def getViaSift():
img2 = cv2.cvtColor(getImageFromCam(), cv2.COLOR_BGR2GRAY) # trainImage
# Initiate SIFT detector
sift = cv2.xfeatures2d.SIFT_create()
# find the keypoints and descriptors with SIFT
kp2, des2 = sift.detectAndCompute(img2, None)
FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
mypath = 'imdata'
fileList = [
f for f in os.listdir(mypath)
if os.path.isfile(os.path.join(mypath, f))
]
for k in fileList:
img1 = cv2.imread(mypath + "/" + k, 0) # queryImage
kp1, des1 = sift.detectAndCompute(img1, None)
matches = flann.knnMatch(des1, des2, k=2)
# store all the good matches as per Lowe's ratio test.
good = []
for m, n in matches:
if m.distance < 0.7 * n.distance:
good.append(m)
if len(good) > MIN_MATCH_COUNT:
return k.split('_')[0]
return "Cannot Detect"
database_images = args.d
descriptor_file = args.l
load_descriptor = args.load
database_descriptors = {}
name_list = []
if load_descriptor == 'Y' or load_descriptor =='y':
print("Loading Pre Computed Descriptors")
assert os.path.exists(descriptor_file)
with open(descriptor_file, 'rb') as file:
database_descriptors = pickle.load(file)
else:
for image_name in tqdm(os.listdir(database_images)):
img = cv2.imread(database_images+image_name,0)
keypoint, descriptor = sift.detectAndCompute(img)
img_name,img_extension = os.path.splitext(image_name)
database_descriptors[img_name] = descriptor
name_list.append(img_name)
with open(descriptor_file, 'wb') as file:
pickle.dump(database_descriptors, file)
print("--Database Descriptors Loaded--")
correct_count = 0
for query_name in tqdm(os.listdir(query_images)):
max_count_name = None
max_count = 0
query = cv2.imread(query_images+query_name, 0)
GOOD_MATCH_THRESH = 10
descriptor_file = args.l
query_image = args.q
matches_track = None
database_image = None
distances_track = list()
with open(descriptor_file, 'rb') as file:
database_descriptors = pickle.load(file)
img_q = cv2.imread(query_image)
img_q_gray = cv2.imread(query_image, 0)
# using the SIFT algorithm to generate keypoints and descriptors
keypoints_1, descriptors_1 = sift.detectAndCompute(img_q_gray, verbose=True)
max_count = 0
for database_name in database_descriptors.keys():
d_desc = database_descriptors[database_name]
FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=100)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(descriptors_1, d_desc, k=2)
distances = list()
counts = list()
for i, (m, n) in enumerate(matches):
if m.distance < 0.7 * n.distance:
distances.append(m)
counts.append(len(distances))
if len(distances) != 0:
import cv2
import sift as sift
import pylab
img = cv2.imread('E:/Plots/myplot4.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
sift = cv2.xfeatures2d.SIFT_create()
(kps, descs) = sift.detectAndCompute(gray, None)
img1 = cv2.drawKeypoints(gray,
kps,
img,
flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imshow('SIFT_Algorithm', img1)
pylab.show()
surf = cv2.xfeatures2d.SURF_create()
(kps2, descs2) = surf.detectAndCompute(gray, None)
img2 = cv2.drawKeypoints(gray,
kps2,
img,
flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imshow('SURF_Algorithm', img2)
pylab.show()
fast = cv2.FastFeatureDetector_create()
kps3 = fast.detect(gray, None)
img3 = cv2.drawKeypoints(gray,
kps3,
img,
flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)