segmentation method to obtain the detection result of the convex point and the braille image after tilt correction.
步骤S11、针对倾斜校正后的图像，利用盲文方三行两列的特点，对凸点位置信息进行纵坐标的聚类，将凸点纵坐标接近的盲文点划分为一组，求其纵坐标均值得到多条预选盲文方水平行线的位置。Step S11, for the tilt-corrected image, use the characteristics of three rows and two columns of the braille square to cluster the ordinate of the bump position information, divide the braille points whose ordinates are close to each other into a group, and find their ordinates The mean gets the positions of multiple preselected braille square horizontal lines.
步骤S12、从上往下找出符合标准的三条水平行线，即相邻两条水平线之间距离符合统计信息中盲文方点距的范围，如果找不到则生成一个默认的盲文方网格，算法结束。Step S12. Find three horizontal lines that meet the standard from top to bottom, that is, the distance between two adjacent horizontal lines meets the range of the Braille square dot pitch in the statistical information. If not found, generate a default Braille square grid , the algorithm ends.
步骤S13、如果找到了，则从这三条水平线位置开始，根据统计得到的盲文方点距、行距等信息分别向上、向下拓展，且拓展的过程中生成以最新拓展的一组三条水平线为基准，同时剔除位置错误的水平线直到达到盲文图像两端，即可得到多组三条水平线一组的盲文方水平线。Step S13, if found, start from the position of these three horizontal lines, expand upwards and downwards respectively according to the statistically obtained Braille square dot spacing, line spacing and other information, and generate a set of newly expanded three horizontal lines as a benchmark during the expansion process , while removing the horizontal lines with wrong positions until they reach both ends of the braille image, then multiple groups of three horizontal lines and one group of braille square horizontal lines can be obtained.
步骤S14、同上述方法可得到多组两条竖直线一组的盲文方竖直线。Step S14, with the above method, multiple groups of two vertical lines and one set of braille square vertical lines can be obtained.
步骤S15、每组中三条水平线和两条竖直线的交叉点即为盲文点可能存在的位置，六个交叉点组成一个盲文方，最终生成整个盲文方网格。Step S15, the intersection of three horizontal lines and two vertical lines in each group is the possible location of Braille dots, six intersection points form a Braille square, and finally generate the entire Braille square grid.
根据上述算法得到的盲文方定位效果如图8所示，可见在凸点检测基础上进行盲文方定位，消除了凹点带来的影响，算法速度快鲁棒性高。The braille square positioning effect obtained according to the above algorithm is shown in Figure 8. It can be seen that the braille square positioning based on the convex point detection eliminates the influence of the concave point, and the algorithm is fast and robust.
步骤6、盲文点计算机辅助标注。当需要标注新的盲文书籍，或者盲文试卷的时候。如果我们已经有了一个盲文点检测的分类器，该分类器可以辅助我们进行新盲文图像的快速标注，即由机器先进行标注，人工再进行修正，从而提升标注效率，减少人工标注劳动量。具体步骤如下。Step 6, Braille dot computer-aided marking. When it is necessary to label new Braille books, or Braille test papers. If we already have a classifier for braille point detection, this classifier can assist us in the rapid labeling of new braille images, that is, the machine will label first, and then manually correct it, so as to improve the labeling efficiency and reduce the labor of manual labeling. Specific steps are as follows.
步骤S16、基于以上步骤1、2、3、4、5，得到具有盲文方定位的凸点检测结果。如图9所示，将该图显示在屏幕上。Step S16, based on the above steps 1, 2, 3, 4, 5, obtain the bump detection result with Braille square positioning. As shown in Figure 9, the graph is displayed on the screen.
步骤S17、利用鼠标点选需要修改的盲文方位置，获取该盲文方的信息。Step S17, use the mouse to click on the position of the braille square to be modified, and obtain the information of the braille square.
步骤S18、按快捷键删除该盲文方的标注信息。比如DEL进行盲文方标注的删除。Step S18, pressing the shortcut key to delete the marking information of the braille party. For example, DEL deletes the braille square label.
步骤S19、用键盘快捷键进行盲文方内盲文点的快速填充，并在屏幕上实时显示已填充好的凸点。在实际标注时，可采用小键盘的数字键，仅选择某个位置上有凸点的数字。比如，如果该盲文方中仅有1、2、5三个位置有凸点，则仅利用数字键选择1、2、5三个键即可完成该盲文方凸点的填充。同时在屏幕上显示已经填充好的凸点。Step S19 , using keyboard shortcuts to quickly fill the Braille dots in the Braille square, and display the filled bumps on the screen in real time. In actual marking, you can use the number keys on the small keyboard to select only the numbers with raised dots at a certain position. For example, if there are only three positions 1, 2, and 5 in the braille square with bumps, the filling of the bumps in the braille square can be completed only by selecting the three keys 1, 2, and 5 with the number keys. At the same time, the filled bumps are displayed on the screen.
步骤S20、也可通过键盘快捷键进行盲文方位置微调，从而更精确的匹配盲文图像上的某一个盲文方。In step S20, the position of the braille square can also be fine-tuned through keyboard shortcuts, so as to more accurately match a certain braille square on the braille image.
步骤S21、该盲文方标注完之后，可以采用快捷键进行盲文方位置的移动，移动到下一个盲文方位置。由于中国盲文的排列遵循了国家标准，盲文方行间距和列间距有固定的范围，可以结合盲文图像采集的分辨率，提前统计该盲文图像中对应的盲文方行间距和列间距，方便在交互式操作时直接进行行列的移动。比如，利用键盘上的“上下左右”方向键进行盲文方位置的单步移动，每次移动距离可以提前根据盲文图像进行统计和确定。也可以采用步骤S17，直接点选的方式，选取下一个需要标注的盲文方。这里也可以进一步用快捷键微调盲文方的位置，方法同上步骤S20。Step S21, after marking the braille square, the shortcut key can be used to move the position of the braille square to the next braille square. Since the arrangement of Braille in China complies with national standards, the row spacing and column spacing of Braille squares have a fixed range, and the corresponding Braille square row spacing and column spacing in the Braille image can be counted in advance based on the resolution of Braille image collection, which is convenient for interactive Directly move the row and column during the type operation. For example, use the "up, down, left, and right" arrow keys on the keyboard to move the position of the braille square in a single step, and the distance of each movement can be counted and determined in advance based on the braille image. Step S17 can also be used to directly select the next braille square to be marked. Here, you can further fine-tune the position of the braille square with shortcut keys, the method is the same as step S20 above.
步骤S22、重复步骤S17到步骤S21，完成对整张盲文图像盲文点的交互式辅助修改。Step S22, repeating steps S17 to S21 to complete the interactive auxiliary modification of the Braille dots on the entire Braille image.
步骤S23、标注结束之后，按快捷键保存该盲文图像的标注信息。比如，点击“S“键进行标注信息的保存，以盲文方的形式，保存盲文方位置信息，以及填充的盲文点的位置信息等。Step S23, after the labeling is finished, press the shortcut key to save the labeling information of the braille image. For example, click the "S" button to save the marking information, and save the position information of the braille square and the position information of the filled braille point in the form of a braille square.
步骤7、高精度盲文点和盲文方识别。通过以上步骤1到步骤5，得到盲文方的定位结果，可以利用盲文方位置信息，去除Adaboost级联分类器带来的部分误报，因为凸点基本上会出现在盲文方的六个盲文点位置，从而可以提升基于Adaboost分类器的识别效果。更重要的是在盲文方定位基础上，可以仅针对每个盲文方对应的6个盲文点区域，利用更复杂的分类器来提升凸点识别的准确性。具体步骤如下：Step 7. High-precision Braille dot and Braille square recognition. Through the above steps 1 to 5, the positioning results of the braille square can be obtained, and the position information of the braille square can be used to remove some false positives caused by the Adaboost cascade classifier, because the bumps basically appear on the six braille dots of the braille square position, which can improve the recognition effect based on the Adaboost classifier. More importantly, on the basis of braille square positioning, a more complex classifier can be used to improve the accuracy of bump recognition only for the 6 braille dot areas corresponding to each braille square. Specific steps are as follows:
步骤S24、优选的，基于步骤1、2得到凸点标注信息，或者利用步骤1、2、3、4、5、6得到凸点标注信息。Step S24, preferably, obtain the bump marking information based on steps 1 and 2, or use steps 1, 2, 3, 4, 5, and 6 to obtain the bump marking information.
步骤S25、截取以凸点为中心点的图像作为正例样本，以凹点和背景的中心点的图像作为反例样本。比如采用24*24的样本大小。Step S25 , intercepting the image with the convex point as the center point as a positive sample, and taking the image with the center point of the concave point and the background as a negative sample. For example, a sample size of 24*24 is used.
步骤S26、提取样本的多种特征，分别训练多个分类器。优选的，可以提取灰度特征，可以提取HOG梯度直方图特征，可以提取LBP局部二值特征，或者将HOG和LBP进一步串联的特征，并采用支持向量机SVM或者随机森林或者其他的分类器，训练凸点的分类器，同时得到多个分类器。Step S26, extracting various features of the samples, and training multiple classifiers respectively. Preferably, grayscale features can be extracted, HOG gradient histogram features can be extracted, LBP local binary features can be extracted, or features further concatenated with HOG and LBP, and support vector machine SVM or random forest or other classifiers are used, Train a bump classifier and get multiple classifiers at the same time.
步骤S27、基于步骤5得到盲文方定位信息。Step S27, obtain braille party positioning information based on step 5.
步骤S28、截取以每个盲文方对应的6个盲文点为中心的小图，将这些小图分别提取多种特征，利用训练好的分类器分别进行凸点的分类判别。优选的，可以提取HOG，LBP，串联的HOG_LBP特征，然后使用三个对应的SVM分类器进行识别，包括HOG-SVM，LBP-SVM，HOG_LBP+SVM。Step S28 , intercepting small images centered on the 6 Braille dots corresponding to each Braille square, extracting various features from these small images, and using the trained classifier to classify and distinguish the convex points. Preferably, HOG, LBP, and concatenated HOG_LBP features can be extracted, and then three corresponding SVM classifiers can be used for identification, including HOG-SVM, LBP-SVM, and HOG_LBP+SVM.
步骤S29、将多个SVM分类器分类结果，与级联分类器进行结果融合。最终的融合结果为不同分类器的结果与其对应的权值的乘积。如果最终的融合结果超过某阈值，说明大多数分类器的输出是凸点，则认为其存在凸点。凹点的检测方法同凸点。Step S29, merging the classification results of multiple SVM classifiers with the cascaded classifiers. The final fusion result is the product of the results of different classifiers and their corresponding weights. If the final fusion result exceeds a certain threshold, indicating that the output of most classifiers is a convex point, it is considered that there is a convex point. The detection method of the concave point is the same as that of the convex point.
步骤S30、可以进一步将盲文方内的凸点信息转化为盲文方信息，从而完成基于盲文方的检测和识别。In step S30, the convex point information in the Braille square can be further transformed into Braille square information, so as to complete the detection and recognition based on the Braille square.
步骤S31、可以融合正反面的盲文点的识别结果，来提高盲文点和盲文方的识别性能。In step S31, the recognition results of the front and back Braille dots may be fused to improve the recognition performance of the Braille dots and Braille squares.
步骤S32、还可以将盲文方的信息翻译为汉语文字和句子，根据句子分析来排查检测错误的盲方，从而提高盲文编辑人员的工作效率。Step S32, it is also possible to translate the information of Braille squares into Chinese characters and sentences, and troubleshoot wrongly detected Braille squares according to sentence analysis, thereby improving the work efficiency of Braille editors.
基于以上步骤，基于组合分类器的方法，对盲文图像的凸点平均识别性能，达到了准确率99.75％，召回率99.58％。对盲文方的平均识别性能，达到了准确率98.27％，召回率98.84％。本发明针对扫描仪得到的200dpi的盲文图像，利用以上步骤1至步骤7得到盲文点和盲文方检测结果，检测一张图像平均在1.8秒以内。Based on the above steps, based on the method of combining classifiers, the average recognition performance of bumps in Braille images has reached an accuracy rate of 99.75% and a recall rate of 99.58%. For the average recognition performance of Braille squares, the accuracy rate is 98.27%, and the recall rate is 98.84%. The present invention aims at the 200dpi Braille image obtained by the scanner, uses the above steps 1 to 7 to obtain the detection results of Braille dots and Braille squares, and detects an image within 1.8 seconds on average.
以下为与上述方法实施例对应的系统实施例，本实施系统可与上述实施方式互相配合实施。上述施方式中提到的相关技术细节在本实施系统中依然有效，为了减少重复，这里不再赘述。相应地，本实施系统中提到的相关技术细节也可应用在上述实施方式中。The following are system embodiments corresponding to the above-mentioned method embodiments, and this implementation system can be implemented in cooperation with the above-mentioned embodiments. The relevant technical details mentioned in the foregoing implementation manners are still valid in this implementation system, and will not be repeated here in order to reduce repetition. Correspondingly, relevant technical details mentioned in this implementation system may also be applied in the above implementation manners.
本发明还提出了一种盲文点交互式标注系统，其中包括：The present invention also proposes an interactive marking system for braille dots, which includes:
采集模块，用于通过采集设备获取纸版盲文的数字化图像；The collection module is used to obtain the digitized image of the paper version of Braille through the collection device;
标注模块，用于以盲文方为单位对该数字化图像进行交互式盲文点标注；The labeling module is used to carry out interactive braille dot labeling on the digitized image in units of braille squares;
其中该标注模块包括：Among them, the labeling module includes:
盲文方选取模块，将该数字化图像显示在屏幕上，并通过交互式设备在该数字化图像上选取某一个盲文的盲文方位置；The braille square selection module displays the digitized image on the screen, and selects a braille square position on the digitized image through an interactive device;
显示模块，用于将属于该盲文方位置的盲文方标识显示在屏幕上，通过交互设备为该盲文方标识内的盲文点进行标注，并在屏幕上实时显示已标注完成的盲文点；移动该盲文方位置至下一个盲文方，或执行该步骤22选取下一个盲文的盲文方位置，重复执行该步骤23直到对该数字化图像内全部盲文点完成标注。The display module is used to display the braille party logo belonging to the braille party position on the screen, mark the braille dots in the braille party logo through the interactive device, and display the marked braille dots on the screen in real time; move the From the braille square position to the next braille square, or perform step 22 to select the braille square position of the next braille, and repeat step 23 until all the braille points in the digitized image are marked.
该盲文点交互式标注系统，其中该采集设备包括扫描仪、摄像机或盲文图像采集仪器；该纸版盲文包括凸点和/或凹点形式的盲文点。In the Braille dot interactive labeling system, the collection device includes a scanner, a video camera or a Braille image collection device; the paper version of the Braille includes Braille dots in the form of raised dots and/or concave dots.
该盲文点交互式标注系统，其中该盲文方标识为盲文方对应的6个盲文点或盲文方对应的“日”字形方格，该“日”字形方格的每个交叉点代表一个盲文点位置。The braille dot interactive labeling system, wherein the braille square is identified as 6 braille dots corresponding to the braille square or a "day"-shaped square corresponding to the braille square, and each intersection point of the "day"-shaped square represents a braille dot Location.
该盲文点交互式标注系统，其中根据中国盲文书写规范和该数字化图像的分辨率，确定盲文方对应的6个盲文点间的间距或“日”字形方格的尺寸比例。In the Braille dot interactive marking system, according to the Chinese Braille writing standard and the resolution of the digitized image, the spacing between the 6 Braille dots corresponding to the Braille square or the size ratio of the "日"-shaped square is determined.
该盲文点交互式标注系统，其中该交互式设备包括键盘、鼠标、触控板。In the braille dot interactive marking system, the interactive device includes a keyboard, a mouse, and a touch panel.
虽然本发明以上述实施例公开，但具体实施例仅用以解释本发明，并不用于限定本发明，任何本技术领域技术人员，在不脱离本发明的构思和范围内，可作一些的变更和完善，故本发明的权利保护范围以权利要求书为准。Although the present invention is disclosed with the above embodiments, the specific embodiments are only used to explain the present invention, and are not intended to limit the present invention. Any person skilled in the art can make some changes without departing from the concept and scope of the present invention. and perfection, so the scope of protection of the present invention is defined by the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711070494.0ACN108062886A (en) | 2017-11-03 | 2017-11-03 | Braille point interactive mode mask method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711070494.0ACN108062886A (en) | 2017-11-03 | 2017-11-03 | Braille point interactive mode mask method and system |
| Publication Number | Publication Date |
|---|---|
| CN108062886Atrue CN108062886A (en) | 2018-05-22 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711070494.0APendingCN108062886A (en) | 2017-11-03 | 2017-11-03 | Braille point interactive mode mask method and system |
| Country | Link |
|---|---|
| CN (1) | CN108062886A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298236A (en)* | 2019-05-20 | 2019-10-01 | 中国科学院计算技术研究所 | A kind of braille automatic distinguishing method for image and system based on deep learning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080318191A1 (en)* | 2004-03-25 | 2008-12-25 | Mcadams John B | Braille type device, system, and method |
| CN101840648A (en)* | 2010-04-28 | 2010-09-22 | 长春大学 | Automatic braille marking system |
| CN102063628A (en)* | 2011-01-14 | 2011-05-18 | 长春大学 | Method for extracting double-sided braille |
| CN202150089U (en)* | 2011-07-18 | 2012-02-22 | 中国科学院计算技术研究所 | Braille converter |
| CN105404621A (en)* | 2015-09-25 | 2016-03-16 | 中国科学院计算技术研究所 | Method and system for blind people to read Chinese character |
| CN106446885A (en)* | 2016-09-21 | 2017-02-22 | 北京联合大学 | Paper-based Braille recognition method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080318191A1 (en)* | 2004-03-25 | 2008-12-25 | Mcadams John B | Braille type device, system, and method |
| CN101840648A (en)* | 2010-04-28 | 2010-09-22 | 长春大学 | Automatic braille marking system |
| CN102063628A (en)* | 2011-01-14 | 2011-05-18 | 长春大学 | Method for extracting double-sided braille |
| CN202150089U (en)* | 2011-07-18 | 2012-02-22 | 中国科学院计算技术研究所 | Braille converter |
| CN105404621A (en)* | 2015-09-25 | 2016-03-16 | 中国科学院计算技术研究所 | Method and system for blind people to read Chinese character |
| CN106446885A (en)* | 2016-09-21 | 2017-02-22 | 北京联合大学 | Paper-based Braille recognition method and system |
| Title |
|---|
| 尹佳: "《纸介盲文自动识别系统关键技术研究》", 《中国优秀硕士学位论文全文数据库（电子期刊） 信息科技辑》* |
| 尹佳等: "《盲文自动识别方法研究》", 《长春大学学报》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298236A (en)* | 2019-05-20 | 2019-10-01 | 中国科学院计算技术研究所 | A kind of braille automatic distinguishing method for image and system based on deep learning |
| CN110298236B (en)* | 2019-05-20 | 2021-11-30 | 中国科学院计算技术研究所 | Automatic Braille image identification method and system based on deep learning |
| Publication | Publication Date | Title |
|---|---|---|
| CN108052955B (en) | High-precision Braille identification method and system | |
| CN110298236B (en) | Automatic Braille image identification method and system based on deep learning | |
| US8755595B1 (en) | Automatic extraction of character ground truth data from images | |
| CN110597806A (en) | A system and method for wrong question set generation and answer statistics based on review recognition | |
| CN108052936B (en) | A method and system for automatic tilt correction of braille images | |
| CN106156761A (en) | The image form detection of facing moving terminal shooting and recognition methods | |
| CN109033046A (en) | Structuring visible document snap information input system and method | |
| JP4694613B2 (en) | Document orientation determination apparatus, document orientation determination method, program, and recording medium therefor | |
| CN113657162A (en) | Bill OCR recognition method based on deep learning | |
| CN104715256A (en) | Auxiliary calligraphy exercising system and evaluation method based on image method | |
| Kaundilya et al. | Automated text extraction from images using OCR system | |
| CN106980857B (en) | Chinese calligraphy segmentation and recognition method based on copybook | |
| CN114821620B (en) | Text content extraction and recognition method based on vertical merging of line text boxes | |
| CN112446259A (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN106446885A (en) | Paper-based Braille recognition method and system | |
| CN107958261B (en) | Braille point detection method and system | |
| CN108304836A (en) | A kind of books Ordering Detection Algorithm based on image | |
| CN113436222A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN114565926A (en) | Two-stage Braille detection and identification method based on target detection | |
| CN111612045B (en) | Universal method for acquiring target detection data set | |
| CN117649670A (en) | Document layout analysis model training method, application method, computer device and computer readable storage medium | |
| CN108062548B (en) | A Braille square adaptive positioning method and system | |
| CN112861794A (en) | Universal detection algorithm for optical printing texts and scene texts | |
| CN114782975A (en) | A method for OCR identification of electronic file table format | |
| CN114241492A (en) | Method for recognizing handwritten text of composition manuscript paper and reproducing text structure |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20180522 |