以下我一直以为我下载的是opencv4.1.0的源码编译的，其实是opencv4.4.0。另外ubuntu16.04下编译的opencv4.1.0在ubuntu20.04上可以直接使用，无问题。当然我下面在ubuntu20.04下编译的opencv4.4.0（我一直以为是4.1.0）在ubuntu20.04下使用也没问题。
看过之前介绍的应该知道我用的是ubuntu16.04+opencv3.4.1+tensorflow，用了一年多比较稳定。但这次因要升级到ubuntu20.04，结果整个移植过去，却出现很多报错如：
其实本来还有几个库没有，其实不是没有，是在ubuntu16.04下比如是libxxx5.so，现在会报错说没有libxxx6.so，所以我直接软链接过去解决的。上图中“libtensorflow_cc.so:.dynsym local symbol at index 1552(>=sh_info of 2)”
/usr/bin/ld: /usr/lib/gcc/x86_64-linux-gnu/9/../../../../lib/libtensorflow_cc.so: .dynsym local symbol at index 1552 (>= sh_info of 2)
/usr/bin/ld: /usr/lib/gcc/x86_64-linux-gnu/9/../../../../lib/libtensorflow_cc.so: .dynsym local symbol at index 2428 (>= sh_info of 2)
/usr/bin/ld: /usr/lib/gcc/x86_64-linux-gnu/9/../../../../lib/libtensorflow_cc.so: .dynsym local symbol at index 2429 (>= sh_info of 2)类似这的三条报错很好解决，就是在linker时加上-fuse-ld=gold即可。
如上所示，别的IDE也是直接在linker后加-fuse-ld=gold即可。
看已经可以正常输出类别了。
**********************************************************************************************************
但是图1的那些关于opencv的报错我没解决掉，于是我直接在ubuntu20.04下cmake3.18.1编译opencv4.1.0，其实网上很多教程，但在cmake时日志提示报错如下：
#use_cache "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache"
#do_unpack "ippicv_2020_lnx_intel64_20191018_general.tgz" "7421de0095c7a39162ae13a6098782f9" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/a56b6ac6f030c312b2dce17430eef13aed9af274/ippicv/ippicv_2020_lnx_intel64_20191018_general.tgz" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/3rdparty/ippicv"
#check_md5 "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/ippicv/7421de0095c7a39162ae13a6098782f9-ippicv_2020_lnx_intel64_20191018_general.tgz"
#mismatch_md5 "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/ippicv/7421de0095c7a39162ae13a6098782f9-ippicv_2020_lnx_intel64_20191018_general.tgz" "d41d8cd98f00b204e9800998ecf8427e"
#delete "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/ippicv/7421de0095c7a39162ae13a6098782f9-ippicv_2020_lnx_intel64_20191018_general.tgz"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/ippicv/7421de0095c7a39162ae13a6098782f9-ippicv_2020_lnx_intel64_20191018_general.tgz" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/a56b6ac6f030c312b2dce17430eef13aed9af274/ippicv/ippicv_2020_lnx_intel64_20191018_general.tgz"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#match_hash_in_cmake_cache "OCV_DOWNLOAD_ADE_HASH_3rdparty_ade_v0_1_1f_zip"
#do_copy "boostdesc_bgm.i" "0ea90e7a8f3f7876d450e4149c97c74f" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_bgm.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/0ea90e7a8f3f7876d450e4149c97c74f-boostdesc_bgm.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_bgm_bi.i" "232c966b13651bd0e46a1497b0852191" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm_bi.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_bgm_bi.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/232c966b13651bd0e46a1497b0852191-boostdesc_bgm_bi.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm_bi.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_bgm_hd.i" "324426a24fa56ad9c5b8e3e0b3e5303e" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm_hd.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_bgm_hd.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/324426a24fa56ad9c5b8e3e0b3e5303e-boostdesc_bgm_hd.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_bgm_hd.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_binboost_064.i" "202e1b3e9fec871b04da31f7f016679f" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_064.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_binboost_064.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/202e1b3e9fec871b04da31f7f016679f-boostdesc_binboost_064.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_064.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_binboost_128.i" "98ea99d399965c03d555cef3ea502a0b" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_128.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_binboost_128.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/98ea99d399965c03d555cef3ea502a0b-boostdesc_binboost_128.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_128.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_binboost_256.i" "e6dcfa9f647779eb1ce446a8d759b6ea" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_256.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_binboost_256.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/e6dcfa9f647779eb1ce446a8d759b6ea-boostdesc_binboost_256.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_binboost_256.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "boostdesc_lbgm.i" "0ae0675534aa318d9668f2a179c2a052" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_lbgm.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/boostdesc_lbgm.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/boostdesc/0ae0675534aa318d9668f2a179c2a052-boostdesc_lbgm.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/34e4206aef44d50e6bbcd0ab06354b52e7466d26/boostdesc_lbgm.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "vgg_generated_48.i" "e8d0dcd54d1bcfdc29203d011a797179" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_48.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/vgg_generated_48.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/vgg/e8d0dcd54d1bcfdc29203d011a797179-vgg_generated_48.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_48.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "vgg_generated_64.i" "7126a5d9a8884ebca5aea5d63d677225" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_64.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/vgg_generated_64.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/vgg/7126a5d9a8884ebca5aea5d63d677225-vgg_generated_64.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_64.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "vgg_generated_80.i" "7cd47228edec52b6d82f46511af325c5" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_80.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/vgg_generated_80.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/vgg/7cd47228edec52b6d82f46511af325c5-vgg_generated_80.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_80.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "vgg_generated_120.i" "151805e03568c9f490a5e3a872777b75" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_120.i" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/downloads/xfeatures2d/vgg_generated_120.i"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/xfeatures2d/vgg/151805e03568c9f490a5e3a872777b75-vgg_generated_120.i" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/fccf7cd6a4b12079f73bbfb21745f9babcd4eb1d/vgg_generated_120.i"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
#
#do_copy "face_landmark_model.dat" "7505c44ca4eb54b4ab1e4777cb96ac05" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/8afa57abc8229d611c4937165d20e2a2d9fc5a12/face_landmark_model.dat" "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/share/opencv4/testdata/cv/face/"
#missing "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/build/share/opencv4/testdata/cv/face//face_landmark_model.dat"
#cmake_download "/home/jumper/thirdparty/opencv-4.1.0/opencv-master/.cache/data/7505c44ca4eb54b4ab1e4777cb96ac05-face_landmark_model.dat" "https://raw.githubusercontent.com/opencv/opencv_3rdparty/8afa57abc8229d611c4937165d20e2a2d9fc5a12/face_landmark_model.dat"
#try 1
# Trying 0.0.0.0:443...
# connect to 0.0.0.0 port 443 failed: 拒绝连接
# Trying :::443...
# connect to :: port 443 failed: 拒绝连接
# Failed to connect to raw.githubusercontent.com port 443: 拒绝连接
# Closing connection 0
# 可以从日志看到我有7个boostdesc_XXX.i和4个vgg.i，1个ippicv和1个face.dat下载失败。日志中也可以看到13个文件的网址，于是我一个个下载，当然有的不好下载，我就复制过来的（当然最好去找些网盘之类的下载链接，我的7个boostdesc最后是找的别人网盘中的链接）。
挣扎好久，终于解决，以下是一些坑的记录：
1、ubuntu20.04中.cache文件夹居然是隐藏的！比如我下载的opencv4.1.0源码一个文件夹是opencv_master，另一个文件夹是opencv_contrib_master，那么这个.cache就隐藏在opencv_master文件夹下。一定要在终端用命令去定位到这个文件夹，可以看到这个文件夹下至少有data（用于存放face.dat文件）、ippicv（用于存放ippicv)、xfeatures2d这三个文件夹，其中xfeatures2d下有vgg、boostdesc两个子文件夹。首先用命令行将上图中下载的这13个文件夹复制一份到.cache对应文件夹中。
2、从日志可以看到，这13个文件，还要对齐按照日志中的要求进行改名，
改名后，再将这13个文件夹也复制一份到.cache文件夹的对应文件夹中。
3、再次重新cmake一次，此时可以看到只会报boost_desc与face.dat的错了，VGG和ippicv都不会再显示mismatch_md5了，而是显示match_cmake之类的，不用管，只要没有mismatch_md5就表示OK。同时，可以看到build文件夹下自动生成了一个downloads文件夹，此文件夹下有一个xfeatures2d文件夹，里面有自动生成4个vgg文件。这也表示VGG成功。
4、怎么解决boost_desc与face.dat报错，我试了很久，网上方法都试过，但没解决。因为cmake-configure后，这8个文件总会被0字节的同名文件替代，比如0ae0675534aa318d9668f2a179c2a052（这一串数字我称为md5码）-boostdesc_lbgm 复制过去时明明不是0字节，但cmake/configure后会变成0字节，导致报错。
最后我实在没办法了，按照错误日志上的提示，意思是说md5码不匹配。比如对0ae0675534aa318d9668f2a179c2a052-boostdesc_lbgm.i我就去查这一串对应的md5码是什么：
通过这命令可以看到0ae0675534aa318d9668f2a179c2a052（错误md5码）对应的码实际是bf7e3c0acd53bf4cccfb9c02a0a46b69（正确md5码），所以将这7个boost_desc文件和face.dat文件分别找到正确md5码，然后重命名，比如我的这个文件应重命名为bf7e3c0acd53bf4cccfb9c02a0a46b69-boostdesc_lbgm.i，然后将这8个文件分别复制一份到.cache对应位置。同时，找到这8个文件相应的cmake配置文件，比如7个boost_desc.i文件是在opencv_contrib_master/modules/xfeatures2d/.../download_boostdesc_cmakelist（有点像这个名字的文件中），打开就是我上图的样子，然后将原来的那7个md5注释掉，换成正确的md5码。这样boostdesc.i的7个问题就解决了。
至于face.dat这个文件的问题其实与boost_desc.i处理一样，只不过其cmake配置文件路径不一样（自己找找，好像在modules/face下面的CMakelist里），然后将错误的md5码改成正确的md5即可。
cmake重新编译，所有都正常通过，不会再报错！！！同时可以看到downloads文件夹下自动生成了所有的boost_desc文件！
然后就开始对opencv_master/build文件夹下进行编译，成功。
然后可以看到build文件夹下生成了include和lib，自己可以在别的地方新建一个文件夹如opencv4.1.0_thirdparty（可以作为动态链接库了），将include和lib复制过去，同时将opencv_master和opencv_contrib_master下的各个modules下的文件夹都看一遍，只要有include/opencv2/下有文件夹和文件的都拷贝进opencv4.1.0_thirdparty/include/opencv2/下，这样整个opencv4.1.0_thirdparty才可以拷贝到别的电脑上使用。
******************************************************************************************************
另外我在ubuntu20.04下发现奇怪问题，
我编译完后，打开编译生成的文件竟然不是可执行文件，而是shared library，所以总是提示找不到binary，无法在IDE下运行或调试。但是在终端运行这个shared library也出了结果。我同事试了用QT也是这样。明明我们IDE配置啥的都是照搬16.04啊。
然后我试了下这样run/debug，就可以在IDE下运行或调试了：
但原因不知。
****************************************************************************************************************************
另外我发现工程此时在ubuntu20.04+opencv4.1下报了个问题：
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.4.0-dev) /home/jumper/thirdparty/opencv-4.1.0/opencv-master/modules/imgproc/src/convhull.cpp:359: error: (-5:Bad argument) The convex hull indices are not monotonous, which can be in the case when the input contour contains self-intersections in function 'convexityDefects'这个轮廓不属于simple型轮廓，就报我上面那个错。其实我看了下这种报错说不单调，说有交叉，说不属于simple型，但我输出了出问题的轮廓以及对应点：
看起来没什么异常，但在求其中一处的凹陷时如下图我画的白色部分，求这里的凹陷时报那个错：
这些白色点我输出是这样：感觉就是不连续，然后也没实质交叉，所以没太明白具体要求是怎么样才不报错。
[2006, 598]
[2005, 599]
[2005, 600]
[2003, 602]
[2003, 603]
[2002, 604]
[2001, 604]
[2000, 605]
[1999, 605]
[1998, 606]
[1997, 606]
[1996, 605]
[1995, 606]
[1989, 606]
[1988, 605]
[1986, 605]
[1985, 604]
[1982, 604]
[1983, 605]
[1982, 606]
[1981, 606]
[1980, 607]
[1979, 607]
[1978, 608]
[1977, 608]
[1976, 609]
[1976, 611]
[1977, 610]
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.4.0-dev) /home/jumper/thirdparty/opencv-4.1.0/opencv-master/modules/imgproc/src/convhull.cpp:359: error: (-5:Bad argument) The convex hull indices are not monotonous, which can be in the case when the input contour contains self-intersections in function 'convexityDefects'于是我自己想了个办法如下，将之前所有直接使用opencv4.1.0中的convexityDefects的地方，改成我写的这个函数，如果返回值小于0（就是可能遇到了上面报错的那种情况），就舍弃此次凹陷点。因为不符合查找凹陷点的条件。
//convexityDefects(contours[i],hullsI[i],defects[i]);
int convexflag=debugconvexdetect(contours[i],hullsI[i],defects[i]);
if(convexflag<0)
continue;C++下的debugconvexdetect这个函数以及python下的解决办法我都上传到 https://download.csdn.net/download/wd1603926823/88913950
改成这样就好了。目前测试稳定，无问题。也给别人试过，同样解决问题。
**************************************************************************************************************************************
发现opencv4.1.0下给图片标注中文，使用原来的代码不行，然后我改了下，就行了。
#ifndef OPENCV_CVX_TEXT_2007_08_31_H
#define OPENCV_CVX_TEXT_2007_08_31_H
#include "ft2build.h"
#include FT_FREETYPE_H
//#include "debug.h"
//#include <cv.h>
//#include <highgui.h>
#include <opencv.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include <locale.h>
#include <string>
/**
* \class cvxText
* \brief OpenCV中输出汉字
*
* OpenCV中输出汉字。字库提取采用了开源的FreeFype库。由于FreeFype是
* GPL版权发布的库，和OpenCV版权并不一致，因此目前还没有合并到OpenCV
* 扩展库中。
*
* 显示汉字的时候需要一个汉字字库文件，字库文件系统一般都自带了。
* 这里采用的是一个开源的字库：“文泉驿正黑体”。
*
* 关于"OpenCV扩展库"的细节请访问
* http://code.google.com/p/opencv-extension-library/
*
* 关于FreeType的细节请访问
* http://www.freetype.org/
* */
class cvxText
{
// 禁止copy
cvxText& operator=(const cvxText&);
public:
/**
* 装载字库文件
*/
cvxText(const char *freeType);
virtual ~cvxText();
/**
* 获取字体。目前有些参数尚不支持。
*
* \param font 字体类型, 目前不支持
* \param size 字体大小/空白比例/间隔比例/旋转角度
* \param underline 下画线
* \param diaphaneity 透明度
*
* \sa setFont, restoreFont
*/
void getFont(int *type,cv::Scalar *size=NULL, bool *underline=NULL, float *diaphaneity=NULL);
/**
* 设置字体。目前有些参数尚不支持。
*
* \param font 字体类型, 目前不支持
* \param size 字体大小/空白比例/间隔比例/旋转角度
* \param underline 下画线
* \param diaphaneity 透明度
*
* \sa getFont, restoreFont
*/
void setFont(int *type,cv::Scalar *size=NULL, bool *underline=NULL, float *diaphaneity=NULL);
/**
* 恢复原始的字体设置。
*
* \sa getFont, setFont
*/
void restoreFont();
/**
* 输出汉字(颜色默认为黑色)。遇到不能输出的字符将停止。
*
* \param img 输出的影象
* \param text 文本内容
* \param pos 文本位置
*
* \return 返回成功输出的字符长度，失败返回-1。
*/
int putText(cv::Mat &img, const char *text, cv::Point pos);
/**
* 输出汉字。遇到不能输出的字符将停止。
*
* \param img 输出的影象
* \param text 文本内容
* \param pos 文本位置
* \param color 文本颜色
*
* \return 返回成功输出的字符长度，失败返回-1。
*/
int putText(cv::Mat &src, const char *text, cv::Point pos, cv::Scalar color);
//================================================================
//================================================================
private:
// 输出当前字符, 更新m_pos位置
void putWChar(cv::Mat &img, wchar_t wc, cv::Point &pos, cv::Scalar color);
size_t get_wchar_size(const char *str);
wchar_t *c2w(const char *pc);
private:
FT_Library m_library; // 字库
FT_Face m_face; // 字体
//===============================================================
// 默认的字体输出参数
int m_fontType;
cv::Scalar m_fontSize;
bool m_fontUnderline;
float m_fontDiaphaneity;
};
#endif // OPENCV_CVX_TEXT_2007_08_31_H#include <wchar.h>
#include <assert.h>
#include <locale.h>
#include <ctype.h>
#include "cvxText.h"
//====================================================================
cvxText::cvxText(const char *freeType)
{
assert(freeType != NULL);
// 打开字库文件, 创建一个字体
if(FT_Init_FreeType(&m_library)) throw;
if(FT_New_Face(m_library, freeType, 0, &m_face)) throw;
// 设置字体输出参数
restoreFont();
// 设置C语言的字符集环境
setlocale(LC_ALL, "");
}
// 释放FreeType资源
cvxText::~cvxText()
{
FT_Done_Face (m_face);
FT_Done_FreeType(m_library);
}
size_t cvxText::get_wchar_size(const char *str)
{
size_t len = strlen(str)+2;
size_t size=0;
int i;
for(i=0; i < (int)len; i++)
{
if( str[size] >= 0 && str[size] <= 127 ) //不是全角字符
size+=sizeof(wchar_t);
else //是全角字符，是中文
{
size+=sizeof(wchar_t);
i+=2;
}
}
return size;
}
wchar_t *cvxText::c2w(const char *pc)
{
if(!pc)
return NULL;
size_t size_of_ch = (strlen(pc)+2)*sizeof(char);
size_t size_of_wc = get_wchar_size(pc);
//std::cout<<size_of_ch<<" "<<size_of_wc<<std::endl;
wchar_t *pw;
if(!(pw = (wchar_t*)malloc(size_of_wc)))
{
printf("malloc fail");
return NULL;
}
mbstowcs(pw,pc,size_of_wc);
return pw;
}
//设置字体参数:
//
// font - 字体类型, 目前不支持
// size - 字体大小/空白比例/间隔比例/旋转角度
// underline - 下画线
// diaphaneity - 透明度
void cvxText::getFont(int *type, cv::Scalar *size, bool *underline, float *diaphaneity)
{
if(type) *type = m_fontType;
if(size) *size = m_fontSize;
if(underline) *underline = m_fontUnderline;
if(diaphaneity) *diaphaneity = m_fontDiaphaneity;
}
void cvxText::setFont(int *type, cv::Scalar *size, bool *underline, float *diaphaneity)
{
// 参数合法性检查
if(type)
{
if(type >= 0)
m_fontType = *type;
}
if(size)
{
m_fontSize.val[0] = fabs(size->val[0]);
m_fontSize.val[1] = fabs(size->val[1]);
m_fontSize.val[2] = fabs(size->val[2]);
m_fontSize.val[3] = fabs(size->val[3]);
}
if(underline)
{
m_fontUnderline = *underline;
}
if(diaphaneity)
{
m_fontDiaphaneity = *diaphaneity;
}
}
// 恢复原始的字体设置
void cvxText::restoreFont()
{
m_fontType = 0; // 字体类型(不支持)
m_fontSize.val[0] = 45;//60; // 字体大小//2017.10.19 upgrade
m_fontSize.val[1] = 0.5; // 空白字符大小比例
m_fontSize.val[2] = 0.1; // 间隔大小比例
m_fontSize.val[3] = 0; // 旋转角度(不支持)
m_fontUnderline = false; // 下画线(不支持)
m_fontDiaphaneity = 1.0; // 色彩比例(可产生透明效果)
// 设置字符大小
FT_Set_Pixel_Sizes(m_face, (int)m_fontSize.val[0], 0);
}
// 输出函数(颜色默认为)
int cvxText::putText(cv::Mat &img, const char *text, cv::Point pos)
{
return putText(img, text, pos, CV_RGB(255,0,0));
}
int cvxText::putText(cv::Mat &img, const char *text, cv::Point pos, cv::Scalar color)
{
if(!img.data) return -1;
if(text == NULL) return -1;
int i;
wchar_t *cw1 = c2w(text);
for(i = 0; i<(int)wcslen(cw1); i++)
{
putWChar(img, cw1[i], pos, color);
}
if(cw1!=NULL)
{
free(cw1);
}
return i;
}
// 输出当前字符, 更新m_pos位置
void cvxText::putWChar(cv::Mat &img,wchar_t wc, cv::Point &pos, cv::Scalar color)
{
// 根据unicode生成字体的二值位图
FT_UInt glyph_index = FT_Get_Char_Index(m_face, wc);
FT_Load_Glyph(m_face, glyph_index, FT_LOAD_DEFAULT);
FT_Render_Glyph(m_face->glyph, FT_RENDER_MODE_MONO);
FT_GlyphSlot slot = m_face->glyph;
//行列数
int rows = slot->bitmap.rows;
int cols = slot->bitmap.width;
for(int i = 0; i < rows; ++i)
{
for(int j = 0; j < cols; ++j)
{
int tmpvalue=i;
int off = tmpvalue* (slot->bitmap.pitch )+ j/8;
if(slot->bitmap.buffer[off] & (0xC0 >> (j%8)))
{
int r =pos.y -(rows-1-i);
int c = pos.x + j;
if(r >= 0 && r < img.rows && c >= 0 && c < img.cols)
{
cv::Vec3b pixel = img.at<cv::Vec3b>(cv::Point(c, r));
cv::Scalar scalar = cv::Scalar(pixel.val[0], pixel.val[1], pixel.val[2]);
// 进行色彩融合
float p = m_fontDiaphaneity;
for (int k = 0; k < 4; ++k) {
scalar.val[k] = scalar.val[k]*(1-p) + color.val[k]*p;
}
img.at<cv::Vec3b>(cv::Point(c, r))[0] = (unsigned char)(scalar.val[0]);
img.at<cv::Vec3b>(cv::Point(c, r))[1] = (unsigned char)(scalar.val[1]);
img.at<cv::Vec3b>(cv::Point(c, r))[2] = (unsigned char)(scalar.val[2]);
}
}
} // end for
} // end for
// 修改下一个字的输出位置
double space = m_fontSize.val[0]*m_fontSize.val[1];
double sep = m_fontSize.val[0]*m_fontSize.val[2];
pos.x += (int)((cols? cols: space) + sep);
}float m_diaphaneity=1.0f;
cvxText m_cvxText("simhei.ttf");
m_cvxText.setFont(NULL, NULL, NULL, &m_diaphaneity);
...
m_cvxText.putText(colorImage, algae[i].name.c_str(), cv::Point(c, r), MY_COLOR);
... 目前测试稳定，字体显示正常：
/*******************************************************************************************************/
2020.9.21
我同事想按照opencv官网示例使用cv::text::OCRTesseract模块，他是在windows下怎么搞都没使用起来，都不正确。然后我想着我前不久也编译了opencv4.4.0，试试看在ubuntu下使用这个模块。结果到示例的这一句时会报错：
Ptr<OCRTesseract> ocr = OCRTesseract::create();报错说 OCRTesseract (33): OCRTesseract not found.
OCRTesseract (33): OCRTesseract not found.原来是我之前编译的opencv4.4.0虽然也包含text模块，但opencv的text模块需要依赖额外的库，所以直接是无法使用的，要使用这个模块必须将这个模块额外的依赖库编译时编译进去。于是我只能重新编译一个带Tesseract的opencv4.4.0。在此吐槽网上很多教程都粘贴复制，看得很无语，没意义，千篇一律都是windows下的教程。都没有讲怎么在ubuntu+cmake+Tesseract+opencv的具体步骤，再次感叹国内外知识接轨的速度太慢了。我的具体步骤如下：
1、按下列命令安装下面的所有依赖项
2、然后去Leptonica官网下载某个版本，我下的是1.76，所以我并没有用下面的命令安装leptonica
3、去GitHub - tesseract-ocr/tesseract: Tesseract Open Source OCR Engine (main repository) 下载tesseract，可以看到一定有cmake文件夹以及CMakelist，之前我下的3.04版本的没有这些，把我坑死了。按下列命令安装Tesseract和Leptonica
安装完毕在终端确认如下：并且上面命令中的路径下已经有了这两个库的include和lib
4、然后我开始cmake编译了，发现第一次configure时，没有出现Tesseract相关的字眼，于是我急了，开始乱试：
首先，我去Tesseract和Leptonica两个原文件夹下分别执行下列命令：
mkdir build
cd build
cmake ../
make
sudo make install然后我再在Tesseract原文件夹下执行下列命令：
$ ./autogen.sh
$ ./configure
$ make
$ sudo make install
$ sudo ldconfig
$ make training
$ sudo make training-install然后我又把$HOME/usr/local下这两个库的所有.so文件拷贝一份到/usr/local/lib，又拷了一份到/usr/lib。并将这两个路径添加到ld.so.conf并ldconfig更新。
5、然后我重新开始cmake，发现第一次configure还是没有Tesseract，（又折腾N久）此时已疯，于是无奈又点击一次configure，终于出现了Tesseract字样：（原来是要点击2次才会出现，而且出现时路径都有，不会NOTFOUND！反正我此时第二次点击configure时出来的都有路径，我没修改）
此时高兴疯。cmake后面都无任何报错。可以看到这次编译opencv4.4.0没有报任何与opencv相关的错，这都得益于文章开头的第一次编译传统opencv4.4.0时做的那些工作。
6、然后开始进入buildwithTesseract文件夹进行opencv的make与make install
7、然后把刚刚编译好的opencv的so拷贝一份到/usr/lib，同时拷一份到/usr/local/lib，然后ldconfig更新一下
8、给你们看下我编译完的tesseract和leptonica文件夹
9、跟之前编译不带opencv4.4.0一样，将一些include和lib拷贝到opencv4.4.0_tesseract，这样以后这个文件夹就可以拷给别人用而不用别人也编译一遍了。
10、然后工程配置：
11、下载一些模型到tessdata内，记得将这个tessdata加入到环境变量，重启。不然待会儿测试没有模型。
12、工程测试代码：
#include <opencv2/text.hpp>
#define HAVE_TESSERACT
#ifdef HAVE_TESSERACT
#include <tesseract/baseapi.h>
#include <tesseract/resultiterator.h>
#endif
using namespace cv::text;
using OCRTesseract = cv::text::OCRTesseract;
int main()
{
cv::Mat mat = cv::imread("/...(my path)/1.png");
if ( mat.empty() )
return 0;
std::string output_text;
char *dataPath = "/...(my path)/tessdata";
cv::Ptr<OCRTesseract> ptrOcr = OCRTesseract::create(dataPath);
ptrOcr->run(mat, output_text );
cout << output_text << endl;
return 0;
}结果：红色警告部分忽略，反正不影响我使用，以后有空再优化。
测试图片是：下面这幅图
结果是：
可以看到输出了结果，不区分标点符号，效果还OK。红色警告部分暂不用管，
Error in pixReadMemTiff: function not present
Error in pixReadMem: tiff: no pix returned
Error in pixaGenerateFontFromString: pix not made
Error in bmfCreate: font pixa not made不影响使用。之所以有警告，是因为每次运行会进行一些检查，你没安装的库就会报出这些警告。可以看到我开始的图里只有png和zlib，而实际最好下面这些都安装，这样就不会报警告了。如果你和我一样只用了png图像，那你不安装下面这么多也行，有png就够了。
libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.2) : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.0
Found AVX2
Found AVX
Found FMA
Found SSE终端我也运行了一下，同样的结果：
至此，opencv中使用OCRTesseract模块初步测试完毕。
/*************************************************************************************************直接使用tensorflow进行字符识别****************************************************************************/
tensorflow训练模型完毕，python下预测是这样：
然后c++下：
/*
* charactersPredict.h
*
* Created on: 2020年10月29日
* Author: wd
*/
#ifndef SRC_CHARACTERSPREDICT_H_
#define SRC_CHARACTERSPREDICT_H_
//opencv------------------------------------//
#include <opencv2/opencv.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/objdetect.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <opencv2/ml.hpp>
#include <opencv2/ml/ml.hpp>
//tensorflow_cc----------------------------------------//
#include "tensorflow/core/framework/graph.pb.h"
#include <tensorflow/core/public/session_options.h>
#include <tensorflow/core/protobuf/meta_graph.pb.h>
#include <fstream>
#include <utility>
#include <vector>
#include <Eigen/Core>
#include <Eigen/Dense>
#include "tensorflow/cc/ops/const_op.h"
#include "tensorflow/cc/ops/image_ops.h"
#include "tensorflow/cc/ops/standard_ops.h"
#include "tensorflow/core/framework/graph.pb.h"
#include "tensorflow/core/framework/tensor.h"
#include "tensorflow/core/graph/default_device.h"
#include "tensorflow/core/graph/graph_def_builder.h"
#include "tensorflow/core/lib/core/errors.h"
#include "tensorflow/core/lib/core/stringpiece.h"
#include "tensorflow/core/lib/core/threadpool.h"
#include "tensorflow/core/lib/io/path.h"
#include "tensorflow/core/lib/strings/stringprintf.h"
#include "tensorflow/core/platform/env.h"
#include "tensorflow/core/platform/init_main.h"
#include "tensorflow/core/platform/logging.h"
#include "tensorflow/core/platform/types.h"
#include "tensorflow/core/public/session.h"
#include "tensorflow/core/util/command_line_flags.h"
//----------------------------------------------//
using namespace std;
using namespace cv;
#define MODELGRAPHWG_PATH "/media/root/Ubuntu43/tmpwg/model/ckp-80.meta"
#define MODELWG_PATH "/media/root/Ubuntu43/tmpwg/model/ckp-80"
const char charall[]= "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ-'.!?,\"&";
class charactersPredict {
public:
charactersPredict();
//主调用接口
int charactersPredictJpwg(Mat &inputgrayimg,string &outputchar);
virtual ~charactersPredict();
private:
tensorflow::Session* session;
int sizao_rows;
int sizao_cols;
int cnnInit();
void getchar(tensorflow::Tensor &resultpredict,string &result);
void imgrotate(Mat &src,Mat &dst);
int predict(Mat &src,string &charresult);
};
#endif /* SRC_CHARACTERSPREDICT_H_ *//*
* charactersPredict.cpp
*
* Created on: 2020年10月29日
* Author: wd
*/
#include "charactersPredict.h"
charactersPredict::charactersPredict() {
// TODO Auto-generated constructor stub
int initflag=cnnInit();
sizao_rows=100;
sizao_cols=32;
}
int charactersPredict::cnnInit()
{
///CNN initiation--Wang Dan 20191030
tensorflow::Status status = NewSession(tensorflow::SessionOptions(), &session);
if (!status.ok())
{
std::cout << "ERROR: NewSession() failed..." << std::endl;
return -1;
}
tensorflow::MetaGraphDef graphdef;
tensorflow::Status status_load = ReadBinaryProto(tensorflow::Env::Default(), MODELGRAPHWG_PATH, &graphdef); //从meta文件中读取图模型;
if (!status_load.ok()) {
std::cout << "ERROR: Loading model failed..." << std::endl;
std::cout << status_load.ToString() << "\n";
return -1;
}
tensorflow::Status status_create = session->Create(graphdef.graph_def()); //将模型导入会话Session中;
if (!status_create.ok()) {
std::cout << "ERROR: Creating graph in session failed..." << status_create.ToString() << std::endl;
return -1;
}
// 读入预先训练好的模型的权重
tensorflow::Tensor checkpointPathTensor(tensorflow::DT_STRING, tensorflow::TensorShape());
checkpointPathTensor.scalar<std::string>()() = MODELWG_PATH;
status = session->Run(
{{ graphdef.saver_def().filename_tensor_name(), checkpointPathTensor },},
{},{graphdef.saver_def().restore_op_name()},nullptr);
if (!status.ok())
{
throw runtime_error("Error loading checkpoint ...");
}
return 0;
}
void charactersPredict::getchar(tensorflow::Tensor &resultpredict,string &result)
{
int datanum=resultpredict.shape().dim_size(1);
auto thedata = resultpredict.tensor<long long int,2>();
for(int ind=0;ind!=datanum;ind++)
{
long long int dataind=thedata(0,ind);
char tmp=charall[dataind];
result +=tmp;
}
}
void charactersPredict::imgrotate(Mat &src,Mat &dst)
{
for(int r=0;r!=src.rows;r++)
{
for(int c=0;c!=src.cols;c++)
{
dst.ptr<uchar>(c)[r]=src.ptr<uchar>(r)[c];
}
}
}
int charactersPredict::charactersPredictJpwg(Mat &inputgrayimg,string &outputchar)
{
if(!(inputgrayimg.data))
{
std::cout << "ERROR: input img is empty..." << std::endl;
return -1;
}
if(inputgrayimg.channels()!=1)
{
std::cout << "ERROR: input img is invalid (not gray image)..." << std::endl;
return -2;
}
outputchar="";
int flag=predict(inputgrayimg,outputchar);
if(flag!=0)
{
std::cout << "ERROR: predict() is wrong..." << std::endl;
return -3;
}
return 0;
}
int charactersPredict::predict(Mat &src,string &charresult)
{
//CNN start...20190710 wd
tensorflow::Tensor resized_tensor(tensorflow::DT_FLOAT, tensorflow::TensorShape({1,sizao_rows,sizao_cols,1}));
float *imgdata = resized_tensor.flat<float>().data();
cv::Mat cnninputImg(sizao_rows, sizao_cols, CV_32FC1, imgdata);
cv::Mat srccnn(sizao_rows, sizao_cols, CV_8UC1);
imgrotate(src,srccnn);
srccnn.convertTo(cnninputImg, CV_32FC1);
//对图像做预处理
cnninputImg=cnninputImg/255;
//CNN input
vector<std::pair<string, tensorflow::Tensor> > inputs;
std::string Input1Name = "input";
inputs.push_back(std::make_pair(Input1Name, resized_tensor));
std::string Input2Name="seq_len";
tensorflow::Tensor seq(tensorflow::DT_INT32, tensorflow::TensorShape({1}));
seq.vec<int>()(0)=24;
inputs.push_back(std::make_pair(Input2Name, seq));
//CNN predict
vector<tensorflow::Tensor> decode;
string output="dense_decoded";
tensorflow::Status status_run = session->Run(inputs, {output}, {}, &decode);
if (!status_run.ok()) {
std::cout << "ERROR: RUN failed in session->Run()..." << std::endl;
std::cout << status_run.ToString() << "\n";
return -1;
}
tensorflow::Tensor resultpredict=decode[0];
getchar(resultpredict,charresult);
return 0;
}
charactersPredict::~charactersPredict() {
// TODO Auto-generated destructor stub
tensorflow::Status freestatus=session->Close();//二维数组输出
if (!freestatus.ok())
{
std::cout << "ERROR: release session failed..." << std::endl;
}
}#include "charactersPredict.h"
int main()
{
charactersPredict characterpredictobj;
double alltime=0.0;
char srcfile[100];
for(int group_index=0;group_index<=1345;group_index++)
{
//printf("image=%d ...",group_index);
sprintf(srcfile, "/media/root/Ubuntu43/tmpwg/3/%d.jpg",group_index);
Mat srcimg=imread(srcfile,0);
if(!srcimg.data)
{
continue;
}
cv::TickMeter timer;
timer.start();
string imgresult="";
characterpredictobj.charactersPredictJpwg(srcimg,imgresult);
timer.stop();
cout<<"image is "<<group_index<<" result: "<<imgresult.c_str()<<" time is: "<<timer.getTimeMilli()<<" ms!"<<endl;
alltime+=(timer.getTimeMilli());
timer.reset();
//cout<<"result: "<<imgresult.c_str()<<endl;
}
double average=alltime/1346;
cout<<"time average: "<<average<<" ms."<<endl;
printf("测试完成！\n");
return 0;
}结果：
另外从大图切割出小图网上有代码：
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/dnn.hpp>
#include <vector>
#include <string>
#include<iostream>
using namespace std;
using namespace cv;
using namespace cv::dnn;
//https://github.com/hpc203/ocr-opencv-dnn/blob/master/text_detect_recognition.cpp
struct sStatisticsChar
{
Rect box;
string chars;
bool flag;
};
const char* keys =
"{ help h | | Print help message. }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera.}"
"{ model m | | Path to a binary .pb file contains trained detector network.}"
"{ ocr | | Path to a binary .pb or .onnx file contains trained recognition network.}"
"{ width | 320 | Preprocess input image by resizing to a specific width. It should be multiple by 32. }"
"{ height | 320 | Preprocess input image by resizing to a specific height. It should be multiple by 32. }"
"{ thr | 0.5 | Confidence threshold. }"
"{ nms | 0.4 | Non-maximum suppression threshold. }";
void decodeBoundingBoxes(const Mat& scores, const Mat& geometry, float scoreThresh,
std::vector<RotatedRect>& detections, std::vector<float>& confidences);
void fourPointsTransform(const Mat& frame, Point2f vertices[4], Mat& result);
void decodeText(const Mat& scores, std::string& text);
double calcLineDegree(const Point2f& firstPt, const Point2f& secondPt);
double getRcDegree(const RotatedRect box);
inline string num2str(int i)
{
stringstream ss;
ss << i;
return ss.str();
}
int main(int argc, char** argv)
{
string vPath = "/media/root/Ubuntu43/tmpwg/wholeimgs/";
float confThreshold = 0.05;
float nmsThreshold = 0.05;
int inpWidth = 480;
int inpHeight = 320;
String modelDecoder = "/media/root/Ubuntu43/tmpwg/vs_segment_model/netmodel/frozen_east_text_detection.pb";
String modelRecognition = "/media/root/Ubuntu43/tmpwg/vs_segment_model/netmodel/CRNN_VGG_BiLSTM_CTC.onnx";
CV_Assert(!modelDecoder.empty());
// Load networks.
Net detector = readNet(modelDecoder);
Net recognizer;
if (!modelRecognition.empty())
recognizer = readNet(modelRecognition);
std::vector<Mat> outs;
std::vector<String> outNames(2);
outNames[0] = "feature_fusion/Conv_7/Sigmoid";
outNames[1] = "feature_fusion/concat_3";
string name;
int ii = 0;
for (int i = 226; i < 227; i++)
{
name = vPath + num2str(i) + ".jpg";
Mat frame0, blob;
frame0 = imread(name);
if (frame0.empty())
{
continue;
}
Mat frame = Mat::zeros(frame0.size(), CV_8UC3);
Rect rect = Rect(0, 108, 1920, 640);
frame0(rect).copyTo(frame(rect));
blobFromImage(frame, blob, 1.0, Size(inpWidth, inpHeight), Scalar(123.68, 116.78, 103.94), true, false);
detector.setInput(blob);
detector.forward(outs, outNames);
Mat scores = outs[0];
Mat geometry = outs[1];
// Decode predicted bounding boxes.
std::vector<RotatedRect> boxes;
std::vector<float> confidences;
decodeBoundingBoxes(scores, geometry, confThreshold, boxes, confidences);
// Apply non-maximum suppression procedure.
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
Point2f ratio((float)frame.cols / inpWidth, (float)frame.rows / inpHeight);
vector<sStatisticsChar> StatisticsChar;
for (size_t i = 0; i < indices.size(); ++i)
{
RotatedRect& box = boxes[indices[i]];
float rate = (float)box.size.width / box.size.height;
RotatedRect box1 = box;
box1.size.width = box.size.width*1.1;
Point2f vertices[4];
box1.points(vertices);
for (int j = 0; j < 4; ++j)
{
vertices[j].x *= ratio.x;
vertices[j].y *= ratio.y;
}
Mat cropped;
fourPointsTransform(frame, vertices, cropped);
string pathchar = "/media/root/Ubuntu43/tmpwg/segmentresults/" + num2str(ii) + ".jpg";
ii++;
cvtColor(cropped, cropped, cv::COLOR_BGR2GRAY);
imwrite(pathchar,cropped);//存小图图片
//后面的我没使用，而是直接用存的小图去用tensorflow c++预测
/*
Mat blobCrop = blobFromImage(cropped, 1.0 / 127.5, Size(), Scalar::all(127.5));
recognizer.setInput(blobCrop);
Mat result = recognizer.forward();
sStatisticsChar sc;
std::string wordRecognized = "";
decodeText(result, wordRecognized);
sc.box = box.boundingRect();
sc.chars = wordRecognized;
sc.flag = false;
StatisticsChar.push_back(sc);
*/
}
}
return 0;
}整体结果如下：
可以看到右边这张大图切割出6个小图然后6个小图的识别结果已打印出来！
/******************************************************************************************************/
开心：在烤火的小布丁。
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
