def colormask(image, isday=True, tgtcolr='Default', isdebug=False):
#
#image = NormalizeT(image)
#showResult("normalized",image)
# blue mask + yellow mask
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
h, s, v = cv2.split(hsv)
sat = (s.copy()).astype('float')
val = (v.copy()).astype('float')
sat /= 255
val /= 255
#
hue = np.zeros(image.shape[:2])
hue[hue >= 0] = 0.2
#
blue1 = h.copy()
blue2 = h.copy()
yellow = h.copy()
#
if isday:
blue1 = np.where((h < 105) | (h > 135) | (v < 40) | (s < 40), 0, 255)
blue2 = np.where((h < 100) | (h > 140) | (v < 30) | (s < 30), 0, 255)
yellow = np.where((h < 20) | (h > 40) | (v < 40) | (s < 40), 0, 255)
else:
blue1 = np.where((h < 105) | (h > 135), 0, 255)
blue2 = np.where((h < 100) | (h > 140), 0, 255)
yellow = np.where((h < 20) | (h > 40), 0, 255)
#
for case in switch(tgtcolr):
if case('Blue'):
hue[blue2 > 0] = 0.5
hue[blue1 > 0] = 1.0
hue[yellow > 0] = 0.1
break
if case('Yellow'):
hue[yellow > 0] = 1.0
hue[blue2 > 0] = 0.1
hue[blue1 > 0] = 0.15
break
if case('Default'):
hue[blue2 > 0] = 0.4
hue[blue1 > 0] = 0.9
hue[yellow > 0] = 0.7
break
#
if isday:
mask = (hue * sat * val)**2 #(hue*sat*val)**2
else:
mask = (hue * sat)**2
#
if isdebug:
showResult("colormask:mask", mask)
return mask
def detect(self, origin, isdebug=False):
start = time.time()
# Default Size
h, w, c = origin.shape
size = 200.0
# Resize
img = cv2.resize(origin, (int(w * size / h), int(size)))
#showResult("img",img)
for case in switch(AnalyzeImageQuality.dayornight(img)):
if case('Day'):
# Extract Good Features
corners = refinedGoodFeatures(origin, img)
mask = checkFeatures(img, corners, isdebug)
closing = close(mask)
refined_gfmask = refine_gfimage(img, closing)
#showResult("refined_gfmask",refined_gfmask)
finalmasks = mkfinalmasks(img,
refined_gfmask,
isday=True,
isdebug=isdebug)
break
if case('Night'):
finalmasks = mkfinalmasks(img, None, isday=isdebug)
break
for colrindex, fmask in enumerate(finalmasks):
if (fmask > 0).sum() == 0:
continue
bboxes = mask2plates(img, fmask)
# Resize
if bboxes is not None:
bboxes = resizeBBoxes(bboxes, h / size)
rois = BBoxes2ROIs(origin, bboxes)
for i, roi in enumerate(rois):
confidence = self.licenplatevalidator.process(
roi, mode=colrs[colrindex], isdebug=isdebug)
print confidence
if confidence > 0.7:
#pts = self.licenplatevalidator.getRefinedROI()
#bbox = refineBBox(bboxes[i],pts)
bbox = resizeBBox(bboxes[i], ratio=0.9)
print("total elapsed time: " +
str(int((time.time() - start) * 1000) / 1000.0) +
"s")
return confidence, [bbox], [roi]
'''
# Check Result
if isdebug and bboxes is not None:
drawBBox(origin,bboxes,debug=True)
for i in range(len(rois)):
showResult("cropped",rois[i])
'''
return 0.0, None, None
def morphological(img, model=cv2.MORPH_OPEN):
#http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_imgproc/py_morphological_ops/py_morphological_ops.html
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
#cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(5,5))
#cv2.getStructuringElement(cv2.MORPH_CROSS,(5,5))
for case in switch(model):
if case(cv2.MORPH_OPEN):
out = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
break
if case(cv2.MORPH_CLOSE):
out = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
return out
def FeatureSpace(img, target="LP"):
# RGB->HSV
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
h, s, v = cv2.split(hsv)
#blur = cv2.GaussianBlur(s,(5,5),0)
#gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#s_ = np.array(s.shape)
#s_ = cv2.normalize(s, s_, 0, 255, cv2.NORM_MINMAX)
for case in switch(target):
if case('LP'):
return s
if case('VIN'):
return v
def processImg(file_path, filename):
thisiswhat = app.classifier.run(file_path)
image = cv2.imread(file_path)
for case in switch(thisiswhat):
app.results.append(filename + " :")
if case('lp'):
app.results.append(" 现场相片")
# Detect Vehicle
bbox_car = app.detector.detect(
opencv2skimage(image)) #mpimg.imread(path)
if bbox_car is not None:
img_car = cropImg_by_BBox(image, bbox_car)
app.results.append(r"车 : 有 ")
# Detect License Plate
confidence, bboxes_lp, rois = app.licenseplatedetector.process(
img_car)
markImg = processLP(image, bbox_car, bboxes_lp, confidence)
cv2.imwrite(file_path, markImg)
else:
app.results.append(r"车 : 不全面")
confidence, bboxes_lp, rois = app.licenseplatedetector.process(
image)
markImg = processLP(image, None, bboxes_lp, confidence)
if markImg is not None:
cv2.imwrite(file_path, markImg)
break
if case('vin'):
app.results.append(r" 车架号")
app.vehicleidentifier.initialize()
isFound, confidence, markImg = app.vehicleidentifier.process(image)
if isFound:
app.results.append(r"车架号 : 有")
cv2.imwrite(file_path, markImg)
else:
app.results.append(r"车架号 : 没有")
break
if case():
app.results.append(r" 没意思")
break
def upload_file():
if request.method == 'POST':
file = request.files['file']
if file and allowed_file(file.filename):
# Delete tmp files
# if exists(app.image_fn):
# os.remove(app.image_fn)
if exists(app.result_fn):
os.remove(app.result_fn)
app.results[:] = []
# save an uploaded file to "uploads" folder
filename = secure_filename(file.filename)
app.filename = filename
file_path = os.path.join(app.config['UPLOAD_FOLDER'], app.filename)
file.save(file_path)
#####################
# Analyze the Image #
#####################
start = time.time()
# Load Image
image = cv2.imread(file_path)
# Quality Analyzing
app.qualityanalyzer.initialize()
fm, result, explanation = app.qualityanalyzer.process(image)
for case in switch(explanation):
if case('Normal'):
# Determine what this is
processImg(file_path, filename)
break
if case('Blurry'):
app.results.append(r" 模糊")
break
if case('Reflective'):
app.results.append(r" 不清楚")
processImg(file_path, filename)
break
if case('Too Reflective'):
app.results.append(r" 曝光过度")
break
end = time.time()
elapsedtime = end - start
app.results.append(r"经过时间 : " +
str(int(elapsedtime * 1000) / 1000.0) + "s ")
#######################
#######################
# Save Image and Result
#os.rename(file_path, app.image_fn)
with open(app.result_fn, 'w') as file:
for result in app.results:
file.write(result)
file.write('\n')
return redirect("/")
#return redirect(url_for('uploaded_file',
# filename="facedetect-"+filename))
results = ""
for result in app.results:
results += html.result_value_header + result + html.result_value_tail
image = ""
if exists(os.path.join(app.config['UPLOAD_FOLDER'], app.filename)):
image = html.image_header + app.filename + html.image_tail
return html.header + \
html.result_header + \
results + \
html.result_tail +\
html.image_container_header +\
image + \
html.image_container_tail + \
html.tail