圖片中通過查找輪廓,然后繪制輪廓外界矩形的方式,將每一和數(shù)字分割出來,并和對(duì)應(yīng)的數(shù)字相對(duì)應(yīng)。以字典的形式保存
每一個(gè)模板都是這樣的形式存儲(chǔ)。
array([[ 0, 0, 0, 0, 0, 0, 0, 255, 255, 255, 255, 255, 255],
[ 0, 0, 0, 0, 0, 0, 0, 0, 255, 255, 255, 255, 255],
[ 0, 0, 0, 0, 0, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 0, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 255, 255, 255],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 255, 255, 255, 255, 0, 0, 0, 255, 255, 0, 0, 0],
[255, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[255, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 255, 255]], dtype=uint8)
對(duì)測試圖片操作,取得我們需要的,每個(gè)數(shù)字的像素 .
3.經(jīng)過Sobel之后可能數(shù)字沒有連接在一起,所以執(zhí)行閉操作將相鄰的數(shù)字連接起來,因?yàn)閿?shù)字是橫向的,所以閉操作的核設(shè)置為[1,1,1,1,1,1,1,1,1]
。
5.通過連續(xù)數(shù)字區(qū)域分割出每一個(gè)數(shù)字,然后將每個(gè)數(shù)字和模板進(jìn)行匹配,匹配結(jié)果最高的就是最有可能的數(shù)字。
# 初始化卷積核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
#讀取輸入圖像,預(yù)處理
image = cv2.imread(image)
cv_show('image',image)
image = myutils.resize(image, width=300)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv_show('gray',gray)
#禮帽操作,突出更明亮的區(qū)域
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
cv_show('tophat',tophat)
#
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, #ksize=-1相當(dāng)于用3*3的
ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")
print (np.array(gradX).shape)
cv_show('gradX',gradX)
#通過閉操作(先膨脹,再腐蝕)將數(shù)字連在一起
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
cv_show('gradX',gradX)
#THRESH_OTSU會(huì)自動(dòng)尋找合適的閾值,適合雙峰,需把閾值參數(shù)設(shè)置為0
thresh = cv2.threshold(gradX, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('thresh',thresh)
#再來一個(gè)閉操作
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel) #再來一個(gè)閉操作
cv_show('thresh',thresh)
# 計(jì)算輪廓
thresh_, threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = threshCnts
cur_img = image.copy()
cv2.drawContours(cur_img,cnts,-1,(0,0,255),3)
cv_show('img',cur_img)
locs = []
# 遍歷輪廓
for (i, c) in enumerate(cnts):
# 計(jì)算矩形
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h)
# 選擇合適的區(qū)域,根據(jù)實(shí)際任務(wù)來,這里的基本都是四個(gè)數(shù)字一組
if ar > 2.5 and ar 4.0:
if (w > 40 and w 55) and (h > 10 and h 20):
#符合的留下來
locs.append((x, y, w, h))
# 將符合的輪廓從左到右排序
locs = sorted(locs, key=lambda x:x[0])
output = []
# 遍歷每一個(gè)輪廓中的數(shù)字
for (i, (gX, gY, gW, gH)) in enumerate(locs):
# initialize the list of group digits
groupOutput = []
# 根據(jù)坐標(biāo)提取每一個(gè)組
group = gray[gY - 5:gY + gH + 5, gX - 5:gX + gW + 5]
cv_show('group',group)
# 預(yù)處理
group = cv2.threshold(group, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('group',group)
# 計(jì)算每一組的輪廓
group_,digitCnts,hierarchy = cv2.findContours(group.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
digitCnts = contours.sort_contours(digitCnts,
method="left-to-right")[0]
# 計(jì)算每一組中的每一個(gè)數(shù)值
for c in digitCnts:
# 找到當(dāng)前數(shù)值的輪廓,resize成合適的的大小
(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)
# 計(jì)算匹配得分
scores = []
# 在模板中計(jì)算每一個(gè)得分
for (digit, digitROI) in digits.items():
# 模板匹配
result = cv2.matchTemplate(roi, digitROI,
cv2.TM_CCOEFF)
(_, score, _, _) = cv2.minMaxLoc(result)
scores.append(score)
# 得到最合適的數(shù)字
groupOutput.append(str(np.argmax(scores)))
# 畫出來
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)
# 得到結(jié)果
output.extend(groupOutput)
# 打印結(jié)果
print("Credit Card Type: {}".format(FIRST_NUMBER[output[0]]))
print("Credit Card #: {}".format("".join(output)))
cv2.imshow("Image", image)
cv2.waitKey(0)
# (194, 300)
# Credit Card Type: MasterCard
# Credit Card #: 5412751234567890
到此這篇關(guān)于Python如何識(shí)別銀行卡卡號(hào)?的文章就介紹到這了,更多相關(guān)Python識(shí)別卡號(hào)內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家!