def __init__(self, *args, **kwargs):
super(TestHistClassifier, self).__init__(*args, **kwargs)
self.classifier = HistogramColorClassifier(
channels=[0, 1, 2],
hist_size=[128, 128, 128],
hist_range=[0, 256, 0, 256, 0, 256],
hist_type='BGR')
BASE_PATH = "Data/Color_Classification/model_"
models = []
self.names = [
"Flash", "Batman", "Hulk", "Superman", "Captain America",
"Wonder Woman", "Iron Man", "Wolverine"
]
for i in range(1, 9):
models.append(cv2.imread(BASE_PATH + str(i) + '.png'))
for model, name in zip(models, self.names):
self.classifier.addModelHistogram(model, name=name)
self.test_image = cv2.imread('Data/Color_Classification/image_2.jpg')
def determineFanType():
classifier = HistogramColorClassifier(channels=[0, 1, 2],
hist_size=[128, 128, 128],
hist_range=[0, 256, 0, 256, 0, 256],
hist_type='BGR')
bif_model = cv2.imread('./data/bif/REFERENCE.jpg')
classifier.addModelHistogram(bif_model)
fck_model = cv2.imread('./data/fck/REFERENCE.jpg')
classifier.addModelHistogram(fck_model)
path = input("Please enter the path of the image you want to check: ")
filecheck = Path(path)
if filecheck.is_file():
resize(path)
image = cv2.imread(path)
result = classifier.returnHistogramComparisonArray(
image, method="intersection")
if result[0] > result[1]:
print("Picture is most likely of a BIF fan.")
elif result[0] < result[1]:
print("Picture is most likely of an FCK fan.")
else:
print("Cant determine fan type. Try a different picture")
showResultGraph(2, 'BIF', 'FCK', result)
else:
print(
"File dosent exist. Run the file again and try a different path.")
def learn_object_from_folder(images_folder, image_extension='jpg'):
'''Given a folder with images of objects on uniform background
and different colours fingerprints, it associate the colours
to the object name.
The folder must contain images named:
1_firstobjectname.jpg, 2_secondobjectname.jpg, ...
When username=None the object is associated
with an empty object and not used.
'''
my_classifier = HistogramColorClassifier(channels=[0, 1, 2],
hist_size=[128, 128, 128],
hist_range=[0, 256, 0, 256, 0, 256],
hist_type='BGR')
for filename in os.listdir(images_folder):
if filename.endswith(image_extension):
model = cv2.imread(filename)
my_classifier.addModelHistogram(model)
return my_classifier
def __init__(self, icub_root='/icubSim'):
# Global variables
self.thread_movement_detection = threading.Thread(target=None)
self.acapela_account_login = ''
self.acapela_application_login = ''
self.acapela_application_password = ''
self.acapela_service_url = ''
# Deepgaze variables
self.object_list = list()
self.histogram_classifier = HistogramColorClassifier(
channels=[0, 1, 2],
hist_size=[128, 128, 128],
hist_range=[0, 256, 0, 256, 0, 256],
hist_type='BGR')
# Init YARP
yarp.Network.init()
# Camera connection
try:
cam_w = 320 # 640
cam_h = 240 # 480
# Left camera
print("[ICUB] Init: Waiting for " + icub_root + "/cam/left' ...")
self.port_left_camera = yarp.Port()
self.port_left_camera.open("/pyera-left-image-port")
yarp.Network.connect(icub_root + "/cam/left",
"/pyera-left-image-port")
# right camera
print("[ICUB] Init: Waiting for " + icub_root + "/cam/right' ...")
self.port_right_camera = yarp.Port()
self.port_right_camera.open("/pyera-right-image-port")
yarp.Network.connect(icub_root + "/cam/right",
"/pyera-right-image-port")
# Set the numpy array to fill with the image
self.img_array = np.zeros((cam_h, cam_w, 3), dtype=np.uint8)
self.yarp_image = yarp.ImageRgb()
self.yarp_image.resize(cam_w, cam_h)
self.yarp_image.setExternal(self.img_array,
self.img_array.shape[1],
self.img_array.shape[0])
except BaseException, err:
print("[ICUB][ERROR] connect To Camera catching error " + str(err))
return
#MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
#CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
#SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#In this example the histogram intersection algorithm is used in order
#to classify eight different superheroes. The histogram intersection is
#one of the simplest classifier and it uses histograms as
#comparison to identify the best match between an input image and a model.
import cv2
import numpy as np
from matplotlib import pyplot as plt
from deepgaze.color_classification import HistogramColorClassifier
#Defining the classifier
my_classifier = HistogramColorClassifier(channels=[0, 1, 2], hist_size=[128, 128, 128], hist_range=[0, 256, 0, 256, 0, 256], hist_type='BGR')
model_1 = cv2.imread('model_1.png') #Flash
model_2 = cv2.imread('model_2.png') #Batman
model_3 = cv2.imread('model_3.png') #Hulk
model_4 = cv2.imread('model_4.png') #Superman
model_5 = cv2.imread('model_5.png') #Capt. America
model_6 = cv2.imread('model_6.png') #Wonder Woman
model_7 = cv2.imread('model_7.png') #Iron Man
model_8 = cv2.imread('model_8.png') #Wolverine
#model_9 = cv2.imread('model_9_c.png') #Thor
#model_10 = cv2.imread('model_10_c.png') #Magneto
my_classifier.addModelHistogram(model_1)
my_classifier.addModelHistogram(model_2)
my_classifier.addModelHistogram(model_3)
class TestHistClassifier(unittest.TestCase):
"""Test cases to ensure color classification with Histogram Color Classifier works as expected"""
def __init__(self, *args, **kwargs):
super(TestHistClassifier, self).__init__(*args, **kwargs)
self.classifier = HistogramColorClassifier(
channels=[0, 1, 2],
hist_size=[128, 128, 128],
hist_range=[0, 256, 0, 256, 0, 256],
hist_type='BGR')
BASE_PATH = "Data/Color_Classification/model_"
models = []
self.names = [
"Flash", "Batman", "Hulk", "Superman", "Captain America",
"Wonder Woman", "Iron Man", "Wolverine"
]
for i in range(1, 9):
models.append(cv2.imread(BASE_PATH + str(i) + '.png'))
for model, name in zip(models, self.names):
self.classifier.addModelHistogram(model, name=name)
self.test_image = cv2.imread('Data/Color_Classification/image_2.jpg')
def test_ComparisonArray(self):
expected_comparison = [
0.00818883, 0.55411926, 0.12405966, 0.07735263, 0.34388389,
0.12672027, 0.09870308, 0.2225694
]
#expected_name=['Flash', 'Batman', 'Hulk', 'Superman', 'Captain America', 'Wonder Woman', 'Iron Man', 'Wolverine']
comparison_array = self.classifier.returnHistogramComparisonArray(
self.test_image, method="intersection")
assert np.allclose(comparison_array, expected_comparison)
def test_Names(self):
expected_name = [
'Flash', 'Batman', 'Hulk', 'Superman', 'Captain America',
'Wonder Woman', 'Iron Man', 'Wolverine'
]
assert self.classifier.returnNameList() == expected_name
def test_BestMatchIndex(self):
assert self.classifier.returnBestMatchIndex(self.test_image) == 1
def test_BestMatchName(self):
assert self.classifier.returnBestMatchName(self.test_image) == 'Batman'
def test_Cache(self):
expected_name = [
'Flash', 'Batman', 'Hulk', 'Superman', 'Captain America',
'Wonder Woman', 'Iron Man', 'Wolverine'
]
self.classifier.returnHistogramComparisonArray(self.test_image,
method="intersection")
assert self.classifier.returnNameList() == expected_name
assert self.classifier.returnBestMatchIndex() == 1
assert self.classifier.returnBestMatchName() == 'Batman'
#MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
#CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
#SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#In this example the histogram intersection algorithm is used in order
#to classify eight different superheroes. The histogram intersection is
#one of the simplest classifier and it uses histograms as
#comparison to identify the best match between an input image and a model.
import cv2
import numpy as np
from matplotlib import pyplot as plt
from deepgaze.color_classification import HistogramColorClassifier
#Defining the classifier
my_classifier = HistogramColorClassifier(channels=[0, 1, 2], hist_size=[128, 128, 128], hist_range=[0, 256, 0, 256, 0, 256], hist_type='BGR')
model_1 = cv2.imread('model_1.png') #Flash
model_2 = cv2.imread('model_2.png') #Batman
model_3 = cv2.imread('model_3.png') #Hulk
model_4 = cv2.imread('model_4.png') #Superman
model_5 = cv2.imread('model_5.png') #Capt. America
model_6 = cv2.imread('model_6.png') #Wonder Woman
model_7 = cv2.imread('model_7.png') #Iron Man
model_8 = cv2.imread('model_8.png') #Wolverine
#model_9 = cv2.imread('model_9_c.png') #Thor
#model_10 = cv2.imread('model_10_c.png') #Magneto
my_classifier.addModelHistogram(model_1)
my_classifier.addModelHistogram(model_2)
my_classifier.addModelHistogram(model_3)