Repository: HuangCongQing/OpenCV
Branch: master
Commit: 5713577de082
Files: 21
Total size: 2.1 MB
Directory structure:
gitextract_u125kwrs/
├── .gitignore
├── 00.py
├── 01read_show.py
├── 01项目实战-信用卡数字识别/
│ └── template-matching-ocr/
│ ├── myutils.py
│ └── ocr_template_match.py
├── 02save.py
├── 02项目实战-文档扫描OCR识别/
│ └── Scan/
│ ├── .idea/
│ │ ├── document-scanner.iml
│ │ ├── misc.xml
│ │ ├── modules.xml
│ │ └── workspace.xml
│ ├── scan.py
│ └── test.py
├── LICENSE
├── README.md
├── dataset/
│ └── 2023-02-07-22_46_36.txt
├── practice/
│ └── vis/
│ ├── 01show_bbox.ipynb
│ ├── 02show_line.ipynb
│ └── 03show_text.ipynb
└── 基于python的Opencv项目实战/
├── 图像处理/
│ └── 图像处理-2(直方图&模板匹配).ipynb
└── 图像操作/
├── 图像基本操作.ipynb
└── 图像处理.ipynb
================================================
FILE CONTENTS
================================================
================================================
FILE: .gitignore
================================================
代码+资料
================================================
FILE: 00.py
================================================
import cv2
print(cv2.__version__)
================================================
FILE: 01read_show.py
================================================
# encoding:utf-8
import cv2
img = cv2.imread("./cat.jpg")
cv2.namedWindow("Image显示")
cv2.imshow("Image显示", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# https: // www.cnblogs.com/zangyu/p/5802142.html
================================================
FILE: 01项目实战-信用卡数字识别/template-matching-ocr/myutils.py
================================================
'''
Description: OCR-模板匹配 参考：https://www.bilibili.com/video/BV1oJ411D71z?t=11&p=9
Author: HCQ
Company(School): UCAS
Email: 1756260160@qq.com
Date: 2021-01-23 11:12:41
LastEditTime: 2021-01-25 12:28:10
FilePath: /OpenCV/01项目实战-信用卡数字识别/template-matching-ocr/myutils.py
'''
import cv2
# 轮廓排序
def sort_contours(cnts, method="left-to-right"):
reverse = False
i = 0
if method == "right-to-left" or method == "bottom-to-top":
reverse = True
if method == "top-to-bottom" or method == "bottom-to-top":
i = 1
boundingBoxes = [cv2.boundingRect(c) for c in cnts] #用一个最小的矩形(外接矩形)，把找到的形状包起来x,y,h,w 根据x横坐标就可以排序
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes), # sorted
key=lambda b: b[1][i], reverse=reverse)) # reverse
return cnts, boundingBoxes
# resize
def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
dim = None
(h, w) = image.shape[:2]
if width is None and height is None:
return image
if width is None:
r = height / float(h)
dim = (int(w * r), height)
else:
r = width / float(w)
dim = (width, int(h * r))
resized = cv2.resize(image, dim, interpolation=inter)
return resized
================================================
FILE: 01项目实战-信用卡数字识别/template-matching-ocr/ocr_template_match.py
================================================
'''
Description: OCR-模板匹配 参考：https://www.bilibili.com/video/BV1oJ411D71z?t=11&p=9
运行命令： python ocr_template_match.py -i xxx -t xxx
运行命令： python 01项目实战-信用卡数字识别/template-matching-ocr/ocr_template_match.py -i 01项目实战-信用卡数字识别/template-matching-ocr/images/credit_card_01.png -t 01项目实战-信用卡数字识别/template-matching-ocr/images/ocr_a_reference.png
Author: HCQ
Company(School): UCAS
Email: 1756260160@qq.com
Date: 2021-01-23 11:12:41
LastEditTime: 2021-01-25 14:07:18
FilePath: /OpenCV/01项目实战-信用卡数字识别/template-matching-ocr/ocr_template_match.py
'''
# 导入工具包
from imutils import contours
import numpy as np
import argparse
import cv2
import myutils
# 设置参数
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to input image")
ap.add_argument("-t", "--template", required=True,
help="path to template OCR-A image")
args = vars(ap.parse_args())
# 指定信用卡类型
FIRST_NUMBER = {
"3": "American Express",
"4": "Visa",
"5": "MasterCard",
"6": "Discover Card"
}
# 绘图展示
def cv_show(name,img):
cv2.imshow(name, img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# ==========================开始 1 处理模板图片========================================
# 读取一个模板图像
img = cv2.imread(args["template"]) # 参数 01项目实战-信用卡数字识别/template-matching-ocr/images/ocr_a_reference.png
cv_show('img',img)
# 灰度图
ref = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv_show('ref',ref)
# 二值图像
ref = cv2.threshold(ref, 10, 255, cv2.THRESH_BINARY_INV)[1]
cv_show('ref',ref)
# 计算轮廓
#cv2.findContours()函数接受的参数为二值图，即黑白的（不是灰度图）,cv2.RETR_EXTERNAL只检测外轮廓，cv2.CHAIN_APPROX_SIMPLE只保留终点坐标
#返回的list中每个元素都是图像中的一个轮廓
# 高版本没有第一个参数ref_了，只会返回后两个
# ref_, refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE) # 低版本
refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE) # 高版本
cv2.drawContours(img,refCnts,-1,(0,0,255),3)
cv_show('img',img)
print (np.array(refCnts).shape) # 多少轮廓
refCnts = myutils.sort_contours(refCnts, method="left-to-right")[0] #排序，从左到右，从上到下
digits = {}
# 遍历每一个轮廓
for (i, c) in enumerate(refCnts):
# 计算外接矩形并且resize成合适大小
(x, y, w, h) = cv2.boundingRect(c)
roi = ref[y:y + h, x:x + w] # x旋转区域
roi = cv2.resize(roi, (57, 88)) # resize
# 每一个数字对应每一个模板
digits[i] = roi
# =======================2 处理信用卡图片================================
# 初始化卷积核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)) # 核大小 5x5
#读取输入图像，预处理
image = cv2.imread(args["image"]) # 参数
cv_show('image',image)
image = myutils.resize(image, width=300)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv_show('gray',gray)
#礼帽操作，突出更明亮的区域（字体区域）
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel) # rectKernel初始化核
cv_show('tophat',tophat)
#
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, #ksize=-1相当于用3*3的
ksize=-1)
gradX = np.absolute(gradX) # 只用x效果更好，随意没用xy梯度
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal))) # 归一化
gradX = gradX.astype("uint8")
print (np.array(gradX).shape)
cv_show('gradX',gradX)
#通过闭操作（先膨胀，再腐蚀）将数字连在一起，形成四大块 背景也过滤了
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
cv_show('gradX',gradX)
#THRESH_OTSU会自动寻找合适的阈值，适合双峰，需把阈值参数设置为0
thresh = cv2.threshold(gradX, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('thresh',thresh)
#再来一个闭操作
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel) #再来一个闭操作
cv_show('thresh',thresh)
# 计算轮廓
# 高版本没有第一个参数thresh_了，只会返回后两个
# thresh_, threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
# cv2.CHAIN_APPROX_SIMPLE)
threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = threshCnts # 最终轮廓
cur_img = image.copy()
cv2.drawContours(cur_img,cnts,-1,(0,0,255),3)
cv_show('img',cur_img)
locs = [] # 有价值的区域
# 遍历轮廓
for (i, c) in enumerate(cnts):
# 计算矩形
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h) # 长宽比
# 选择合适的区域，根据实际任务来，这里的基本都是四个数字一组
if ar > 2.5 and ar < 4.0:
if (w > 40 and w < 55) and (h > 10 and h < 20):
#符合的留下来
locs.append((x, y, w, h))
# 将符合的轮廓从左到右排序
locs = sorted(locs, key=lambda x:x[0])
output = []
# 遍历每一个轮廓中的数字（四个大轮廓，每个轮廓里面有4个数字）
for (i, (gX, gY, gW, gH)) in enumerate(locs):
# initialize the list of group digits
groupOutput = []
# 根据坐标提取每一个组
group = gray[gY - 5:gY + gH + 5, gX - 5:gX + gW + 5] # 往外扩大一点范围
cv_show('group',group)
# 预处理（二值化）
group = cv2.threshold(group, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('group',group)
# 计算每一组的轮廓（4个数字，四个轮廓）
# 高版本没有第一个参数group_了，只会返回后两个
# group_,digitCnts,hierarchy = cv2.findContours(group.copy(), cv2.RETR_EXTERNAL,
# cv2.CHAIN_APPROX_SIMPLE)
digitCnts,hierarchy = cv2.findContours(group.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
digitCnts = contours.sort_contours(digitCnts,
method="left-to-right")[0]
# 计算每一组中的每一个数值
for c in digitCnts:
# 找到当前数值的轮廓，resize成合适的的大小
(x, y, w, h) = cv2.boundingRect(c)
roi = group[y:y + h, x:x + w]
roi = cv2.resize(roi, (57, 88))
cv_show('roi',roi)
# 计算匹配得分
scores = []
# 在模板中计算每一个得分=============================================================================
for (digit, digitROI) in digits.items():
# 模板匹配（和模板中的10个数字匹配）
result = cv2.matchTemplate(roi, digitROI,
cv2.TM_CCOEFF)
(_, score, _, _) = cv2.minMaxLoc(result)
scores.append(score)
# 得到最合适的数字
groupOutput.append(str(np.argmax(scores))) # score最大的下标
# 画出来
cv2.rectangle(image, (gX - 5, gY - 5),
(gX + gW + 5, gY + gH + 5), (0, 0, 255), 1)
cv2.putText(image, "".join(groupOutput), (gX, gY - 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.65, (0, 0, 255), 2)
# 得到结果
output.extend(groupOutput)
# 打印结果
print("Credit Card Type: {}".format(FIRST_NUMBER[output[0]]))
print("Credit Card #: {}".format("".join(output)))
cv2.imshow("Image", image)
cv2.waitKey(0)
================================================
FILE: 02save.py
================================================
import cv2
import numpy as np
img = cv2.imread("./cat.jpg")
emptyImage = np.zeros(img.shape, np.uint8)
emptyImage2 = img.copy()
emptyImage3 = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#emptyImage3[...]=0
cv2.imshow("EmptyImage", emptyImage)
cv2.imshow("Image", img)
cv2.imshow("EmptyImage2", emptyImage2)
cv2.imshow("EmptyImage3", emptyImage3)
cv2.imwrite("./img/cat2.jpg", img, [int(cv2.IMWRITE_JPEG_QUALITY), 5])
cv2.imwrite("./img/cat3.jpg", img, [int(cv2.IMWRITE_JPEG_QUALITY), 100])
cv2.imwrite("./img/cat.png", img, [int(cv2.IMWRITE_PNG_COMPRESSION), 0])
cv2.imwrite("./img/cat2.png", img, [int(cv2.IMWRITE_PNG_COMPRESSION), 9])
cv2.waitKey(0)
cv2.destroyAllWindows()
================================================
FILE: 02项目实战-文档扫描OCR识别/Scan/.idea/document-scanner.iml
================================================
================================================
FILE: 02项目实战-文档扫描OCR识别/Scan/.idea/misc.xml
================================================
================================================
FILE: 02项目实战-文档扫描OCR识别/Scan/.idea/modules.xml
================================================
================================================
FILE: 02项目实战-文档扫描OCR识别/Scan/.idea/workspace.xml
================================================