def load_diabetes():
"""
Load the diabetes dataset
@return: diabetes dataset by (data, target)
"""
# 文件路径
file_path_data = './cache/sk/sk_diabete_data.csv'
file_path_target = './cache/sk/sk_diabete_target.csv'
# 如果存在数据文件，则直接读取
if os.path.exists(file_path_data):
# 读取文件
df_data = pd.read_csv(file_path_data)
df_target = pd.read_csv(file_path_target)
return df_data.as_matrix(), df_target.as_matrix()
else:
filecm.makedir(file_path_data, by_file=True)
# 取得数据
diabetes = datasets.load_diabetes()
logcm.print_obj(diabetes.DESCR, 'diabetes.DESCR')
logcm.print_obj(diabetes.data, '样本原始数据集')
logcm.print_obj(diabetes.target, '样本目标数据集')
# 保存到文件
DataFrame(diabetes.data).to_csv(file_path_data, index=False)
DataFrame(diabetes.target).to_csv(file_path_target, index=False)
return diabetes.data, diabetes.target
def save_xml(xml_str, save_path, encoding="utf-8"):
"""
格式化root转换为xml文件
@param xml_str: 根节点
@param save_path: xml文件
@param encoding: 文本编码
@return: 无
"""
try:
logcm.print_info("Saving xml file --> %s" % save_path)
# 解析XML文档
xml_doc = minidom.parseString(xml_str.encode(encoding))
# 确保目录存在
filecm.makedir(save_path, by_file=True)
# 写入XML文件
with open(save_path, "w+") as file:
xml_doc.writexml(file,
addindent="\t",
newl="\n",
encoding=encoding)
except Exception as e:
logcm.print_info("Saving xml error! %s" % e, fg='red')
def get_hand_digits_knn():
"""
取得训练好的手写数字识别的KNN对象，如果有缓存文件，优先读取缓存。
@return: KNN对象
"""
# 缓存路径及文件设定
path = './cache/cv'
file_train = 'digits_knn_train.npy'
file_label = 'digits_knn_label.npy'
filecm.makedir(path)
if filecm.exists(path, file_train):
# 从缓存文件中加载训练样本和结果
logcm.print_info("load hand digits train data from cache file.")
train = np.load(os.path.join(path, file_train))
label = np.load(os.path.join(path, file_label))
else:
# 从图片中获取训练样本和结果
logcm.print_info("load hand digits train data from Image.")
img = cv2.imread('./images/cv_digits.png')
# 灰度转换
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 把图片切割为50*100个Cell
cells = [np.hsplit(row, 100) for row in np.vsplit(gray, 50)]
train = []
# 删除图片边界空白
for i in range(50):
for j in range(100):
cell_img = cells[i][j]
cell_img2 = opencvcm.resize_by_max_contours(
cell_img, 20, 20, 1, 1)
# if j == 0:
# cv2.imwrite('%s/digits_cell_%d_%d.jpg' % (path, i, j), cell_img2)
# 计算训练数据，对每个Cell，进行reshape处理，
# 把图片展开成400列，行数不确定
train.append(cell_img2.reshape((1, 400)))
# 训练数据整理为np.array格式
train = np.array(train).reshape(-1, 400).astype(np.float32)
# 每个数字500遍
label = np.repeat(np.arange(10), 500)
# 保存缓存文件
np.save(os.path.join(path, file_train), train)
np.save(os.path.join(path, file_label), label)
# KNN算法
knn = cv2.ml.KNearest_create()
# 训练数据
knn.train(train, cv2.ml.ROW_SAMPLE, label)
return knn
from numpy.linalg import norm
from common import cvsvmcm
from common import filecm
from common import logcm
from common import plotcm
# SVM模型
svm = cvsvmcm.get_car_plate_svm()
# 获取plates文件夹下所有文件路径
img_path = gb.glob("./images/plates/*")
# 定义并创建临时目录
tmp_path = './temp/cv/plate'
filecm.makedir(tmp_path)
# 图片矩阵
img_matrix = []
# 标题矩阵
title_matrix = []
# 对每一张图片进行处理
for path in img_path:
img_list = []
title_list = []
img = cv2.imread(path)
img_list.append(img)
filename = filecm.short_name(path)
title_list.append('原图-%s' % filename)
def get_print_number_knn():
"""
取得训练好的打印数字识别的KNN对象，如果有缓存文件，优先读取缓存。
@return: KNN对象
"""
# 缓存路径及文件设定
path = './cache/cv'
file_train = 'number_knn_train.npy'
file_label = 'number_knn_label.npy'
filecm.makedir(path)
if filecm.exists(path, file_train):
# 从缓存文件中加载训练样本和结果
train = np.load(os.path.join(path, file_train))
label = np.load(os.path.join(path, file_label))
else:
# 从图片中获取训练样本和结果
# 获取numbers文件夹下所有文件路径
img_path = gb.glob("./images/numbers/*")
# 定义并创建临时目录
tmp_path = './temp/cv/number'
filecm.makedir(tmp_path)
label = []
train = []
func_key = "get_print_number_knn"
## 对每一张图片进行处理
for file_path in img_path:
# 文件短名称
name = filecm.short_name(file_path)
# 读取图片
img = cv2.imread(file_path)
# 颜色空间转换（转换成灰度图）
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
save_tmp(gray, func_key, "gray", tmp_path, name)
# 高斯模糊
blur = cv2.GaussianBlur(gray, (5, 5), 0)
save_tmp(blur, func_key, "GaussianBlur", tmp_path, name)
# 自适应阈值可以看成一种局部性的阈值，通过规定一个区域大小，
thresh = cv2.adaptiveThreshold(blur, 255, 1, 1, 11, 2)
save_tmp(thresh, func_key, "adaptiveThreshold", tmp_path, name)
# 查找检测物体的轮廓。
image, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
height, width = img.shape[:2]
## 图片第一行和第二行数字
list1 = []
list2 = []
for cnt in contours:
# 直边界矩形
[x, y, w, h] = cv2.boundingRect(cnt)
# 根据轮廓矩形的宽度和高度筛识别出数字所在区域
if w > 30 and h > (height / 4):
## 按y坐标分行
if y < (height / 2):
list1.append([x, y, w, h]) ## 第一行
else:
list2.append([x, y, w, h]) ## 第二行
## 按x坐标排序，上面已经按y坐标分行
list1_sorted = sorted(list1, key=lambda t: t[0])
list2_sorted = sorted(list2, key=lambda t: t[0])
for i in range(5):
[x1, y1, w1, h1] = list1_sorted[i]
[x2, y2, w2, h2] = list2_sorted[i]
## 切割出每一个数字
number_roi1 = gray[y1:y1 + h1, x1:x1 + w1] # Cut the img_test to size
number_roi2 = gray[y2:y2 + h2, x2:x2 + w2] # Cut the img_test to size
## 对图片进行大小统一和预处理
resized_roi1 = cv2.resize(number_roi1, (20, 40))
thresh1 = cv2.adaptiveThreshold(resized_roi1, 255, 1, 1, 11, 2)
resized_roi2 = cv2.resize(number_roi2, (20, 40))
thresh2 = cv2.adaptiveThreshold(resized_roi2, 255, 1, 1, 11, 2)
j = i + 6
if j == 10:
j = 0
# 保存数字图片
save_tmp(thresh1, func_key, "adaptiveThreshold", tmp_path, name + "-" + str(i + 1))
save_tmp(thresh2, func_key, "adaptiveThreshold", tmp_path, name + "-" + str(j))
## 归一化
normalized_roi1 = thresh1 / 255.
normalized_roi2 = thresh2 / 255.
## 把图片展开成一行，然后保存到samples
## 保存一个图片信息，保存一个对应的标签
train.append(normalized_roi1.reshape((1, 800)))
label.append(float(i + 1))
train.append(normalized_roi2.reshape((1, 800)))
label.append(j)
# 训练数据整理为np.array格式
train = np.array(train).reshape(-1, 800).astype(np.float32)
label = np.array(label).astype(np.float32)
# 保存缓存文件
np.save(os.path.join(path, file_train), train)
np.save(os.path.join(path, file_label), label)
# KNN算法
knn = cv2.ml.KNearest_create()
# 训练数据
knn.train(train, cv2.ml.ROW_SAMPLE, label)
return knn
{
"img_root": "./images/img",
"img_ext": ".jpeg",
"max_count" : 10,
"fps": 10,
"save_path": "./temp/output.avi",
"width": 1024,
"height": 683
}
"""
# 加载配置文件
cfg = loadcfgcm.load("cv_video_from_img.json", default_config)
# 创建目录
filecm.makedir(cfg['save_path'], True)
filecm.makedir('./temp/cv/video-from-img')
# 新建视频写入类
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
videoWriter = cv2.VideoWriter(cfg['save_path'], fourcc, cfg['fps'],
(cfg['width'], cfg['height']))
im_output = VideoImageOutput(videoWriter)
# 取得图片列表
path_list = filecm.search_files(cfg["img_root"], cfg['img_ext'], r'^[^\.]+')
# 取得处理数量
max_size = cfg['max_count']
if max_size > len(path_list):
max_size = len(path_list)
from common import imagecm
# 配置
default_config = """
{
"video_path": "/temp/output.avi",
"img_root": "/path/to/img",
"max_count" : 10,
"fps": 5
}
"""
# 加载配置文件
cfg = loadcfgcm.load("cv_video_to_img.json", default_config)
filecm.makedir(cfg['img_root'])
vc = cv2.VideoCapture(cfg['video_path'])
frame_no = 0
count = 0
if vc.isOpened():
rval, frame = vc.read()
else:
rval = False
while rval:
rval, frame = vc.read()
frame_no = frame_no + 1
if frame_no % cfg['fps'] == 0:
count += 1
cv2.imwrite(cfg["img_root"] + str(count) + '.jpg', frame)
#!/usr/bin/env python # -*- coding: utf-8 -*- """ 一个HDF5文件是一种存放两类对象的容器：dataset和group. Dataset是类似于数组的数据集，而group是类似文件夹一样的容器，存放dataset和其他group。 在使用h5py的时候需要牢记一句话：groups类比词典，dataset类比Numpy中的数组。 """ import h5py import numpy as np from common import filecm # 输出文件 tmp_path = "./temp/file/mytestfile.hdf5" filecm.makedir(tmp_path, by_file=True) # HDF5的写入： imgData = np.zeros((30, 3, 128, 256)) # 创建一个h5文件，文件指针是f f = h5py.File(tmp_path, 'w') # 将数据写入文件的主键data下面 f['data'] = imgData # 将数据写入文件的主键labels下面 f['labels'] = range(100) # 关闭文件 f.close() # HDF5的读取： # 打开h5文件 f = h5py.File(tmp_path, 'r') # 可以查看所有的主键
import numpy as np
import os
from numpy.linalg import norm
from common import filecm
from common import logcm
from common import opencvcm
SZ = 20 # 训练图片长宽
MAX_WIDTH = 1000 # 原始图片最大宽度
Min_Area = 2000 # 车牌区域允许最大面积
PROVINCE_START = 1000
CACHE_PATH = './cache/cv'
DATA_PATH = './data/plate'
filecm.makedir(CACHE_PATH)
filecm.makedir(DATA_PATH)
# 读取图片文件
def imreadex(filename):
return cv2.imdecode(np.fromfile(filename, dtype=np.uint8),
cv2.IMREAD_COLOR)
def point_limit(point):
if point[0] < 0:
point[0] = 0
if point[1] < 0:
point[1] = 0
