def fft_display(im, videoFilename=None):
rows = im.shape[0]
cols = im.shape[1]
template = np.zeros((rows, cols))
# Generates the FFt
FFT = np.fft.fft2(im)
FFT = np.fft.fftshift(FFT)
logFFT = np.log10(np.abs(FFT))
logFFT = (logFFT/np.max(logFFT)) * 255
# Creates array to poulate with max values
maxValues = np.flipud(np.argsort(logFFT.flatten()))
used = template.copy()
current = template.copy()
scaled = template.copy()
summed = template.copy()
# creates writer and image window
cv2.namedWindow(videoFilename)
writer = video_writer(im.shape,videoFilename)
for i in maxValues:
# puts freq into used array
used.flat[i] = logFFT.flat[i]
# returns spatial sine wave for freq
template.flat[i] = logFFT.flat[i]
current = np.fft.ifft2(template)
template.flat[i] = 0
#scales the current array and sums all freqs
scaled = ((current - np.min(current))/ np.max(current)) *255
summed = summed + current
# stitching all images together
frame = stitch(im,logFFT,used,current,scaled,summed)
if writer.isOpened():
writer.write(frame)
# shows the image
cv2.imshow(videoFilename,frame)
action = ipcv.flush()
if action == "pause":
action = ipcv.flush()
if action == "pause":
continue
elif action == "exit":
writer.release()
sys.exit()
def dft2(f, scale=True, method='break', verbose=False):
#initialize variables
shape = f.shape
j = complex(0, 1)
e = math.exp(1)
M = shape[0]
N = shape[1]
pi = math.pi
f_x_y = numpy.zeros((shape), dtype=numpy.complex128)
dst = numpy.zeros(shape, dtype=numpy.complex128)
# checkerboard image to center
for x in range(0, shape[0]):
for y in range(0, shape[1]):
f[x, y] = f[x, y] * pow(-1, (x + y))
#now compute fourier transform
if method == 'together': #discrete, four-loop method
for u in range(0, shape[0]):
for v in range(0, shape[1]):
for x in range(0, shape[0]):
for y in range(0, shape[1]):
f_x_y[x, y] = f[x, y] * (e**(-j * 2 * pi *
(((u * x) / M) +
((v * y) / N))))
if scale == True:
dst[u, v] = sum(sum(f_x_y)) / (M * N)
else:
dst[u, v] = sum(sum(f_x_y))
if method == 'break': #modified, less computationally-heavy method
f_x_v = numpy.zeros(shape, dtype=numpy.complex128)
for x in range(
0, M
): #use DFT algorithm twice, computing rows first, then columns.
f_x_v[x, :] = dft(f[x, :], scale=scale, shift=False, verbose=False)
for y in range(0, N):
dst[:, y] = dft(f_x_v[:, y],
scale=scale,
shift=False,
verbose=False)
# Optional display method
if verbose == True:
f_complex = dst[:, :] + 1j * dst[:, :]
f_abs = numpy.abs(f_complex) + 1 # lie between 1 and 1e6
f_bounded = 20 * numpy.log(f_abs)
f_img = 255 * f_bounded / numpy.max(f_bounded)
f_img = f_img.astype(numpy.uint8)
cv2.imshow('F(z) of Source Image', f_img)
ipcv.flush()
return dst
else:
return dst
def otsu_threshold(im, maxCount=255, verbose=False):
hist = cv2.calcHist([im], [0], None, [maxCount+1], [0, maxCount+1])
firstIndex = np.min(im)
lastIndex = np.max(im)
print(firstIndex)
print(lastIndex)
r = np.zeros(maxCount+1)
for i in range(65, 206):
threshold = np.argmax(r)
threshIm = np.ones(np.shape(im))
threshIm = threshIm * im
np.place(threshIm, im < threshold, 0)
np.place(threshIm, im >= threshold, 1)
return (threshIm, threshold)
if __name__ == '__main__':
import cv2
import ipcv
import os.path
import time
home = os.path.expanduser('~')
filename = home + os.path.sep + 'src/python/examples/data/giza.jpg'
im = cv2.imread(filename, cv2.IMREAD_UNCHANGED)
print('Filename = {0}'.format(filename))
print('Data type = {0}'.format(type(im)))
print('Image shape = {0}'.format(im.shape))
print('Image size = {0}'.format(im.size))
startTime = time.time()
thresholdedImage, threshold = ipcv.otsu_threshold(im, verbose=True)
print('Elapsed time = {0} [s]'.format(time.time() - startTime))
print('Threshold = {0}'.format(threshold))
cv2.namedWindow(filename, cv2.WINDOW_AUTOSIZE)
cv2.imshow(filename, im)
cv2.namedWindow(filename + ' (Thresholded)', cv2.WINDOW_AUTOSIZE)
cv2.imshow(filename + ' (Thresholded)', thresholdedImage * 255)
action = ipcv.flush()
def display(img,name='test'): cv2.namedWindow(name,cv2.WINDOW_AUTOSIZE) cv2.imshow(name,img) ipcv.flush()
maxCount = numpy.max(blankSheet)
if (numRowsB-numColsB) % 2 != 0:
blankSheet = numpy.pad(blankSheet, ((0,0),(pad1,pad1+1)), 'constant', constant_values=((maxCount, maxCount),(maxCount,maxCount)))
elif (numRowsA-numColsA) % 2 == 0:
blankSheet = numpy.pad(blankSheet, ((0,0),(pad1,pad1)), 'constant', constant_values=((maxCount, maxCount),(maxCount,maxCount)))
return answerSheet, blankSheet
if __name__ == '__main__':
#answerSheet1 = cv2.imread('gray0001.tif')
answerSheet1 = cv2.imread('black0007.tif')
#############FOR HIGH RES##############
#blankSheet1 = cv2.imread('original300dpi.tif')
#############FOR LOW RES##############
blankSheet1 = cv2.imread('original.tif')
answerSheet, blankSheet = paddingAnswers(answerSheet1, blankSheet1)
'''
cv2.namedWindow('Fiducial1 Padded', cv2.WINDOW_AUTOSIZE)
cv2.imshow('Fiducial1 Padded', fiducial1.astype(numpy.uint8))
cv2.waitKey()
cv2.namedWindow('Answer Sheet', cv2.WINDOW_AUTOSIZE)
cv2.imshow('Answer Sheet', fiducial3)
cv2.imwrite('fiducial1.tif', fiducial1)
cv2.imwrite('fiducial2.tif', fiducial2)
cv2.imwrite('fiducial3.tif', fiducial3)
cv2.imwrite('answerSheet1.tif', answerSheet)
'''
action = ipcv.flush()
import time
home = os.path.expanduser('~')
filename = home + os.path.sep + 'src/python/examples/data/crowd.jpg'
filename = home + os.path.sep + 'src/python/examples/data/lenna.tif'
#filename = home + os.path.sep + 'src/python/examples/data/redhat.ppm'
#filename = home + os.path.sep + 'src/python/examples/data/lenna_color.tif'
src = cv2.imread(filename)
map1, map2 = ipcv.map_rotation_scale(src, rotation=30, scale=[1.3, 0.8])
startTime = time.clock()
dst = ipcv.remap(src,
map1,
map2,
interpolation=ipcv.INTER_NEAREST,
borderMode=ipcv.BORDER_CONSTANT,
borderValue=0)
elapsedTime = time.clock() - startTime
print('Elapsed time (remap) = {0} [s]'.format(elapsedTime))
srcName = 'Source (' + filename + ')'
cv2.namedWindow(srcName, cv2.WINDOW_AUTOSIZE)
cv2.imshow(srcName, src)
dstName = 'Destination (' + filename + ')'
cv2.namedWindow(dstName, cv2.WINDOW_AUTOSIZE)
cv2.imshow(dstName, dst)
ipcv.flush()
home = os.path.expanduser('~')
filename = home + os.path.sep + 'src/python/examples/data/redhat.ppm'
filename = home + os.path.sep + 'src/python/examples/data/crowd.jpg'
filename = home + os.path.sep + 'src/python/examples/data/checkerboard.tif'
filename = home + os.path.sep + 'src/python/examples/data/lenna.tif'
src = cv2.imread(filename, cv2.IMREAD_UNCHANGED)
dstDepth = ipcv.IPCV_8U
#kernel = numpy.asarray([[-1,-1,-1],[-1,9,-1],[-1,-1,-1]])
# offset = 0
# kernel = numpy.asarray([[-1,-1,-1],[-1,8,-1],[-1,-1,-1]])
# offset = 128
# kernel = numpy.ones((15,15))
# offset = 0
kernel = numpy.asarray([[1, 1, 1], [1, 1, 1], [1, 1, 1]])
offset = 0
startTime = time.time()
dst = ipcv.filter2D(src, dstDepth, kernel, delta=offset)
print('Elapsed time = {0} [s]'.format(time.time() - startTime))
cv2.namedWindow(filename, cv2.WINDOW_AUTOSIZE)
cv2.imshow(filename, src)
cv2.namedWindow(filename + ' (Filtered)', cv2.WINDOW_AUTOSIZE)
cv2.imshow(filename + ' (Filtered)', dst)
action = ipcv.flush()
def fft_display(img, videoFilename=None):
try:
img = img.copy()
dims = ipcv.dimensions(img)
r, c = dims["rows"], dims["cols"]
temp = np.zeros((r, c))
# generating FFT
# FFT = np.fft.fftshift(np.fft.fft(img))
# FFT = np.fft.fftshift( np.fft.fft2(img) )
# logFFT = np.log( np.abs( FFT / np.sqrt(FFT.size) ) ).astype(ipcv.IPCV_8U)
FFT = np.fft.fft2(img)
# print("AVERAGE VALUE IS EQUAL TO:",FFT.flat[0])
FFT = np.fft.fftshift(FFT)
FFT = np.abs(FFT)
logFFT = np.log10(FFT)
logFFT = (logFFT / np.max(logFFT)) * 255
print("MAX IS EQUAL TO:", np.max(logFFT))
print("MIN IS EQUAL TO:", np.min(logFFT))
# creating array to poulate with maximum values
maximumValues = np.flipud(np.argsort(logFFT.flatten()))
used = temp.copy()
current = temp.copy()
currentScaled = temp.copy()
summed = temp.copy()
#creating writer and image window
cv2.namedWindow(videoFilename)
writer = create_video_writer(img.shape, videoFilename)
for freqIndex in maximumValues:
# for index in np.arange(0,maximumValues.size,2)
# puting frequency in 'used' array
used.flat[freqIndex] = logFFT.flat[freqIndex]
# returning the spatial sine wave for freq
temp.flat[freqIndex] = logFFT.flat[freqIndex]
current = np.fft.ifft2(temp)
temp.flat[freqIndex] = 0
print("MAX IS EQUAL TO:", np.max(current))
print("MIN IS EQUAL TO:", np.min(current))
#scaling the current
currentScaled = (
(current - np.min(current)) / np.max(current)) * 255
#summing up all the freq
summed = summed + current
#stiching all images together
frame = stich(img, logFFT, used, current, currentScaled, summed)
print("frame dataType =", frame.dtype)
#writing frame
if writer.isOpened():
writer.write(frame)
#displaying image
cv2.imshow(videoFilename, frame)
action = ipcv.flush()
if action == "pause":
action = ipcv.flush()
if action == "pause":
continue
elif action == "exit":
writer.release()
sys.exit()
except Exception as e:
ipcv.debug(e)
import ipcv
import os.path
import time
home = os.path.expanduser('~')
filename = home + os.path.sep + 'src/python/examples/data/crowd.jpg'
filename = home + os.path.sep + 'src/python/examples/data/lenna.tif'
src = cv2.imread(filename)
startTime = time.clock()
map1, map2 = ipcv.map_rotation_scale(src, rotation=30, scale=[1.3, 0.8])
#map1, map2 = ipcv.map_rotation_scale(src, rotation=0, scale=[2.0, 2.0])
elapsedTime = time.clock() - startTime
print('Elapsed time (map creation) = {0} [s]'.format(elapsedTime))
startTime = time.clock()
dst = cv2.remap(src, map1, map2, cv2.INTER_NEAREST)
# dst = ipcv.remap(src, map1, map2, ipcv.INTER_NEAREST)
elapsedTime = time.clock() - startTime
print('Elapsed time (remapping) = {0} [s]'.format(elapsedTime))
srcName = 'Source (' + filename + ')'
cv2.namedWindow(srcName, cv2.WINDOW_AUTOSIZE)
cv2.imshow(srcName, src)
dstName = 'Destination (' + filename + ')'
cv2.namedWindow(dstName, cv2.WINDOW_AUTOSIZE)
cv2.imshow(dstName, dst)
ipcv.flush()
def character_recognition(src, templates, threshold, filterType='spatial', verbose=False):
"""
Function to determine the number of characters (for each character) that
exist in an image.
Author:
Jesse Jurman (jrj2703)
Args:
src (array of ints): image to read charcters from
templates (array of arrays): images for each character to be read in
threshold (float): how strong the response needs to be before it is
considered a match
filterType (string): type of filter to run with images.
defaults to 'spatial', can be 'match'
verbose (bool): plot character maps
Returns:
a list of the indicies for the templates, in the order that they appear
on the source image
a histogram (size of the array templates)
Raises:
ValueError: filterType of not spatial or matched
"""
isrc = invertImage(src)
results = []
text = []
# text map is a mapping of x,y coords to letters
# this will be sorted to retrieve the final text
textMap = {}
if (filterType == 'spatial'):
# for every template, build a 2D map of where the template matches
for character in templates:
if (verbose):
cv2.namedWindow('isrc', cv2.WINDOW_AUTOSIZE)
cv2.imshow('isrc', isrc)
if (verbose):
cv2.namedWindow('character', cv2.WINDOW_AUTOSIZE)
cv2.imshow('character', character)
# invert the character
icharacter = invertImage(character)
# normalize template
icharacter = icharacter.astype(np.float64)
if (icharacter.sum() != 0):
icharacter /= icharacter.sum()
if (verbose):
cv2.namedWindow('icharacter', cv2.WINDOW_AUTOSIZE)
cv2.imshow('icharacter', icharacter)
# find points using filter2D
cloudMatch = cv2.filter2D(src, -1, icharacter)
if (verbose):
cv2.namedWindow('CloudMatch', cv2.WINDOW_AUTOSIZE)
cv2.imshow('CloudMatch', cloudMatch)
# make single points using np.where
pointMatch = np.where(cloudMatch >= threshold, 0, 255)
pointMatch = np.array(pointMatch, cloudMatch.dtype)
if (verbose):
cv2.namedWindow('PointMatch', cv2.WINDOW_AUTOSIZE)
cv2.imshow('PointMatch', pointMatch)
if (verbose):
ipcv.flush()
results.append((pointMatch/255).sum())
coords = np.where(pointMatch >= threshold)
for coordInd in range(len(coords[0])):
coordTuple = (coords[0][coordInd], coords[1][coordInd])
# we don't know what actual letter we're dealing with,
# but we kinda know the index using the size of the results list
# this will totally overwrite letters that sit in the same coord
textMap[coordTuple] = len(results)-1
elif (filterType == 'matched'):
# you can set the loading bar width here
# make sure it's smaller than your window, otherwise it'll
# print a LOT of newlines
loadingBarWidth = 50
loading = ipcv.Bar(loadingBarWidth)
load = 0
# iterate through our templates
for character in templates:
# update loading bar
load += 1
loading.showBar(load/len(templates))
# image of matches
resImage = np.zeros(src.shape)
# size of 2d slices
s = templates[0].shape
arrayWidth = s[0]*s[1]
# invert character
icharacter = invertImage(character)
# flatten template
rcharacter = icharacter.flatten()
# invert source
isrc = invertImage(src)
row = 0
for row in range(src.shape[0]-s[0]):
for col in range(src.shape[1]-s[1]):
# cut out a portion of the image, based on the row and column
cut = isrc[row:row+s[0], col:col+s[1]]
wideCut = cut.flatten()
# manipulate the character
numerator = np.vdot(rcharacter, wideCut)
denominator = np.vdot(np.linalg.norm(rcharacter),
np.linalg.norm(wideCut))
if (denominator != 0):
resImage[row][col] = numerator/denominator
loading.showBar(load/len(templates))
if (verbose):
cv2.namedWindow('resImage', cv2.WINDOW_AUTOSIZE)
cv2.imshow('resImage', resImage)
finImage = np.where(resImage >= threshold, 255, 0)
finImage = np.array(finImage, src.dtype)
if (verbose):
cv2.namedWindow('finImage', cv2.WINDOW_AUTOSIZE)
cv2.imshow('finImage', finImage)
if (verbose):
ipcv.flush()
results.append((finImage/255).sum())
coords = np.where(finImage >= threshold)
for coordInd in range(len(coords[0])):
coordTuple = (coords[0][coordInd], coords[1][coordInd])
# we don't know what actual letter we're dealing with,
# but we kinda know the index using the size of the results list
# this will totally overwrite letters that sit in the same coord
textMap[coordTuple] = len(results)-1
else:
raise ValueError("only filter types supported are spatial and matched")
# sort the text by it's x and y value
# print("TEXTMAP.KEYS()", textMap.keys())
sortedMapKeys = sorted(textMap.keys(), key=itemgetter(0,1))
# print("SORTEDMAPKEYS",sortedMapKeys)
for smk in sortedMapKeys:
text.append(textMap[smk])
return text, results
def character_recognition(src,
templates,
threshold,
filterType='spatial',
verbose=False):
"""
Function to determine the number of characters (for each character) that
exist in an image.
Author:
Jesse Jurman (jrj2703)
Args:
src (array of ints): image to read charcters from
templates (array of arrays): images for each character to be read in
threshold (float): how strong the response needs to be before it is
considered a match
filterType (string): type of filter to run with images.
defaults to 'spatial', can be 'match'
verbose (bool): plot character maps
Returns:
a list of the indicies for the templates, in the order that they appear
on the source image
a histogram (size of the array templates)
Raises:
ValueError: filterType of not spatial or matched
"""
isrc = invertImage(src)
results = []
text = []
# text map is a mapping of x,y coords to letters
# this will be sorted to retrieve the final text
textMap = {}
if (filterType == 'spatial'):
# for every template, build a 2D map of where the template matches
for character in templates:
if (verbose):
cv2.namedWindow('isrc', cv2.WINDOW_AUTOSIZE)
cv2.imshow('isrc', isrc)
if (verbose):
cv2.namedWindow('character', cv2.WINDOW_AUTOSIZE)
cv2.imshow('character', character)
# invert the character
icharacter = invertImage(character)
# normalize template
icharacter = icharacter.astype(np.float64)
if (icharacter.sum() != 0):
icharacter /= icharacter.sum()
if (verbose):
cv2.namedWindow('icharacter', cv2.WINDOW_AUTOSIZE)
cv2.imshow('icharacter', icharacter)
# find points using filter2D
cloudMatch = cv2.filter2D(src, -1, icharacter)
if (verbose):
cv2.namedWindow('CloudMatch', cv2.WINDOW_AUTOSIZE)
cv2.imshow('CloudMatch', cloudMatch)
# make single points using np.where
pointMatch = np.where(cloudMatch >= threshold, 0, 255)
pointMatch = np.array(pointMatch, cloudMatch.dtype)
if (verbose):
cv2.namedWindow('PointMatch', cv2.WINDOW_AUTOSIZE)
cv2.imshow('PointMatch', pointMatch)
if (verbose):
ipcv.flush()
results.append((pointMatch / 255).sum())
coords = np.where(pointMatch >= threshold)
for coordInd in range(len(coords[0])):
coordTuple = (coords[0][coordInd], coords[1][coordInd])
# we don't know what actual letter we're dealing with,
# but we kinda know the index using the size of the results list
# this will totally overwrite letters that sit in the same coord
textMap[coordTuple] = len(results) - 1
elif (filterType == 'matched'):
# you can set the loading bar width here
# make sure it's smaller than your window, otherwise it'll
# print a LOT of newlines
loadingBarWidth = 50
loading = ipcv.Bar(loadingBarWidth)
load = 0
# iterate through our templates
for character in templates:
# update loading bar
load += 1
loading.showBar(load / len(templates))
# image of matches
resImage = np.zeros(src.shape)
# size of 2d slices
s = templates[0].shape
arrayWidth = s[0] * s[1]
# invert character
icharacter = invertImage(character)
# flatten template
rcharacter = icharacter.flatten()
# invert source
isrc = invertImage(src)
row = 0
for row in range(src.shape[0] - s[0]):
for col in range(src.shape[1] - s[1]):
# cut out a portion of the image, based on the row and column
cut = isrc[row:row + s[0], col:col + s[1]]
wideCut = cut.flatten()
# manipulate the character
numerator = np.vdot(rcharacter, wideCut)
denominator = np.vdot(np.linalg.norm(rcharacter),
np.linalg.norm(wideCut))
if (denominator != 0):
resImage[row][col] = numerator / denominator
loading.showBar(load / len(templates))
if (verbose):
cv2.namedWindow('resImage', cv2.WINDOW_AUTOSIZE)
cv2.imshow('resImage', resImage)
finImage = np.where(resImage >= threshold, 255, 0)
finImage = np.array(finImage, src.dtype)
if (verbose):
cv2.namedWindow('finImage', cv2.WINDOW_AUTOSIZE)
cv2.imshow('finImage', finImage)
if (verbose):
ipcv.flush()
results.append((finImage / 255).sum())
coords = np.where(finImage >= threshold)
for coordInd in range(len(coords[0])):
coordTuple = (coords[0][coordInd], coords[1][coordInd])
# we don't know what actual letter we're dealing with,
# but we kinda know the index using the size of the results list
# this will totally overwrite letters that sit in the same coord
textMap[coordTuple] = len(results) - 1
else:
raise ValueError("only filter types supported are spatial and matched")
# sort the text by it's x and y value
# print("TEXTMAP.KEYS()", textMap.keys())
sortedMapKeys = sorted(textMap.keys(), key=itemgetter(0, 1))
# print("SORTEDMAPKEYS",sortedMapKeys)
for smk in sortedMapKeys:
text.append(textMap[smk])
return text, results
