今天我在给大家分享一个 OCR 应用——ddddocr自动识别验证码。
前面 4 个d是“带带弟弟”的首拼音。[/笑哭]。
项目地址:https://github.com/sml2h3/ddddocr。
使用的时候用pip命令直接安装即可pip install ddddocr。
OCR的核心技术包含两方面,一是目标检测模型检测图片中的文字,二是文字识别模型,将图片中的文字转成文本文字。
第一类验证码最简单,它们没有复杂的背景图片,所以目标检测模型可以省略,直接将图片送入文字识别模型即可。
识别代码如下:
import ddddocr<br><span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">from</span> PIL import Image<br><br># 模型<br>ocr <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> ddddocr<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.DdddOcr</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>beta<span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span><span style="color: rgb(153, 0, 85); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">True</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br># 验证码图片<br>with open<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">'test.jpg'</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">'rb'</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span> <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">as</span> f<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">:</span><br>image <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> f<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.read</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br>res <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> ocr<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.classification</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>image<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br># 验证码文字内容<br>print<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>res<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span>
第二类验证码有复杂的背景,需要先用目标检测模型框出文字,在进行识别。
代码如下:
import ddddocr<br>import cv2<br><br>det <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> ddddocr<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.DdddOcr</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>det<span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span><span style="color: rgb(153, 0, 85); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">True</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br>with open<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">"test2.jpg"</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">'rb'</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span> <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">as</span> f<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">:</span><br>image <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> f<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.read</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br># 目标检测<br>poses <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> det<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.detection</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>image<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br>print<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>poses<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br>im <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> cv2<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.imread</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">"test2.jpg"</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br># 遍历检测出的文字<br>for box <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">in</span> poses<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">:</span><br>x1<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> y1<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> x2<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> y2 <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> box<br># 给每个文字画矩形框<br>im <span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span> cv2<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.rectangle</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>im<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>x1<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> y1<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span>x2<span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> y2<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> color<span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">0</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">0</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> <span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">255</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> thickness<span style="color: rgb(215, 58, 73); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">=</span><span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">2</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span><br><br>cv2<span style="color: rgb(0, 92, 197); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">.imwrite</span><span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">(</span><span style="color: rgb(102, 153, 0); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">"result.jpg"</span><span style="color: rgb(89, 89, 89); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">,</span> im<span style="color: rgb(153, 153, 119); margin: 0px; padding: 0px; background: none 0% 0% / auto repeat scroll padding-box border-box rgba(0, 0, 0, 0);">)</span>
输出结果如下:
可以看到文字部分已经被框出来了,如果我们在上述代码直接将im[y1:y2, x1:x2]送入文字识别模型,就可以识别出对应的文本内容了。
ddddocr还能识别下面这种带滑块的验证码。
这种虽然不属于OCR的业务范畴,但作为一个通用的验证码识别工具,作者还是支持了,必须给作者点个赞。
以上是用OCR技术,自动识别各种验证码,工具已开源的详细内容。更多信息请关注PHP中文网其他相关文章!