def show_gray_histogram(self):
numbins = 256
ranges = [0.0, 255.0]
width = 256
height = 256
bytes_per_line = 3 * width
hist_image = np.zeros([height, width, 3], np.uint8)
# hist_image = np.zeros((256,256,3)) #创建用于绘制直方图的全0图像
bins = np.arange(numbins).reshape(numbins, 1) # 直方图中各bin的顶点位置
color = [(255, 0, 0)] # BGR三种颜色
for ch, col in enumerate(color):
origin_hist = cv2.calcHist([self.gray_image], [ch], None, [numbins], ranges)
cv2.normalize(origin_hist, origin_hist, 0, 255 * 0.9, cv2.NORM_MINMAX)
hist = np.int32(np.around(origin_hist))
pts = np.column_stack((bins, hist))
cv2.polylines(hist_image, [pts], False, col)
# print(type(hist_image.data))
hist_image = np.flipud(hist_image)
# cv2.imshow("histogram", hist_image)
demo_utils.show_cvimage_to_label(hist_image, self.gray_histogram_label)
def load_image(self):
fname, _ = QFileDialog.getOpenFileName(self, 'Open file', './images', "Image files (*.jpg *.png)")
if len(fname) > 0:
self.image = cv2.imread(fname)
# cv2.imshow(fname, image)
demo_utils.show_cvimage_to_label(self.image, self.image_label)
self.show_histogram()
def classify_sklearn_svm(self):
svc = SVC()
svc.fit(self.training_data, self.responses_data)
predicted = svc.predict(self.test_data)
print("Confusion matrix:\n%s" %
metrics.confusion_matrix(self.test_responses_data,
predicted))
print("Accuracy: %0.4f" % metrics.accuracy_score(self.test_responses_data,
predicted))
output = self.image.copy()
font = cv2.FONT_HERSHEY_SIMPLEX
# fontScale
fontScale = 0.5
# Blue color in BGR
color1 = (255, 0, 0)
# Line thickness of 2 px
thickness = 1
self.features = classify_utils.extract_feautre(self.threshold_image)
print(self.features)
for i in range(0, len(self.features)):
sample_data = np.array([self.features[i][0]], dtype=np.float32)
# print(sample_data.shape)
result = svc.predict(sample_data)
print(self.features[i][0])
print(result[0])
label = int(result[0])
org = (int(self.features[i][1][0]), int(self.features[i][1][1]))
if label == 0:
color = (255, 0, 0)
text = "NUT"
elif label == 1:
color = (0, 255, 0)
text = "RING"
else:
color = (0, 0, 255)
text = "SCREW"
output = cv2.putText(output, text, org, font,
fontScale, color, thickness)
demo_utils.show_cvimage_to_label(output, self.result_label2)
def remove_noise(self):
height, width, bytes_per_component = self.image.shape
bytes_per_line = 3 * width
self.noise_image = np.zeros(self.image.shape, np.uint8)
cv2.medianBlur(self.image, 3, self.noise_image)
demo_utils.show_cvimage_to_label(self.noise_image, self.noise_label)
def load_image(self):
fname, _ = QFileDialog.getOpenFileName(self, 'Open file', './classify_data', "Image files (*.jpg *.png *.pgm)")
if len(fname) > 0:
self.image = cv2.imread(fname)
demo_utils.show_cvimage_to_label(self.image, self.image_label)
self.light_image = cv2.imread('./classify_data/pattern.pgm')
self.threshold_image = classify_utils.preprocess_image(self.image, self.light_image)
demo_utils.show_cvimage_to_label(self.threshold_image, self.threshold_label)
def show_histogram(self):
# hist = cv2.calcHist([self.image],
# [0], #使用的通道
# None, #没有使用mask
# [256], #HistSize
# [0.0,255.0])
b, g, r = cv2.split(self.image)
numbins = 256
ranges = [0.0, 256.0]
b_hist = cv2.calcHist([b], [0], None, [numbins], ranges)
g_hist = cv2.calcHist([g], [0], None, [numbins], ranges)
r_hist = cv2.calcHist([r], [0], None, [numbins], ranges)
print(b_hist.shape)
width = 256
height = 256
hist_image = np.zeros([height, width, 3], np.uint8)
cv2.normalize(b_hist, b_hist, 0, height * 0.9, cv2.NORM_MINMAX)
cv2.normalize(g_hist, g_hist, 0, height * 0.9, cv2.NORM_MINMAX)
cv2.normalize(r_hist, r_hist, 0, height * 0.9, cv2.NORM_MINMAX)
for i in range(1, numbins, 1):
cv2.line(hist_image,
(i - 1, height - np.int32(np.around(b_hist[i - 1][0]))),
(i, height - np.int32(np.around(b_hist[i][0]))),
(255, 0, 0)
)
cv2.line(hist_image,
(i - 1, height - np.int32(np.around(g_hist[i - 1][0]))),
(i, height - np.int32(np.around(g_hist[i][0]))),
(0, 255, 0)
)
cv2.line(hist_image,
(i - 1, height - np.int32(np.around(r_hist[i - 1][0]))),
(i, height - np.int32(np.around(r_hist[i][0]))),
(0, 0, 255)
)
# cv2.imshow("Histogram", hist_image)
demo_utils.show_cvimage_to_label(hist_image, self.histogram_label)
self.show_histogram2()
def remove_light(self):
height, width, bytes_per_component = self.image.shape
bytes_per_line = 3 * width
img32 = np.float32(self.noise_image)
light32 = np.float32(self.light_image)
#
devided = np.divide(img32, light32)
sub_result = 1 - devided
aux = abs(255 * sub_result)
self.light_removed_image = np.uint8(aux)
# light_removed_image = abs(light32 - img32)
# light_removed_image = np.uint8(light_removed_image)
# light_removed_image = np.zeros(self.image.shape, np.uint8)
# cv2.medianBlur(self.image, 3, light_removed_image)
demo_utils.show_cvimage_to_label(self.light_removed_image,
self.light_removed_label)
def apply_threshold(self):
height, width, bytes_per_component = self.image.shape
bytes_per_line = 3 * width
self.threshold_image = np.zeros(self.image.shape, np.uint8)
cv2.threshold(self.light_removed_image, 50, 255, cv2.THRESH_BINARY,
self.threshold_image)
demo_utils.show_cvimage_to_label(self.threshold_image,
self.threshold_label)
imgray = cv2.cvtColor(self.threshold_image, cv2.COLOR_BGR2GRAY)
result = cv2.connectedComponentsWithStats(imgray)
# cv2.CC_STAT_AREA
print(" %d objects found" % result[0])
num_labels = result[0]
# The second cell is the label matrix
labels = result[1]
stats = result[2]
controlids = result[3]
output = np.zeros(self.image.shape, np.uint8)
random.seed()
font = cv2.FONT_HERSHEY_SIMPLEX
# org
org = (50, 50)
# fontScale
fontScale = 0.5
# Blue color in BGR
color1 = (255, 0, 0)
# Line thickness of 2 px
thickness = 1
outputed = False
for i in range(1, num_labels):
area = stats[i][cv2.CC_STAT_AREA]
if area > 10:
print("object:%d with area %d" % (i, area))
mask = labels == i
color = (random.randint(40, 220), random.randint(40, 220),
random.randint(40, 220))
# np.putmask(output, mask, [color])
output[mask] = color
# Using cv2.putText() method
# if not outputed:
print(controlids[i])
org = controlids[i].astype(int)
output = cv2.putText(output, "area: %d" % (area), tuple(org),
font, fontScale, color, thickness)
# outputed = True
# cv2.putText(output, "area %d" % (area), tuple(controlids[i]), cv2.FONT_HERSHEY_COMPLEX,int(6) , color)
demo_utils.show_cvimage_to_label(output, self.segment_label)
def classify_cv_svm(self):
self.svm = cv2.ml.SVM_create()
self.svm.setType(cv2.ml.SVM_C_SVC)
self.svm.setNu(0.05)
self.svm.setKernel(cv2.ml.SVM_CHI2)
self.svm.setDegree(1.0)
# self.svm.setC(2.67)
self.svm.setGamma(2.0)
# TermCriteria(TermCriteria::MAX_ITER, 100, 1e-6));
self.svm.setTermCriteria((cv2.TERM_CRITERIA_MAX_ITER, 100, 1.e-06))
self.svm.train(self.training_data, cv2.ml.ROW_SAMPLE, self.responses_data)
# self.svm.save('svm_data.dat')
result = self.svm.predict(self.test_data)
print(result[1].shape)
print(self.test_responses_data.shape)
# result = np.aarray(result, dtype=np.int32)
result1 = np.array([x[0] for x in result[1]], dtype=np.int32)
print(result1.shape)
mask = result1 == self.test_responses_data
correct = np.count_nonzero(mask)
print("Accuracy cv svm: %0.4f" % (correct * 100.0 / len(result1)))
output = self.image.copy()
font = cv2.FONT_HERSHEY_SIMPLEX
# fontScale
fontScale = 0.5
# Blue color in BGR
color1 = (255, 0, 0)
# Line thickness of 2 px
thickness = 1
self.features = classify_utils.extract_feautre(self.threshold_image)
print(self.features)
for i in range(0, len(self.features)):
sample_data = np.array([self.features[i][0]], dtype=np.float32)
# print(sample_data.shape)
result = self.svm.predict(sample_data)
print(self.features[i][0])
print(result[1][0][0])
label = int(result[1][0][0])
org = (int(self.features[i][1][0]), int(self.features[i][1][1]))
if label == 0:
color = (255, 0, 0)
text = "NUT"
elif label == 1:
color = (0, 255, 0)
text = "RING"
else:
color = (0, 0, 255)
text = "SCREW"
output = cv2.putText(output, text, org, font,
fontScale, color, thickness)
demo_utils.show_cvimage_to_label(output, self.result_label)