import numpy as np
import cv2

def cv_show(name,img):
    cv2.imshow(name,img)
    cv2.waitKey(10)

def order_points(pts):
    rect = np.zeros((4,2),dtype="float32")
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]  # 左上點(diǎn)(x+y最小)
    rect[2] = pts[np.argmax(s)]  # 右下點(diǎn)(x+y最大)
    diff = np.diff(pts,axis=1)
    rect[1] = pts[np.argmin(diff)]  # 右上點(diǎn)(y-x最小)
    rect[3] = pts[np.argmax(diff)]  # 左下點(diǎn)(y-x最大)
    return rect

	A(10, 20)  # 假設(shè)是左上
	B(50, 20)  # 右上
	C(50, 60)  # 右下
	D(10, 60)  # 左下

def four_point_transform(image,pts):
    rect = order_points(pts)
    (tl,tr,br,bl) = rect
    
    # 計(jì)算變換后的寬度和高度
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA),int(widthB))
    
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA),int(heightB))
    
    # 定義目標(biāo)圖像坐標(biāo)
    dst = np.array([[0,0],[maxWidth - 1,0],
                    [maxWidth - 1,maxHeight - 1],[0,maxHeight - 1]],dtype="float32")

    # 計(jì)算透視變換矩陣并應(yīng)用
    M = cv2.getPerspectiveTransform(rect,dst)
    warped = cv2.warpPerspective(image,M,(maxWidth,maxHeight))
    
    return warped

def four_point_transform(image, pts):

rect = order_points(pts)
(tl, tr, br, bl) = rect  # 分解為左上(top-left)、右上(top-right)、右下(bottom-right)、左下(bottom-left)

widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))  # 底邊長(zhǎng)度
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))  # 頂邊長(zhǎng)度
maxWidth = max(int(widthA), int(widthB))  # 取最大值作為輸出圖像寬度

heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))  # 右邊高度
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))  # 左邊高度
maxHeight = max(int(heightA), int(heightB))  # 取最大值作為輸出圖像高度

dst = np.array([
    [0, 0],  # 左上
    [maxWidth - 1, 0],  # 右上
    [maxWidth - 1, maxHeight - 1],  # 右下
    [0, maxHeight - 1]  # 左下
], dtype="float32")

M = cv2.getPerspectiveTransform(rect, dst)  # 計(jì)算變換矩陣
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))  # 應(yīng)用變換

return warped

原始圖像中的四邊形               變換后的矩形
   tl--------tr                    0--------maxWidth
    \        /                      |        |
     \      /                       |        |
      bl----br                       maxHeight

cap = cv2.VideoCapture(0)
if not cap.isOpened():
    print("Cannot open camera")
    exit()

while True:
    flag = 0
    ret,image = cap.read()
    orig = image.copy()
    if not ret:
        print("不能讀取攝像頭")
        break

gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray,(5,5),0)  # 高斯濾波降噪
edged = cv2.Canny(gray,75,200)  # Canny邊緣檢測(cè)

cnts = cv2.findContours(edged,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[-2]
cnts = sorted(cnts,key=cv2.contourArea,reverse=True)[:3]  # 取面積最大的3個(gè)輪廓

for c in cnts:
    peri = cv2.arcLength(c,True)  # 計(jì)算輪廓周長(zhǎng)
    approx = cv2.approxPolyDP(c,0.05 * peri,True)  # 多邊形近似
    area = cv2.contourArea(approx)
    
    # 篩選四邊形且面積足夠大的輪廓
    if area > 20000 and len(approx) == 4:
        screenCnt = approx
        flag = 1
        break

if flag == 1:
    # 繪制輪廓
    image_contours = cv2.drawContours(image,[screenCnt],0,(0,255,0),2)
    
    # 透視變換
    warped = four_point_transform(orig,screenCnt.reshape(4,2))
    
    # 二值化處理
    warped = cv2.cvtColor(warped,cv2.COLOR_BGR2GRAY)
    ref = cv2.threshold(warped,0,255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

# 導(dǎo)入工具包
import numpy as np
import cv2

def cv_show(name,img):
    cv2.imshow(name,img)
    cv2.waitKey(10)
def order_points(pts):
    # 一共4個(gè)坐標(biāo)點(diǎn)
    rect = np.zeros((4,2),dtype="float32") # 用來存儲(chǔ)排序之后的坐標(biāo)位置
    # 按順序找到對(duì)應(yīng)坐標(biāo)0123分別是 左上、右上、右下、左下
    s = pts.sum(axis=1) #對(duì)pts矩陣的每一行進(jìn)行求和操作，（x+y）
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]
    diff = np.diff(pts,axis=1) #對(duì)pts矩陣的每一行進(jìn)行求差操作，（y-x）
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]
    return rect

def four_point_transform(image,pts):
    # 獲取輸入坐標(biāo)點(diǎn)
    rect = order_points(pts)
    (tl,tr,br,bl) = rect
    # 計(jì)算輸入的w和h值
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA),int(widthB))
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA),int(heightB))
    # 變換后對(duì)應(yīng)坐標(biāo)位置
    dst = np.array([[0,0],[maxWidth - 1,0],
                    [maxWidth - 1,maxHeight - 1],[0,maxHeight - 1]],dtype="float32")

    M = cv2.getPerspectiveTransform(rect,dst)
    warped = cv2.warpPerspective(image,M,(maxWidth,maxHeight))
    # 返回變換后的結(jié)果
    return warped


# 讀取輸入
import cv2
cap = cv2.VideoCapture(0)  # 確保攝像頭是可以啟動(dòng)的狀態(tài)
if not cap.isOpened():   #打開失敗
    print("Cannot open camera")
    exit()

while True:
    flag = 0 # 用于標(biāo)時(shí) 當(dāng)前是否檢測(cè)到文檔
    ret,image = cap.read()  # 如果正確讀取幀，ret為True
    orig = image.copy()
    if not ret: #讀取失敗，則退出循環(huán)
        print("不能讀取攝像頭")
        break
    cv_show("image",image)

    gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
    # 預(yù)處理
    gray = cv2.GaussianBlur(gray,(5,5),0) # 高斯濾波
    edged = cv2.Canny(gray,75,200)
    cv_show('1',edged)

    # 輪廓檢測(cè)
    cnts = cv2.findContours(edged,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[-2]

    cnts = sorted(cnts,key=cv2.contourArea,reverse=True)[:3]
    image_contours = cv2.drawContours(image,cnts,-1,(0,255,0),2)
    cv_show("image_contours",image_contours)
    # 遍歷輪廓
    for c in cnts:
        # 計(jì)算輪廓近似
        peri = cv2.arcLength(c,True) # 計(jì)算輪廓的周長(zhǎng)
        # C 表示輸入的點(diǎn)集
        # epsilon表示從原始輪廓到近似輪廓的最大距離，它是一個(gè)準(zhǔn)確度參數(shù)
        # True表示封閉的
        approx = cv2.approxPolyDP(c,0.05 * peri,True) # 輪廓近似
        area = cv2.contourArea(approx)
        # 4個(gè)點(diǎn)的時(shí)候就拿出來
        if area > 20000 and len(approx) == 4:
            screenCnt = approx
            flag = 1
            print(peri,area)
            print("檢測(cè)到文檔")
            break
    if flag == 1:
        # 展示結(jié)果
        # print("STEP 2: 獲取輪廓")
        image_contours = cv2.drawContours(image,[screenCnt],0,(0,255,0),2)
        cv_show("image",image_contours)
        # 透視變換
        warped = four_point_transform(orig,screenCnt.reshape(4,2))
        cv_show("warped",warped)
        # 二值處理
        warped = cv2.cvtColor(warped,cv2.COLOR_BGR2GRAY)
        # ref = cv2.threshold(warped,220,255,cv2.THRESH_BINARY)[1]
        ref = cv2.threshold(warped,0,255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
        cv_show("ref",ref)
cap.release() # 釋放捕捉器
cv2.destroyAllWindows() #關(guān)閉圖像窗口