Train KNN classifier with several samples OpenCV Python
I am working on a logotype classifier/recognizer using Python 2.7.5 and OpenCV 2.4.8,
I have several images of the same logo but in different forms and presentations, I would like to train the classifier with that information and at the final recover the name of that logo regardless the form or presentation.
I would like to know how to train a KNN classifier using that information, I have the code that extracts the keypoints and descriptors using SURF, and I am storing that data directly on the hard disk.
def FeatureDetector(cvImage=None, filename=None):
template = dict()
hessian_threshold = 5000
if(filename is not None):
inputImage = cv.imread(filename)
if(cvImage is not None):
inputImage = cvImage
imageGray = cv.cvtColor(inputImage, cv.COLOR_BGR2GRAY)
detector = cv.SURF(hessian_threshold)
keypoints, descriptors = detector.detectAndCompute(imageGray, None, useProvidedKeypoints = False)
template["image"] = inputImage
template["array"] = imageGray
template["keypoints"] = keypoints
template["descriptors"] = descriptors
return template
def saveKeypoints(filename, keypoints):
kArray = []
for point in keypoints:
keypoint = (point.pt, point.size, point.angle, point.response, point.octave, point.class_id)
kArray.append(keypoint)
with open(filename, "wb") as outputFile:
pickle.dump(kArray, outputFile)
return
def detection(logoName, extension, show=False):
imagePath = PATHS["logos"] + logoName + "/"
if(os.path.exists(imagePath)):
count = 1
while(True):
filename = imagePath + str(count) + "." + extension
if(not os.path.exists(filename)):
print "[!] File '%s' not found, the end of sequence was reached"%(filename)
break
temp = FeatureDetector(filename = filename)
saveKeypoints(PATHS["keypoints"] + inputName + "/" + str(count) + ".kp", temp["keypoints"])
np.save(PATHS["descriptors"] + inputName + "/" + str(count) + ".npy", temp["descriptors"])
np.save(PATHS["arrays"] + inputName + "/" + str(count) + ".npy", temp["array"])
if(show):
showFeatures(filename, temp)
print "[O] Processed '%s'"%(filename)
count += 1
else:
print "[X] Logo not found\n"
return
Then, I have another script that load the data and trains the KNN but only with one form of a logo. I would like to train the classifier with all the forms of the logo, using all the keypoints and descriptors that I have and recover only one result.
def loadKeypoints(path):
keypoints = []
try:
with open(PATHS["keypoints"] + path + ".kp", "rb") as inputFile:
kArray = pickle.load(inputFile)
for point in kArray:
feature = cv.KeyPoint(
x=point[0][0],
y=point[0][1],
_size=point[1],
_angle=point[2],
_response=point[3],
_octave=point[4],
_class_id=point[5]
)
keypoints.append(feature)
except:
return False
return keypoints
def loadSURF():
global TEMPLATES, LOGOS
for logo in LOGOS:
TEMPLATES[logo] = list()
count = 1
while(True):
path = "%s/%d"%(logo, count)
keypoints = loadKeypoints(path)
if(not keypoints):
print "[!] Template for '%s' not found, the end of sequence was reached"%(path)
break
descriptors = np.load(PATHS["descriptors"] + path + ".npy")
array = np.load(PATHS["arrays"] + path + ".npy")
template = {
"keypoints": keypoints,
"descriptors": descriptors,
"array": array
}
print "[O] Template loaded from %s"%(path)
TEMPLATES[logo].append(template)
count += 1
return
def SURFCompare(temp, image):
samples = temp["descriptors"]
responses = np.arange(len(temp["keypoints"]), dtype=np.float32)
knn = cv.KNearest()
knn.train(samples, responses)
for template in TEMPLATES:
pattern = TEMPLATES[template]
for t in pattern:
for ...