def memfunc():
# Note: these files default to notre dame, unless otherwise specified
image1_file = "../data/NotreDame/NotreDame1.jpg"
image2_file = "../data/NotreDame/NotreDame2.jpg"
eval_file = "../data/NotreDame/NotreDameEval.mat"
scale_factor = 0.5
feature_width = 16
image1 = img_as_float32(
rescale(rgb2gray(io.imread(image1_file)), scale_factor))
image2 = img_as_float32(
rescale(rgb2gray(io.imread(image2_file)), scale_factor))
(x1, y1) = student.get_interest_points(image1, feature_width)
(x2, y2) = student.get_interest_points(image2, feature_width)
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
matches, confidences = student.match_features(image1_features,
image2_features)
evaluate_correspondence(image1, image2, eval_file, scale_factor, x1, y1,
x2, y2, matches, confidences, 0)
def memfunc():
# Note: these files default to notre dame, unless otherwise specified
# image1_file = "../data/NotreDame/NotreDame1.jpg"
# image2_file = "../data/NotreDame/NotreDame2.jpg"
#eval_file = "../data/NotreDame/NotreDameEval.mat"
image1_file = "../data/EpiscopalGaudi/EGaudi_1.jpg"
image2_file = "../data/EpiscopalGaudi/EGaudi_1.jpg"
eval_file = "../data/EpiscopalGaudi/EGaudiEval.mat"
#image1_file = "../data/MountRushmore/Mount_Rushmore1.jpg"
#image2_file = "../data/MountRushmore/Mount_Rushmore2.jpg"
#eval_file = "../data/MountRushmore/MountRushmoreEval.mat"
scale_factor = 0.5
feature_width = 16
image1 = img_as_float32(
rescale(rgb2gray(io.imread(image1_file)), scale_factor))
image2 = img_as_float32(
rescale(rgb2gray(io.imread(image2_file)), scale_factor))
(x1, y1) = student.get_interest_points(image1, feature_width, 0.4, 0.06, 0,
0, 0, 400)
(x2, y2) = student.get_interest_points(image2, feature_width, 5, 0.06, 0,
0, 0, 500)
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
matches, confidences = student.match_features(image1_features,
image2_features)
evaluate_correspondence(image1, image2, eval_file, scale_factor, x1, y1,
x2, y2, matches, confidences, 0)
def find_matches(student, image1, image2, eval_file):
(x1, y1) = student.get_interest_points(image1, feature_width)
(x2, y2) = student.get_interest_points(image2, feature_width)
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
matches, confidences = student.match_features(image1_features,
image2_features)
return x1, y1, x2, y2, matches, confidences
def main():
"""
Reads in the data,
Command line usage: python main.py -p | --pair <image pair name>
-p | --pair - flag - required. specifies which image pair to match
"""
# create the command line parser
parser = argparse.ArgumentParser()
parser.add_argument(
"-p",
"--pair",
required=True,
help=
"Either notre_dame, mt_rushmore, or e_gaudi. Specifies which image pair to match"
)
args = parser.parse_args()
print(args)
# (1) Load in the data
image1_color, image2_color, eval_file = load_data(args.pair)
# You don't have to work with grayscale images. Matching with color
# information might be helpful. If you choose to work with RGB images, just
# comment these two lines
image1 = rgb2gray(image1_color)
# Our own rgb2gray coefficients which match Rec.ITU-R BT.601-7 (NTSC) luminance conversion - only mino
# performance improvements and could be confusing to students image1 = image1[:,:,0] * 0.2989 + image1[:,:,
# 1] * 0.5870 + image1[:,:,2] * 0.1140
image2 = rgb2gray(image2_color)
# image2 = image2[:,:,0] * 0.2989 + image2[:,:,1] * 0.5870 + image2[:,:,2] * 0.1140
# make images smaller to speed up the algorithm. This parameter
# gets passed into the evaluation code, so don't resize the images
# except for changing this parameter - We will evaluate your code using
# scale_factor = 0.5, so be aware of this
scale_factor = 0.5
# Bilinear rescaling
image1 = np.float32(rescale(image1, scale_factor))
image2 = np.float32(rescale(image2, scale_factor))
# width and height of each local feature, in pixels
feature_width = 16
# (2) Find distinctive points in each image. See Szeliski 4.1.1
# !!! You will need to implement get_interest_points. !!!
print("Getting interest points...")
(x1, y1) = student.get_interest_points(image1, feature_width, 2, 0.06)
(x2, y2) = student.get_interest_points(image2, feature_width, 2.5, 0.06)
# For development and debugging get_features and match_features, you will likely
# want to use the ta ground truth points, you can comment out the preceding two
# lines and uncomment the following line to do this. Note that the ground truth
# points for mt. rushmore will not produce good results, so you'll have to use
# your own function for that image pair.
# (x1, y1, x2, y2) = cheat_interest_points(eval_file, scale_factor)
# if you want to view your corners uncomment these next lines!
plt.imshow(image1, cmap="gray")
plt.scatter(x1, y1, s=20, facecolors='none', edgecolors='b')
plt.scatter(x1, y1, alpha=0.5, s=0.5)
plt.show()
plt.imshow(image2, cmap="gray")
plt.scatter(x2, y2, alpha=0.9, s=3)
plt.show()
print("Done!")
# 3) Create feature vectors at each interest point. Szeliski 4.1.2
# !!! You will need to implement get_features. !!!
print("Getting features...")
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
print("Done!")
# 4) Match features. Szeliski 4.1.3
# !!! You will need to implement match_features !!!
print("Matching features...")
matches, confidences = student.match_features(image1_features,
image2_features)
print("Done!")
# 5) Evaluation and visualization
# The last thing to do is to check how your code performs on the image pairs
# we've provided. The evaluate_correspondence function below will print out
# the accuracy of your feature matching for your 50 most confident matches,
# 100 most confident matches, and all your matches. It will then visualize
# the matches by drawing green lines between points for correct matches and
# red lines for incorrect matches. The visualizer will show the top
# num_pts_to_visualize most confident matches, so feel free to change the
# parameter to whatever you like.
print("Matches: " + str(matches.shape[0]))
num_pts_to_visualize = 50
evaluate_correspondence(image1_color, image2_color, eval_file,
scale_factor, x1, y1, x2, y2, matches, confidences,
num_pts_to_visualize, args.pair + '_matches.jpg')
def main():
"""
Reads in the data,
Command line usage: python main.py [-a | --average_accuracy] -p | --pair <image pair name>
-a | --average_accuracy - flag - if specified, will compute your solution's
average accuracy on the (1) notre dame, (2) mt. rushmore, and (3) episcopal
guadi image pairs
-p | --pair - flag - required. specifies which image pair to match
"""
# create the command line parser
parser = argparse.ArgumentParser()
parser.add_argument(
"-a",
"--average_accuracy",
help=
"Include this flag to compute the average accuracy of your matching.")
parser.add_argument(
"-p",
"--pair",
required=True,
help=
"Either notre_dame, mt_rushmore, or e_gaudi. Specifies which image pair to match"
)
args = parser.parse_args()
# (1) Load in the data
image1, image2, eval_file = load_data(args.pair)
# You don't have to work with grayscale images. Matching with color
# information might be helpful. If you choose to work with RGB images, just
# comment these two lines
image1 = rgb2gray(image1)
image2 = rgb2gray(image2)
# make images smaller to speed up the algorithm. This parameter
# gets passed into the evaluation code, so don't resize the images
# except for changing this parameter - We will evaluate your code using
# scale_factor = 0.5, so be aware of this
scale_factor = 0.5
# Bilinear rescaling
image1 = np.float32(rescale(image1, scale_factor))
image2 = np.float32(rescale(image2, scale_factor))
# width and height of each local feature, in pixels
feature_width = 16
# (2) Find distinctive points in each image. See Szeliski 4.1.1
# !!! You will need to implement get_interest_points. !!!
print("Getting interest points...")
# For development and debugging get_features and match_features, you will likely
# want to use the ta ground truth points, you can comment out the precedeing two
# lines and uncomment the following line to do this.
#(x1, y1, x2, y2) = cheat_interest_points(eval_file, scale_factor)
(x1, y1) = student.get_interest_points(image1, feature_width)
(x2, y2) = student.get_interest_points(image2, feature_width)
# if you want to view your corners uncomment these next lines!
# plt.imshow(image1, cmap="gray")
# plt.scatter(x1, y1, alpha=0.9, s=3)
# plt.show()
# plt.imshow(image2, cmap="gray")
# plt.scatter(x2, y2, alpha=0.9, s=3)
# plt.show()
print("Done!")
# 3) Create feature vectors at each interest point. Szeliski 4.1.2
# !!! You will need to implement get_features. !!!
print("Getting features...")
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
print("Done!")
# 4) Match features. Szeliski 4.1.3
# !!! You will need to implement match_features !!!
print("Matching features...")
matches, confidences = student.match_features(image1_features,
image2_features)
if len(matches.shape) == 1:
print("No matches!")
return
print("Done!")
# 5) Visualization
# You might want to do some preprocessing of your interest points and matches
# before visualizing (e.g. only visualizing 100 interest points). Once you
# start detecting hundreds of interest points, the visualization can become
# crowded. You may also want to threshold based on confidence
# visualize.show_correspondences produces a figure that shows your matches
# overlayed on the image pairs. evaluate_correspondence computes some statistics
# about the quality of your matches, then shows the same figure. If you want to
# just see the figure, you can uncomment the function call to visualize.show_correspondences
num_pts_to_visualize = matches.shape[0]
print("Matches: " + str(num_pts_to_visualize))
# visualize.show_correspondences(image1, image2, x1, y1, x2, y2, matches, filename=args.pair + "_matches.jpg")
## 6) Evaluation
# This evaluation function will only work for the Notre Dame, Episcopal
# Gaudi, and Mount Rushmore image pairs. Comment out this function if you
# are not testing on those image pairs. Only those pairs have ground truth
# available.
#
# It also only evaluates your top 100 matches by the confidences
# that you provide.
#
# Within evaluate_correspondences(), we sort your matches in descending order
#
num_pts_to_evaluate = matches.shape[0]
evaluate_correspondence(image1, image2, eval_file, scale_factor, x1, y1,
x2, y2, matches, confidences, num_pts_to_visualize)
return
def main():
"""
Reads in the data,
Command line usage: python main.py -p | --pair <image pair name>
-p | --pair - flag - required. specifies which image pair to match
"""
# create the command line parser
parser = argparse.ArgumentParser()
parser.add_argument(
"-p",
"--pair",
required=True,
help=
"Either notre_dame, mt_rushmore, or e_gaudi. Specifies which image pair to match"
)
args = parser.parse_args()
# (1) Load in the data
image1_color, image2_color, eval_file = load_data(args.pair)
# Let's work with grayscale images.
image1 = rgb2gray(image1_color)
image2 = rgb2gray(image2_color)
# make images smaller to speed up the algorithm. This parameter
# gets passed into the evaluation code, so don't resize the images
# except for changing this parameter - We will evaluate your code using
# scale_factor = 0.5, so be aware of this
scale_factor = 0.5
# Bilinear rescaling
image1 = np.float32(rescale(image1, scale_factor))
image2 = np.float32(rescale(image2, scale_factor))
# width and height of each local feature, in pixels
feature_width = 16
# (2) Find distinctive points in each image. See Szeliski 4.1.1
# !!! You will need to implement get_interest_points. !!!
print("Getting interest points...")
(x1, y1) = student.get_interest_points(image1, feature_width)
(x2, y2) = student.get_interest_points(image2, feature_width)
# For development and debugging you can compare with the ta ground truth points
# by uncommenting the following lines.
# Note that the ground truth points for mt. rushmore will not produce good results.
# (x1, y1, x2, y2) = cheat_interest_points(eval_file, scale_factor)
# view your corners!
plt.imshow(image1, cmap="gray")
plt.scatter(x1, y1, alpha=0.9, s=3)
plt.show()
plt.imshow(image2, cmap="gray")
plt.scatter(x2, y2, alpha=0.9, s=3)
plt.show()
print("Done!")
"""
##### FOR NEXT ASSIGNMENT ... #####
# 3) Create feature vectors at each interest point. Szeliski 4.1.2
# !!! You will need to implement get_features. !!!
print("Getting features...")
image1_features = student.get_features(image1, x1, y1, feature_width)
image2_features = student.get_features(image2, x2, y2, feature_width)
print("Done!")
# 4) Match features. Szeliski 4.1.3
# !!! You will need to implement match_features !!!
print("Matching features...")
matches, confidences = student.match_features(image1_features, image2_features)
print("Done!")
# 5) Evaluation and visualization
# The last thing to do is to check how your code performs on the image pairs
# we've provided. The evaluate_correspondence function below will print out
# the accuracy of your feature matching for your 50 most confident matches,
# 100 most confident matches, and all your matches. It will then visualize
# the matches by drawing green lines between points for correct matches and
# red lines for incorrect matches. The visualizer will show the top
# num_pts_to_visualize most confident matches, so feel free to change the
# parameter to whatever you like.
print("Matches: " + str(matches.shape[0]))
num_pts_to_visualize = 50
evaluate_correspondence(image1_color, image2_color, eval_file, scale_factor,
x1, y1, x2, y2, matches, confidences, num_pts_to_visualize, args.pair + '_matches.jpg')
"""
return