def get_pic_detail():
""" 你的 APPID AK SK """
APP_ID = '10327698'
API_KEY = 'xe7uEVwG7aPfIwrYdCpbBBke'
SECRET_KEY = 'rEdBGcYjOPmq8ZZG2GVF4XXjkvva3UGC'
aipImageClassify = AipImageClassify(APP_ID, API_KEY, SECRET_KEY)
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()
image = get_file_content('00.jpg')
options = {}
print(aipImageClassify.objectDetect(image, options))
class ImageColor:
def __init__(self, url=None, file_path=None):
self.file_path = file_path
self.client = AipImageClassify(APP_ID, API_KEY, SECRET_KEY)
self.param = None
self.url = url
self.img = None
self.response = None
# 读取图片
def read_image(self):
if self.file_path:
self.img = cv2.imread(self.file_path)
elif self.url:
self.response = requests.get(self.url)
image_numpy = np.asarray(bytearray(self.response.content), dtype="uint8")
img = cv2.imdecode(image_numpy, cv2.IMREAD_COLOR)
self.img = img
# 主体检测
def subject_detection(self):
if self.file_path:
with open(self.file_path, 'rb') as fp:
# 调用图像主体检测
options = dict()
options["with_face"] = 0
response = self.client.objectDetect(fp.read(), options)
self.param = response['result']
elif self.url:
# 调用图像主体检测
options = dict()
options["with_face"] = 0
response = self.client.objectDetect(self.response.content, options)
if 'result' in response:
self.param = response['result']
# 主体参数裁剪图片
def tailoring(self):
if self.param:
self.img = self.img[self.param['top']:self.param['top'] + self.param['height'],
self.param['left']:self.param['left'] + self.param['width']]
# cv2.imshow('ai', initial_image) # 显示图片
# cv2.waitKey(0)
# 颜色识别
def color_recognition(self, expected_size=40, in_clusters=7, out_clusters=3):
# a = time.time()
self.read_image()
# b = time.time()
# print('读取图片',b-a)
# self.subject_detection()
# c = time.time()
# print('主体检测', c - b)
# self.tailoring()
# d = time.time()
# print('裁剪', d - c)
height, width = self.img.shape[:2]
factor = math.sqrt(width * height / (expected_size * expected_size))
# 下采样 缩小图片
image = cv2.resize(self.img,
(int(width / factor), int(height / factor)),
interpolation=cv2.INTER_LINEAR)
LAB_image = cv2.cvtColor(image, cv2.COLOR_BGR2Lab)
frame_width = int(expected_size / 10 + 2)
in_samples = []
border_samples = []
limit_Y = LAB_image.shape[0] - frame_width
limit_X = LAB_image.shape[1] - frame_width
for y in range(LAB_image.shape[0] - 1):
for x in range(LAB_image.shape[1] - 1):
pt = LAB_image[y][x]
if x < frame_width or y < frame_width or y >= limit_Y or x >= limit_X:
border_samples.append(pt)
else:
in_samples.append(pt)
in_samples = np.array(in_samples, dtype=float)
border_samples = np.array(border_samples, dtype=float)
em_in = cv2.ml.EM_create()
em_in.setClustersNumber(in_clusters)
in_etval, in_likelihoods, in_labels, in_probs = em_in.trainEM(in_samples)
in_means = em_in.getMeans()
in_covs = em_in.getCovs()
em_border = cv2.ml.EM_create()
em_border.setClustersNumber(out_clusters)
border_etval, border_likelihoods, border_labels, border_probs = em_border.trainEM(border_samples)
border_means = em_border.getMeans()
unique_border, counts_border = np.unique(border_labels, return_counts=True)
count_border_labels = dict(zip(unique_border, counts_border))
unique, counts = np.unique(in_labels, return_counts=True)
count_in_labels = dict(zip(unique, counts))
for i in range(in_clusters):
if i not in count_in_labels:
count_in_labels[i] = 0
in_len = len(in_covs)
valid = [True] * in_len
# colors vs background
for i in range(in_len):
if not valid[i]:
continue
prop_in = float(count_in_labels[i]) / len(in_labels)
# 如果比例太小，只能是按钮或标签
if prop_in < 0.05:
valid[i] = False
continue
# 删除相似的颜色
for key in count_border_labels:
prop_border = float(count_border_labels[key]) / len(border_labels)
# 如果颜色更多地出现在中间，它就属于主色调，而不是背景。
if prop_in > prop_border:
continue
cie_dst = CIE2000_distance(in_means[i], border_means[key])
if cie_dst < 5:
valid[i] = False
# colors vs colors
for i in range(in_len):
if not valid[i]:
continue
for j in range(i + 1, in_len):
if not valid[j]:
continue
# 删除阴影和类似颜色
cie_dst = CIE2000_distance(in_means[i], in_means[j])
is_shadow = LAB_shadow(in_means[i], in_means[j])
if is_shadow or cie_dst < 30:
if count_in_labels[j] > count_in_labels[i]:
valid[i] = False
count_in_labels[j] += count_in_labels[i]
break
else:
valid[j] = False
count_in_labels[i] += count_in_labels[j]
num_valid = sum(True == x for x in valid)
colors = []
proportions = []
total_color = 0
# 如果布料与背景颜色相同，则采用更常见的颜色。
if num_valid == 0:
pos = max(count_in_labels, key=count_in_labels.get)
colors = [in_means[pos]]
proportions = [count_in_labels[pos]]
total_color = count_in_labels[pos]
for i in range(in_len):
if not valid[i]:
continue
color = in_means[i]
quantity = count_in_labels[i]
colors.append(color)
proportions.append(quantity)
total_color += quantity
color_list = []
for i, color_LAB in enumerate(colors):
color_LAB = np.array([[[color_LAB[0], color_LAB[1], color_LAB[2]]]])
color_LAB = color_LAB.astype(np.uint8)
color = cv2.cvtColor(color_LAB, cv2.COLOR_Lab2BGR)[0][0]
color = color.tolist()
color[0], color[2] = color[2], color[0]
color = ','.join('%s' % id for id in color)
color_weight = round(proportions[i] / sum(proportions), 2)
color_list.append((color_weight, color, rgb2hex(color)))
color_list = sorted(color_list, key=lambda d: d[0], reverse=True)
e = time.time()
# print('识别',e-d)
return color_list
def BaiDu_image_recognize(file_path, recognize_type):
"""
图像识别
:param file_path: 文件路径
:param recognize_type: 识别类型，共12种：
1. 通用图像识别
2. 菜品识别
3. 车辆识别
4. logo商标识别
5. 动物识别
6. 植物识别
7. 图像主体检测
8. 地标识别
9. 食材识别
10. 红酒识别
11. 货币识别
:return:
"""
# TODO 隐私信息
""" 你的 APP_ID API_KEY SECRET_KEY """
app_id = '23899102' # '你的 App ID'
api_key = 'GKHIEq6gVOfp2AeRxfUopSDM' # '你的 Api Key'
secret_key = 'dLrlMlGemQ1oan2OS8GogLDD0dt1HuVI' # '你的 Secret Key'
# 获取百度云操作类对象
client = AipImageClassify(app_id, api_key, secret_key)
image = get_file_content(file_path)
# """ 调用通用物体识别 """
# result = client.dishDetect(image)
# print(result)
""" 如果有可选参数 """
options = {"baike_num": 5}
""" 带参数调用通用物体识别 """
if recognize_type == 1: # 通用图像识别
response = client.advancedGeneral(image, options)
elif recognize_type == 2: # 菜品识别
response = client.dishDetect(image, options)
elif recognize_type == 3: # 车辆识别
response = client.carDetect(image, options)
elif recognize_type == 4: # logo商标识别
response = client.logoSearch(image)
elif recognize_type == 5: # 动物识别
response = client.animalDetect(image, options)
elif recognize_type == 6: # 植物识别
response = client.plantDetect(image, options)
elif recognize_type == 7: # 图像主体检测
response = client.objectDetect(image)
elif recognize_type == 8: # 地标识别
response = client.landmark(image)
# 花卉识别已经移除
# elif recognize_type == 9: # 花卉识别
# response = client.flower(image)
elif recognize_type == 9: # 食材识别
response = client.ingredient(image, options)
elif recognize_type == 10: # 红酒识别
response = client.redwine(image)
elif recognize_type == 11: # 货币识别
response = client.currency(image)
else:
response = None
response = response['result'][0]
return response
from aip import AipImageClassify
""" 你的 APPID AK SK """
APP_ID = '15180965'
API_KEY = 'Gjw3RzhDcMSS8RESUEiVNWkH'
SECRET_KEY = 'pZVtDe5Z74cA2ropdsI3s3rGMrFmXH9N'
client = AipImageClassify(APP_ID, API_KEY, SECRET_KEY)
""" 读取图片 """
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()
image = get_file_content('images/1.jpg')
""" 调用图像主体检测 """
client.objectDetect(image)
""" 如果有可选参数 """
options = {}
options["with_face"] = 0
""" 带参数调用图像主体检测 """
response = client.objectDetect(image, options)
a = 1