使用opnalpr训练目标检测级联分类器

1.环境

windows7 , opencv3.0 , python-2.6 , PIL-1.1.6.win32-py2.6.exe

2.安装python2.6和PIL

3.下载openalpr的train-detector-master

3.修改prep.py文件，可以直接复制以下代码，修改OPENCV_DIR和BASE_DIR为你自己的目录即可

#!/usr/bin/python

import os
import Image
import uuid
import shutil

import sys

#修改成你需要检测目标的宽度和高度
WIDTH=136
HEIGHT=36
#这个目录里面需要放你的正样本
COUNTRY='china'

#WIDTH=52
#HEIGHT=13
#COUNTRY='eu'

#constants，需要填写你的opencv安装目录，注意这里制定x64位，使用32位可能在训练的时候回出现分配内存不足的情况
OPENCV_DIR= 'D:\\software\\opencv\\opencv_300\\opencv\\build\\x64\\vc11\\bin'
SAMPLE_CREATOR = OPENCV_DIR + '\\opencv_createsamples'

#指定prep.py文件所在的目录即可
BASE_DIR            = 'E:\\PlateRec\\train-detector-master\\train-detector-master\\'

#训练的模型输出目录
OUTPUT_DIR          = BASE_DIR + "out\\"
#负样本放置目录
INPUT_NEGATIVE_DIR  = BASE_DIR + 'raw-neg\\'
#正样本放置目录
INPUT_POSITIVE_DIR  = BASE_DIR + COUNTRY + '\\'
#初始状态目录为空，在运行prep.py neg后，这个目录会有内容
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 + 1

command=""

if command != "":
pass
elif 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(OUTPUT_NEGATIVE_DIR + 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')

total_pics = total_pics + 1
except IOError:
print ("Exception reading image file: " + filename)

f.close()

# Collapse the samples into a vector file
execStr = '%s\\opencv_createsamples %s %s %s -num %d' % (OPENCV_DIR, 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 100

elif command == "showpos":
print ("SHOW")
execStr = '%s\\opencv_createsamples -vec %s -w %d -h %d' % (OPENCV_DIR, VEC_FILE, WIDTH, HEIGHT )
print (execStr)
os.system(execStr)
#opencv_createsamples -vec ../positive/vecfile.vec -w 120 -h 60
elif command == "train":
print ("TRAIN")

data_arg = '-data %s\\' % (OUTPUT_DIR)
bg_arg = '-bg %s' % (NEGATIVE_INFO_FILE)

try:
num_pos_samples = file_len(POSITIVE_INFO_FILE)
except:
num_pos_samples = -1
num_neg_samples = file_len(NEGATIVE_INFO_FILE)

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 )

print ("Execute the following command to start training:")
print (execStr)
#D:\software\opencv\opencv_300\opencv\build\x64\vc11\bin\opencv_traincascade -data E:\PlateRec\train-detector-master\train-detector-master\out\ -vec E:\PlateRec\train-detector-master\train-detector-master\positive\vecfile.vec -bg E:\PlateRec\train-detector-master\train-detector-master\negative\negative.txt -w 136 -h 36 -numPos 1600 -numNeg 6000 -minHitRate 0.99 -maxFalseAlarmRate 0.45 -featureType LBP -numStages 20
#opencv_traincascade -data ./out/ -vec ./positive/vecfile.vec -bg ./negative/negative.txt -w 120 -h 60 -numPos 99 -numNeg 5  -featureType LBP -numStages 20
elif command == "SDFLSDFSDFSDF":

root_dir = '/home/mhill/projects/anpr/AlprPlus/samples/svm/raw-pos'
outputfilename = "positive.txt"

else:
print_usage()
exit()

4.将正样本放在INPUT_POSITIVE_DIR中，负样本放在raw-neg目录中

5.执行以下命令

prep.py neg

prep.py pos

D:\software\opencv\opencv_300\opencv\build\x64\vc11\bin\opencv_traincascade -data E:\PlateRec\train-detector-master\train-detector-master\out\ -vec E:\PlateRec\train-detector-master\train-detector-master\positive\vecfile.vec -bg E:\PlateRec\train-detector-master\train-detector-master\negative\negative.txt -w 45 -h 15 -numPos 1500 -numNeg 4500 -minHitRate 0.99 -maxFalseAlarmRate 0.45 -featureType LBP -numStages 16 -precalcValBufSize 5 -precalcIdxBufSize 100

注意第三个命令很关键，第一个路径是你安装的opencv包含opencv_traincascade.exe文件的目录

-minHitRate 表示每个分类器最多有1600*(1-0.99)个正样本被分类成负样本，下级取正样本的时候需要多取这么多正样本

-maxFalseAlarmRate 表示最大虚警率，每级，最多将6000*0.45个样本分类成正样本

-data 后面是模型输出目录

-vec 后面是执行prep.py pos后生成的vecfile.vec文件目录，其实就在positive目录中

-bg 后面是执行prep.py neg生成negative.txt文件目录，其实就是在negative目录中

-numPos 表示每个弱分类器使用的正样本数，而不是你拥有的正样本的总数

计算公式：正样本总数 >= (numPos + (numStages-1) * (1 - minHitRate) * numPos)

-numNeg 同样表示的是每个弱分类器使用的负样本数，但是这个值可以直接使用你负样本的总个数

-precalcValBufSize 表示每个样本提取的特征使用多大单位为MB,如果不设置默认为1024MB也就是1G，这很大，可能会导致训练到某一stage的时候分配空间失败，所以建议使用小一点的值我这里使用的LBP特征

-precalcIdxBufSize 表示什么索引的buf大小，据说这个值越大训练的越快，但是我为了保险起见别训练个十几个小时又分配内存不足，所以使用的是100MB，默认也是1024MB

ps:我使用1925个正样本，4706个负样本，发现使用上面这个命令参数训练没有问题，而且训练出来的检测效果不错，可能正样本更多一些，比如倾斜着的车牌，负样本更丰富一些比如栅栏，栏杆等容易被识别成车牌的加入到负样本中，效果会更好一些。注意那个w和h不一定就是你的正样本的宽度和高度，可以是等比例缩小的，实际上我试过就是样本136*36这么大的，识别不到目标。

6.开始训练之后如下图所示