sakshi's profile - activity

I have the (x,y) location of points in two images now I want to perform keypoint matching

but..how to implement it in python .?? Can u explain me how to compute the width of the stroke ?

how to find the stroke width transform of an image using opencv (python).

hmm... is there something in opencv to detect facial keypoints?

How to use dlib library in python to detects facial keypoints in an image???

is there something in python also? or could u explain me the approach?

the mask which i want to create can be of some specific region of the image , For example

this is the image from which i want create mask of the face of cat( i.e including eyes , nose , mouth ) or like if i want to create the mask only for the ears i want to create mask for :

the mask :

how to select the region and create mask??

I have used RANSAC algorithm to find the homography and wrap perspective operation to apply it to an image. here is the code

MIN_MATCH_COUNT = 10
img1 = cv2.imread('bus1.jpg',0)
img2 = cv2.imread('bus2.jpg',0)
sift = cv2.SIFT()

kp1, des1 = sift.detectAndCompute(img1,None)
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)
matches = flann.knnMatch(des1,des2,k=2)

good = []
for m,n in matches:
if m.distance < 0.7*n.distance:
    good.append(m)

if len(good)>MIN_MATCH_COUNT:

  src_pts = np.float32([ kp1[m.queryIdx].pt for m in good ]).reshape(-1,1,2)
  dst_pts = np.float32([ kp2[m.trainIdx].pt for m in good ]).reshape(-1,1,2)

  M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC,5.0)
  h,w = img1.shape

  result=cv2.warpPerspective(img2,M,(w,h))

cv2.imshow('result',result)
cv2.waitKey(0)
cv2.destroyAllWindows()

the input images are

bus1.jpg bus2.jpg the output image is

it is not showing the whole image .what is wrong??