def return_pp(img_dir): names=get_abs_names.get_files(img_dir) names.sort() image_vector=[] for i in range(len(names)): image_vector.append(initial_processing.imageToVector(names[i])) #print image_vector #print len(image_vector) sum_img=image_vector[-1] for i in range(len(image_vector)-1): sum_img=sum_img+image_vector[i] # Uncomment to know the sum image #print "printing sum image" #print sum_img hist_img=numpy.histogram(sum_img,bins=34) ## Uncoment to now the histogram #print "Printing histogram" #print hist_img img_for_dimension=Image.open(names[0]) percent_of_pixels=(hist_img[0]/float(img_for_dimension.size[0]*img_for_dimension.size[1]))*100 # Uncomment to know the details of percentage of pixels present per bucket range #print "Printing percentage of pixels" #print percent_of_pixels #print len(percent_of_pixels) #print sum(percent_of_pixels) return percent_of_pixels
def testdb(signature_images,test_set,train_set,mean_img_vect_for_test,eigen_selected_for_test,count_of_dots_original_path,flag_for_rename):
temp_norm_list=[]
sucess=0
signature_images_backup=signature_images
for i in test_set:
temp_norm_list=[]
print "testing undergoing for the image: " +i
temp_test_image=Image.open(i)
temp_test_image_vect=ip.imageToVector(i)
temp_test_image_mean_subtracted=temp_test_image_vect-mean_img_vect_for_test
temp_test_image_mean_subtracted_transpose=numpy.transpose(temp_test_image_mean_subtracted)
temp_test_image_mapped=numpy.matrix(temp_test_image_mean_subtracted_transpose)*numpy.matrix(eigen_selected_for_test)
for j in range(len(signature_images)):
temp_for_norm=signature_images[j]-temp_test_image_mapped
temp_norm_list.append(scipy.linalg.norm(temp_for_norm,2))
temp_min_in_norm_list=min(temp_norm_list)
temp_index_min_in_norm_list = temp_norm_list.index(temp_min_in_norm_list)
recognized=train_set[temp_index_min_in_norm_list]
########## code of checking if the algorithm identified correctly or not
if(flag_for_rename==1):
index_of_underscore=i.find('_')
if(index_of_underscore>=0):
new_i=i.replace('_',os.sep)
new_recognized=recognized.replace('_',os.sep)
else:
new_i=i.replace('.',os.sep,count_of_dots_original_path+1)
new_recognized=recognized.replace('.',os.sep,count_of_dots_original_path+1)
else:
new_i=i
new_recognized=recognized
temp_split_taken_name=new_i.split(os.sep)
temp_split_recognized_name=new_recognized.split(os.sep)
len_of_split_file_name=len(temp_split_recognized_name)
if(temp_split_taken_name[len_of_split_file_name-2]==temp_split_recognized_name[len_of_split_file_name-2]):
print "taken class : " + temp_split_taken_name[len_of_split_file_name-2]
print "recognized class : " +temp_split_recognized_name[len_of_split_file_name-2]
print "sucess"
sucess=sucess+1
else :
print "taken class : " + temp_split_taken_name[len_of_split_file_name-2]
print "recognized class : " +temp_split_recognized_name[len_of_split_file_name-2]
print "failure"
print "printing sucess"
print " identified %d images out of %d images " %(sucess,len(test_set))
return (float(sucess)/len(test_set))*100
def create_xs_ys(self):
self.files_list = \
lslR.get_files(directory=self.IMAGE_DIRECTORY,include=self.include,\
exclude = self.exclude,ftype=self.ftypes)
#print files_list
for file in self.files_list:
for item in self.keywords.iteritems():
#the 1st entry is the class number 0,1,2,3...
key = item[0]
#the second entry is the reg-exp identifying the class
value = item[1]
if file.rfind(value) != -1 :
#print key , file
self.xs.append(initial_processing.imageToVector(file))
self.ys.append(key)
mean_img_vect sum_img_vect """ for i in range(total_dimensions_per_image): mean_img_vect.append(0) sum_img_vect.append(0) """ we might have to convert images to vectors before processing, so imageToVector method in initial_processing is called and all individual images are appended to total_img_vect """ for i in images : image_vect=ip.imageToVector(i) total_img_vect.append(image_vect) """ we might have to number of images to calculate mean/sum of the images """ total_no_of_images=len(total_img_vect) """finding the total of all the images""" for i in range(total_no_of_images): sum_img_vect=sum_img_vect+total_img_vect[i] """ finding the mean of all the images """ mean_img_vect=sum_img_vect/total_no_of_images
def traindb(image_list): # Declarations of some required variables images_abs_names=[] # variable contains all the paths to file total_img_vect=[] # variable to contain total images in vector form mean_img_vect=[] # variable for containing mean of all images sum_img_vect=[] # variable for containing sum of all images mean_for_subtraction=[] # variable contains clones of mean used for subtracting image_vect=[] #holding vectors of images #code starts here image_list_backup=image_list shape_image=Image.open(image_list[0][0]) shape_image_array=numpy.asarray(shape_image) shape=shape_image_array.shape total_dimensions_per_image=shape[0]*shape[1] # ##initialising all the required values such as ###mean_img_vect ####sum_img_vect for i in range(total_dimensions_per_image): mean_img_vect.append(0) sum_img_vect.append(0) #we have to convert images to vectors before processing, ##so imageToVector method in initial_processing is called ###and all individual images are appended to total_img_vect for i in image_list : for j in range(len(i)): temp_image_vect=ip.imageToVector(i[j]) image_vect.append(temp_image_vect) total_img_vect=image_vect # we have to know number of images to calculate ##mean/sum of the images total_no_of_images=len(total_img_vect) #Uncomment following line to know the number of trained images #print "Total number of trained images = %d " %(total_no_of_trained_images) #finding the total of all the images for i in range(total_no_of_images): sum_img_vect=sum_img_vect+total_img_vect[i] #print "printing the total sum of images" #print sum_img_vect # finding the mean of all the images mean_img_vect=sum_img_vect/total_no_of_images #print "printing the mean of all images" #print mean_img_vect # we need to clone mean_img_vect as manytimes as number of images ##to subtract from total_img_vect which actually contains vectors of all ###the images for i in range(total_no_of_images): mean_for_subtraction.append(mean_img_vect) # ##the vectors are to be conveted for furthur processsing of ###co-relation etc.., and transpose is taken so it matches the required ####order, which is each column containing one image in 2-d matrix total_img_array=numpy.asarray(total_img_vect) total_img_array=numpy.transpose(total_img_array) mean_for_subtraction_array=numpy.asarray(mean_for_subtraction) mean_for_subtraction_array=numpy.transpose(mean_for_subtraction_array) ### subtraction of original images with mean is done here for furthur ####processing mean_sub_img_array=total_img_array-mean_for_subtraction_array ### Calculating co-relation matrix using mean_subtracted_matrix """ mean_sum_img_array_transpose=numpy.transpose(mean_sub_img_array) # Calculating the transpose co_relation = numpy.matrix(mean_sum_img_array_transpose)*numpy.matrix(mean_sub_img_array) # casting to matrix #and multiplying to form co-relation matrix ### Calculating Eigen Values and Eigen Vectors """ eig_value,eig_vect = scipy.linalg.eig(co_relation) # returns the eigen values and eigen vectors ### mapping eigen values onto images""" eig_vect=numpy.matrix(eig_vect) # casting to matrix for multiplication mean_sub_img_array = numpy.matrix(mean_sub_img_array) # casting to matrix for multiplication mapped_eig = mean_sub_img_array * eig_vect # Multiplication which maps images to eigen vectors mapped_eig_array=numpy.asarray(mapped_eig) # Converting back to array for slicing no_of_eigen_vectors_to_be_taken=20 # Edit this value to change the no of dimensions to be taken mapped_eig_large_select=mapped_eig_array[:,0:no_of_eigen_vectors_to_be_taken] # Selecting required number of dimensions #using slicing ### Calculating the signature of each image """ # Creating the matrix ( signature matrix )and initialised with zeros cv_signature_images=zeros((total_no_of_images,no_of_eigen_vectors_to_be_taken)) mean_sub_img_array_transpose=numpy.transpose(mean_sub_img_array) # transpose is taken so it becomes easy for multiplicati for i in range(total_no_of_images) : cv_signature_images[i]=mean_sub_img_array_transpose[i] * mapped_eig_large_select #Uncomment following two lines to print the shape of the signature matrix #print cv_signature_images.shape #print " is the sizeof the signature matrix " return mean_img_vect,mapped_eig_large_select,cv_signature_images
def test(self,image_directory,classKeys,include=None,exclude=None):
"""
The method implements the testing part of the algorithm and returns
the successrate in fractions between 0 and 1
"""
#the following reassignment is done to keep the __init__
#method and the test method arguments consistent
test_path = image_directory
test_classes = classKeys
includ = include
exclud = exclude
print "Starting to Test"
#test_path = raw_input("Enter the Path containing test images:")
#test_pattern = list(raw_input("Enter the regexp identifying \
#test images in the directory above:"))
test_files = \
lslR.get_files(directory=test_path,ftype=self.ftypes,include=includ,exclude=exclud)
num = len(test_files)
i = 0
success = 0
failure = 0
for fil in test_files:
#if num - i > 0 :
# print "processing Image number: (%d) , Corresponding to File name: %s " % (i,fil)
xTest = \
numpy.matrix(initial_processing.imageToVector(fil))
xTest_class = -1
#----------------debug code------------
#print type(xTest)
#--------------------------------------
#project testing image on A
#yTest = numpy.transpose(self.A * xTest.transpose())
yTest = xTest * self.A.transpose()
#find the distance of yTest from each Yi
distAndYPair = [] #inf denotes infinity
#self.y_Transpose = numpy.transpose(self.y)
#for y in self.y_Transpose:
for y in self.y:
#print type(yTest),type(y),yTest.shape,y.shape
dist = spatial.distance.euclidean(yTest,y)
#if dist < minPair[0]:
# print "iterating to find the minimum match"
# print "y :",y
# print "yTest :",yTest
# minPair[0] = dist
# minPair[1] = tuple(y)
distAndYPair.append([dist,y])
#print "type of minPair[1]"+str(type(minPair[1]))
#print minPair[1] in self.y_Transpose
distAndYPair.sort()
#print minPair[1] in numpy.transpose(self.y)
#print type(self.y[0])
#print "Minimum distance: ",minPair[0]
recognized_class = self.yZipYs[distAndYPair[0][1]]
#because the class number starts from 0 and the numbering of
#of
for key in test_classes.keys():
if fil.find(key) != -1:
xTest_class = test_classes[key]
break
if recognized_class == xTest_class :
success += 1
else:
failure += 1
#print "Success %d , Failure %d" % (success,failure)
#print "Recognized Class: %d And xTest_Class: %d " % \
#(recognized_class,xTest_class)
i +=1
rate = (float(success)/float(success+failure))
#print "Success Rate is : %f" % rate
return rate
mean_img_vect
sum_img_vect
"""
for i in range(total_dimensions_per_image):
mean_img_vect.append(0)
sum_img_vect.append(0)
"""
we might have to convert images to vectors before processing,
so imageToVector method in initial_processing is called
and all individual images are appended to total_img_vect
"""
for i in images:
image_vect = ip.imageToVector(i)
total_img_vect.append(image_vect)
""" we might have to number of images to calculate
mean/sum of the images
"""
total_no_of_images = len(total_img_vect)
"""finding the total of all the images"""
for i in range(total_no_of_images):
sum_img_vect = sum_img_vect + total_img_vect[i]
""" finding the mean of all the images """
mean_img_vect = sum_img_vect / total_no_of_images
def testdb(signature_images,test_set,train_set,mean_img_vect_for_test,eigen_selected_for_test,trained_images_per_class,flag_for_rename):
# Need to set the flags depending on the file names and directory structure
# rename_flag_is_set=0
# print test_set
# file_path_name_from_test_set_to_set_flag=test_set[0]
# file_path_name_from_test_set_to_set_flag_split=file_path_name_from_test_set_to_set_flag.split(os.sep)
# print file_path_name_from_test_set_to_set_flag_split
# file_path_from_test_set_to_set_flag_length=len(file_path_name_from_test_set_to_set_flag_split)
# file_name_from_test_set_to_set_flag=file_path_name_from_test_set_to_set_flag_split[file_path_from_test_set_to_set_flag_length-1]
# print file_name_from_test_set_to_set_flag
# index_of_underscore=file_name_from_test_set_to_set_flag.find('_')
#
# index_of_dot=file_name_from_test_set_to_set_flag.index('.')
#
# rindex_of_dot=file_name_from_test_set_to_set_flag.rindex('.')
# print index_of_underscore
# if(index_of_underscore>=0):
# rename_flag_is_set=1
# if(index_of_dot>=0):
# rename_flag_is_set=2 */
temp_norm_list=[]
sucess=0
signature_images_backup=signature_images
for i in test_set:
temp_norm_list=[]
#print "testing undergoing for the image: " +i
temp_test_image=Image.open(i)
temp_test_image_vect=ip.imageToVector(i)
temp_test_image_mean_subtracted=temp_test_image_vect-mean_img_vect_for_test
temp_test_image_mean_subtracted_transpose=numpy.transpose(temp_test_image_mean_subtracted)
temp_test_image_mapped=numpy.matrix(temp_test_image_mean_subtracted_transpose)*numpy.matrix(eigen_selected_for_test)
for j in range(len(signature_images)):
temp_for_norm=signature_images[j]-temp_test_image_mapped
temp_norm_list.append(scipy.linalg.norm(temp_for_norm,2))
temp_min_in_norm_list=min(temp_norm_list)
temp_index_min_in_norm_list = temp_norm_list.index(temp_min_in_norm_list)
recognized=train_set[temp_index_min_in_norm_list]
########## code of checking if the algorithm identified correctly or not
if(flag_for_rename==1):
index_of_underscore=i.find('_')
if(index_of_underscore>=0):
new_i=i.replace('_',os.sep,1)
new_recognized=recognized.replace('_',os.sep)
else:
new_i=i.replace('.',os.sep,1)
new_recognized=recognized.replace('.',os.sep,1)
else:
new_i=i
new_recognized=recognized
temp_split_taken_name=new_i.split(os.sep)
temp_split_recognized_name=new_recognized.split(os.sep)
len_of_split_file_name=len(temp_split_recognized_name)
if(temp_split_taken_name[len_of_split_file_name-2]==temp_split_recognized_name[len_of_split_file_name-2]):
#print "taken class : " + temp_split_taken_name[len_of_split_file_name-2]
#print "recognized class : " +temp_split_recognized_name[len_of_split_file_name-2]
#print "sucess"
sucess=sucess+1
#else :
#print "taken class : " + temp_split_taken_name[len_of_split_file_name-2]
#print "recognized class : " +temp_split_recognized_name[len_of_split_file_name-2]
#print "failure"
#print "printing sucess"
#print " identified %d images out of %d images " %(sucess,len(test_set))
return (sucess/len(test_set))
