def apply_filter(self, image, grayscale=False):
"""
Apply the DFT filter to given image.
:param image: PhloxAR.Image
:param grayscale: if True, perform the operation on the gray version
of the image, if False, perform the operation on
each channel and the recombine then to create
the result.
:return: filtered image.
"""
if self.width == 0 or self.height == 0:
warnings.warn("Empty filter. Returning the image.")
return image
w, h = image.size()
if grayscale:
image = image.to_gray()
img = self._image
if img.size() != image.size():
img = img.resize(w, h)
filtered = image.apply_DFT_filter(img)
return filtered
def __add__(self, other):
if not isinstance(other, type(self)):
warnings.warn("Provide PhloxAR.DFT object.")
return None
if self.size() != other.size():
warnings.warn("Both PhloxAR.DFT object mush have the same size.")
return None
numpy_array = self._narray + other._narray
image = PhloxAR.core.image.Image(numpy_array)
ret = DFT(array=numpy_array, image=image, size=image.size())
return ret
def predict(self, image):
"""
**SUMMARY**
Predict the class of the image using trained face recognizer.
**PARAMETERS**
* *image* - Image.The images must be of the same size as provided
in training.
**RETURNS**
* *label* - Class of the image which it belongs to.
**EXAMPLES**
>>> f = FaceRecognizer()
>>> imgs1 = ImageSet(path/to/images_of_type1)
>>> labels1 = ["type1"]*len(imgs1)
>>> imgs2 = ImageSet(path/to/images_of_type2)
>>> labels2 = ["type2"]*len(imgs2)
>>> imgs3 = ImageSet(path/to/images_of_type3)
>>> labels3 = ["type3"]*len(imgs3)
>>> imgs = imgs1 + imgs2 + imgs3
>>> labels = labels1 + labels2 + labels3
>>> f.train(imgs, labels)
>>> img = Image("some_image_of_any_of_the_above_type")
>>> print f.predict(img)
Save Fisher Training Data
>>> f.save("trainingdata.xml")
Load Fisher Training Data and directly use without trainging
>>> f1 = FaceRecognizer()
>>> f1.load("trainingdata.xml")
>>> img = Image("some_image_of_any_of_the_above_type")
>>> print f1.predict(img)
Use CSV files for training
>>> f = FaceRecognizer()
>>> f.train(csvfile="CSV_file_name", delimiter=";")
>>> img = Image("some_image_of_any_of_the_type_in_csv_file")
>>> print f.predict(img)
"""
if not self.supported:
warnings.warn("Fisher Recognizer is supported by OpenCV >= 2.4.4")
return None
if image.size() != self.imageSize:
w, h = self.imageSize
image = image.resize(w, h)
cv2img = image.getGrayNumpyCv2()
label, confidence = self.model.predict(cv2img)
retLabel = self.labels_dict_rev.get(label)
if not retLabel:
retLabel = label
return retLabel, confidence
