车牌识别之Cascade人脸识别训练

主题 概要 人脸识别 人脸识别训练的一个脚本 编辑 时间 新建 20170102 增加截图 20170110 序号 参考资料 1 https://github.com/openalpr/openalpr 2 http://docs.opencv.org/2.4/doc/user_guide/ug_traincascade.html 3 https://github.com/openalpr/train-detector

脚本

前面做车牌识别总结的时候，提到了用人脸识别的方法进行定位。根据参考资料3，checkout出来，里面会有一些自带的正样本和负样本。还有一个python执行脚本，但是是在linux环境上执行的。我家里没有linux的环境，以前没有接触过python，但连蒙带猜，还是顺利把它改造成windows下能跑了。
其实主要的改动就是目录路径，然后每次执行cascade命令的时候都要os.chdir(OPENCV_DIR) 到openCV的执行目录。
目录结构是在参考资料3的基础上加一个cn文件夹，存放我们的中文车牌正样本。

主要要修改的配置有：
图片归一化的宽度和高度，大小是像素：

OpenCV的可执行目录：

训练时的工作基本目录：

下面是修改后的整个python脚本：

#!/usr/bin/pythonimport osfrom PIL import Imageimport uuidimport shutilimport sysWIDTH=49HEIGHT=13COUNTRY='cn'OPENCV_DIR= 'D:/Program Files (x86)/OpenCV2.4.9/opencv/build/x86/vc12/bin'SAMPLE_CREATOR = OPENCV_DIRBASE_DIR            = 'F:/Project/ComShao/LI-Openalpr-train-detector/Train-detector/'OUTPUT_DIR          = BASE_DIR + "out/"INPUT_NEGATIVE_DIR  = BASE_DIR + 'raw-neg/'INPUT_POSITIVE_DIR  = BASE_DIR + COUNTRY + '/'OUTPUT_NEGATIVE_DIR  = BASE_DIR + 'negative/'OUTPUT_POSITIVE_DIR  = BASE_DIR + 'positive/'POSITIVE_INFO_FILE  = OUTPUT_POSITIVE_DIR + 'positive.txt'NEGATIVE_INFO_FILE  = OUTPUT_NEGATIVE_DIR + 'negative.txt'VEC_FILE            = OUTPUT_POSITIVE_DIR + 'vecfile.vec'vector_arg = '-vec %s' % (VEC_FILE)width_height_arg = '-w %d -h %d' % (WIDTH, HEIGHT)def print_usage():    print "Usage: prep.py [Operation]"    print "   -- Operations --"    print "  neg        -- Prepares the negative samples list"    print "  pos        -- Copies all the raw positive files to a opencv vector"    print "  showpos    -- Shows the positive samples that were created"    print "  train      -- Outputs the command for the Cascade Training algorithm"def file_len(fname):    with open(fname) as f:        for i, l in enumerate(f):            pass    return i + 1command=""if command != "":    passelif len(sys.argv) != 2:    print_usage()    exit()else:    command = sys.argv[1]if command == "neg":    print "Neg"    # Get rid of any spaces    for neg_file in os.listdir(INPUT_NEGATIVE_DIR):        if " " in neg_file:            fileName, fileExtension = os.path.splitext(neg_file)            newfilename =  str(uuid.uuid4()) + fileExtension            #print "renaming: " + files + " to "+ root_dir + "/" + str(uuid.uuid4()) + fileExtension            os.rename(INPUT_NEGATIVE_DIR + neg_file, INPUT_POSITIVE_DIR + newfilename)    f = open(NEGATIVE_INFO_FILE,'w')    ## Write a list of all the negative files    for neg_file in os.listdir(INPUT_NEGATIVE_DIR):        if os.path.isdir(INPUT_NEGATIVE_DIR + neg_file):            continue        shutil.copy2(INPUT_NEGATIVE_DIR + neg_file, OUTPUT_NEGATIVE_DIR + neg_file )        #f.write(neg_file + "\r\n")        f.write(neg_file + "\n")    f.close()elif command == "pos":    print "Pos"    info_arg = '-info %s' % (POSITIVE_INFO_FILE)    # Copy all files in the raw directory and build an info file    ## Remove all files in the output positive directory    for old_file in os.listdir(OUTPUT_POSITIVE_DIR):        os.unlink(OUTPUT_POSITIVE_DIR + old_file)    ## First, prep the sample filenames (make sure they have no spaces)    for files in os.listdir(INPUT_POSITIVE_DIR):        if os.path.isdir(INPUT_POSITIVE_DIR + files):            continue        # Rename the file if it has a space in it        newfilename = files        if " " in files:            fileName, fileExtension = os.path.splitext(files)            newfilename =  str(uuid.uuid4()) + fileExtension            #print "renaming: " + files + " to "+ root_dir + "/" + str(uuid.uuid4()) + fileExtension            os.rename(INPUT_POSITIVE_DIR + files, INPUT_POSITIVE_DIR + newfilename)        # Copy from the raw directory to the positive directory        shutil.copy2(INPUT_POSITIVE_DIR + newfilename, OUTPUT_POSITIVE_DIR + newfilename )    total_pics = 0    ## Create the positive.txt input file    f = open(POSITIVE_INFO_FILE,'w')    for filename in os.listdir(OUTPUT_POSITIVE_DIR):        if os.path.isdir(OUTPUT_POSITIVE_DIR + filename):            continue        if filename.endswith(".txt"):            continue    try:        img = Image.open(OUTPUT_POSITIVE_DIR + filename)        # get the image's width and height in pixels        width, height = img.size        f.write(filename + " 1 0 0 " + str(width) + " " + str(height) + '\n')        #f.write(filename + " 1 0 0 " + str(width) + " " + str(height) + '/n')        total_pics = total_pics + 1    except IOError:        print "Exception reading image file: " + filename    f.close()    # Collapse the samples into a vector file    os.chdir(OPENCV_DIR)    #execStr = '%s/opencv_createsamples %s %s %s -num %d' % (OPENCV_DIR, vector_arg, width_height_arg, info_arg, total_pics )    execStr = 'opencv_createsamples %s %s %s -num %d' % (vector_arg, width_height_arg, info_arg, total_pics )    print execStr    os.system(execStr)    #opencv_createsamples -info ./positive.txt -vec ../positive/vecfile.vec -w 120 -h 60 -bg ../negative/PentagonCityParkingGarage21.jpg -num 100elif command == "showpos":    print "SHOW"    os.chdir(OPENCV_DIR)    #execStr = '%s/opencv_createsamples -vec %s -w %d -h %d' % (OPENCV_DIR, VEC_FILE, WIDTH, HEIGHT )    execStr = 'opencv_createsamples -vec %s -w %d -h %d' % (VEC_FILE, WIDTH, HEIGHT )    print execStr    os.system(execStr)    #opencv_createsamples -vec ../positive/vecfile.vec -w 120 -h 60elif command == "train":    print "TRAIN"    #data_arg = '-data %s/' % (OUTPUT_DIR)    data_arg = '-data %s' % (OUTPUT_DIR)    bg_arg = '-bg %s' % (NEGATIVE_INFO_FILE)    #bg_arg = '-bg %s' %  "negative.txt"    try:    num_pos_samples = file_len(POSITIVE_INFO_FILE)    except:    num_pos_samples = -1    num_pos_samples*=0.8    num_neg_samples = file_len(NEGATIVE_INFO_FILE)    num_neg_samples*=0.8    os.chdir(OPENCV_DIR)    #execStr = '%s/opencv_traincascade %s %s %s %s -numPos %d -numNeg %d -maxFalseAlarmRate 0.45 -featureType LBP -numStages 13' % (OPENCV_DIR, data_arg, vector_arg, bg_arg, width_height_arg, num_pos_samples, num_neg_samples )    execStr = 'opencv_traincascade %s %s %s %s -precalcIdxBufSize %d -numPos %d -numNeg %d  -maxFalseAlarmRate 0.45 -featureType LBP -numStages 13' % (data_arg, vector_arg, bg_arg, width_height_arg,6000,num_pos_samples, num_neg_samples )    #execStr = 'opencv_traincascade %s %s %s %s -numPos %d -numNeg %d -maxFalseAlarmRate 0.45 -featureType LBP -numStages 13' % (data_arg, vector_arg, bg_arg, width_height_arg,num_pos_samples, num_neg_samples )    print "Execute the following command to start training:"    print execStr    os.system(execStr)    #opencv_traincascade -data ./out/ -vec ./positive/vecfile.vec -bg ./negative/negative.txt -w 120 -h 60 -numPos 99 -numNeg 5  -featureType LBP -numStages 8    #opencv_traincascade -data ./out/ -vec ./positive/vecfile.vec -bg ./negative/negative.txt -w 120 -h 60 -numPos 99 -numNeg 5  -featureType LBP -numStages 20elif command == "SDFLSDFSDFSDF":    root_dir = '/home/mhill/projects/anpr/AlprPlus/samples/svm/raw-pos'    outputfilename = "positive.txt"else:    print_usage()    exit()

脚本的内容本身很简单，不外乎创建正样本、创建负样本、调用opencv_createsamples、opencv_traincascade两个命令等。
整个人脸识别的原理、通过怎么样提取特征、用的什么算法，这些东西其实才是精华，但毕竟时间有限，也不是专门研究这个的，现在只能做到根据参考资料2，对各个参数有个几分的理解。比如，这里面的参数 -precalcIdxBufSize 是我自己根据openvCV的说明文档添加进去的，大大提高了训练速度。
可能训练最难办的到不是这个脚本的理解，而是这正样本是怎么来的？我这里有12000多张定位好的车牌，其实是应用easyPR里面的方法，自己写了个批量定位的函数，由sobel定位、颜色定位和文字定位而来的。

使用

安装好python2.几，注意不要用3以上版本，会导致print 语法不支持。
切换到工作目录后，依次执行：
prep.py neg
prep.py pos
prep.py train

如果提示下面的语句报错：

可以进入python shell中，执行：pip install image
或者：python -m pip install Pillow