01 资源

OpenCV自带的OCR文本检测用例，opencv_contrib\modules\text\samples\textdetection.cpp。textdetection.cpp检测图片中文本。
模型文件(需要拷贝到Debug或Release目录中)：

opencv_contrib/modules/text/samples/trained_classifierNM1.xml
opencv_contrib/modules/text/samples/trained_classifierNM2.xml

测试图片：

opencv_contrib/modules/text/samples/scenetext_segmented_word01.jpg
opencv_contrib/modules/text/samples/scenetext_segmented_word01_mask.png
opencv_contrib/modules/text/samples/scenetext_segmented_word02.jpg
opencv_contrib/modules/text/samples/scenetext_segmented_word02_mask.png
opencv_contrib/modules/text/samples/scenetext_segmented_word03.jpg
opencv_contrib/modules/text/samples/scenetext_segmented_word03_mask.png
...

02 编译textdetection

参考opencv01 相对完整的编译opencv3.3.0 win版本，编译opencv3.3.0 vs2015版本。
生成文件：D:\git\opencv\build\v3.3.0\x64\bin\Debug\text-example-textdetection.exe。

03 textdetection项目配置

设置textdetection项目为启动项。

# 如果路径中有空格，需要使用双引号,参数路径根据自己实际情况调整
配置属性==>调试==>命令参数=../../../../../../opencv_contrib/modules/text/samples/scenetext_segmented_word03.jpg 
配置属性==>调试==>工作目录=$(OutDir)

04 运行结果

scenetext_segmented_word03.jpg原图：
运行结果: