def apply_algorithms(filename):
data = bf.load_image(filename) # load image
grey = an.get_grey_level_array(data) # grey-level array
text = an.get_texture_analysis(data) # texture analysis
shape = an.get_shape_analysis(data, False) # shape analysis
finalArray = {"grey": grey, "texture": text, "shape": shape}
return finalArray
def showOptions():
os.chdir(VALIDATION_SET_PATH)
validation_images = glob.glob("*.h5")
images = []
for image in validation_images:
image_data = bf.load_image(image)
images.append(image_data)
bf.show_images(images)
os.chdir(BACK_TO_ROOT_REF)
def searchQuery():
global TRAIN_DATA, CHECK_DATA
if not TRAIN_DATA:
if not fetchTrainData():
print("Could Not Search due to possible Network Error")
query_image_id = int(input("Enter Search Image Id: "))
os.chdir(VALIDATION_SET_PATH)
validation_images = glob.glob("*.h5")
source_image_name = validation_images[query_image_id]
source_image_data = bf.load_image(source_image_name)
sourceFinalArray = process.apply_algorithms(source_image_name)
os.chdir(BACK_TO_ROOT_REF)
match_image_name = compare(sourceFinalArray)
if CHECK_DATA == 1:
os.chdir(TRAIN_SET_PATH)
match_image_data = bf.load_image(match_image_name)
os.chdir(BACK_TO_ROOT_REF)
matchImageData = {'image': match_image_data, 'name': match_image_name}
sourceImageData = {
'image': source_image_data,
'name': source_image_name
}
bf.show_result(sourceImageData, matchImageData,
"Result by Original Algorithm")
elif CHECK_DATA == 0:
print("Best Match Image (By Original Algorithm): ", match_image_name)
match_image_name = compareNew(sourceFinalArray)
if CHECK_DATA == 1:
os.chdir(TRAIN_SET_PATH)
match_image_data = bf.load_image(match_image_name)
os.chdir(BACK_TO_ROOT_REF)
matchImageData = {'image': match_image_data, 'name': match_image_name}
sourceImageData = {
'image': source_image_data,
'name': source_image_name
}
bf.show_result(sourceImageData, matchImageData,
"Result by Improved Matching Algorithm")
elif CHECK_DATA == 0:
print("Best Match Image (By Improved Matching Algorithm): ",
match_image_name)
def main():
data = bf.load_image("test2.h5")
thres = np.quantile(data.ravel(), 0.65)
bindata = data // thres
op_selem = disk(6)
close_selem = disk(12)
opened = opening(bindata, op_selem)
closed = closing(opened, close_selem)
peri = perimeter(closed)
area = np.count_nonzero(closed == 1)
compact = 4 * np.pi * area / (peri**2)
print(peri, area, compact)
bf.show_images([data, bindata, opened, closed, canny(closed)])
def main():
parser = argparse.ArgumentParser(
description='Process Image through CloudNine Algorithm')
parser.add_argument("image_path",
metavar="image_path",
type=str,
help="Path to HDF5 Image to process as per algorithm")
args = parser.parse_args()
filename = args.image_path
data = bf.load_image(filename)
bf.get_image_information(filename)
bf.plot_hist_bin(data, 16)
grey = an.get_grey_level_array(data)
text = an.get_texture_analysis(data)
shape = an.get_shape_analysis(data, False)
#print(shape)
finalArray = {"grey": grey, "texture": text, "shape": shape}
print("Feature Array: ", finalArray)