def index_imgs():
global database
global hash_rep
database = []
json_files = os.listdir(config.FEATURES_FOLDER)
json_files = ret_files_without_ext(json_files)
ctr = 0
total_iter = len(hash_rep) * len(json_files)
for i in range(len(hash_rep)):
layer_index = {}
for img in json_files:
with open(path.join(config.FEATURES_FOLDER, img + '.json'),
'r',
encoding='utf-8') as f:
feat_desc = json.load(f)
img_bucket = img_index(feat_desc[img], i)
if (img_bucket not in layer_index):
layer_index[img_bucket] = [img]
else:
layer_index[img_bucket].append(img)
ctr += 1
progress(ctr, total_iter)
database.append(layer_index)
return database
def LBPFeatureDescriptorForImageSubset(self, imageSet):
# Iterating on all the images in the selected folder to calculate HOG FD for each of the images
storeLbpFD = []
lbp = LBP()
number_files = len(imageSet)
i = 0
for filename in imageSet:
hognp = lbp.LBPForSingleImage(
join(str(config.IMAGE_FOLDER), filename))
storeLbpFD.append(hognp.tolist())
i = i + 1
progress(i, number_files)
print(len(storeLbpFD))
return storeLbpFD
def CMFeatureDescriptor(self):
# Iterating on all the images in the selected folder to calculate HOG FD for each of the images
storeCmFD = []
cm = CM()
files = os.listdir(str(
config.IMAGE_FOLDER)) # dir is your directory path
number_files = len(files)
i = 0
for file in os.listdir(str(config.IMAGE_FOLDER)):
filename = os.fsdecode(file)
if filename.endswith(".jpg"):
hognp = cm.CMForSingleImage(
str(config.IMAGE_FOLDER) + "\\" + filename)
storeCmFD.append(hognp.tolist())
i = i + 1
progress(i, number_files)
print()
return storeCmFD
def LBPFeatureDescriptorForImageSubset(self, imageSet):
# Iterating on all the images in the selected folder to calculate HOG FD for each of the images
storeLbpFD = []
lbp = LBP()
files = os.listdir(str(
config.IMAGE_FOLDER)) # dir is your directory path
number_files = len(files)
i = 0
for file in os.listdir(str(config.IMAGE_FOLDER)):
filename = os.fsdecode(file)
if filename.endswith(".jpg") and (filename
in imageSet.imageName.values):
hognp = lbp.LBPForSingleImage(
str(config.IMAGE_FOLDER) + "\\" + filename)
storeLbpFD.append(hognp.tolist())
i = i + 1
progress(i, number_files)
print()
return storeLbpFD
def train_k_means_clustering(data, k, epochs=20):
print('\nRunning K means Clustering.')
datapoints = len(data)
features = len(data[0])
centers = random_centers(data, datapoints, k)
clustered_data = point_clustering(data,
centers,
features,
first_cluster=True)
for i in range(epochs):
centers = mean_center(clustered_data, centers, features)
clustered_data = point_clustering(data,
centers,
features,
first_cluster=False)
progress(i, epochs - 1)
return centers
def LBPFeatureDescriptor(self):
# Iterating on all the images in the selected folder to calculate HOG FD for each of the images
storeLbpFD = {}
lbp = LBP()
files = os.listdir(str(
config.FULL_IMAGESET_FOLDER)) # dir is your directory path
number_files = len(files)
i = 0
for file in os.listdir(str(config.FULL_IMAGESET_FOLDER)):
filename = os.fsdecode(file)
if filename.endswith(".jpg"):
storeLbpFD = {}
hognp = lbp.LBPForSingleImage(
join(str(config.FULL_IMAGESET_FOLDER), filename))
# storeLbpFD.append(hognp.tolist())
storeLbpFD[filename] = (hognp.tolist())
with open(join(config.FEATURES_FOLDER_LBP, filename + ".json"),
'w',
encoding='utf-8') as f:
json.dump(storeLbpFD, f, ensure_ascii=True)
i = i + 1
progress(i, number_files)
def load_features(folder_path):
hog_feature_map = {}
counter = 1
training_files = os.listdir(folder_path)
print("Extracting features for the training images!")
for trainingFile in training_files:
trainingFileJson = os.fsdecode(trainingFile).split(
'.')[0] + '.' + os.fsdecode(trainingFile).split('.')[1] + '.json'
fileExists = os.path.exists(
join(config.FEATURES_FOLDER, trainingFileJson))
data = {}
if fileExists:
with open(join(config.FEATURES_FOLDER, trainingFileJson),
"r") as f:
data = json.load(f)
hog_feature_map.update(data)
else:
data = HOG().HOGForSingleImage(folder_path, trainingFile)
hog_feature_map.update(data)
progress(counter, len(training_files))
counter = counter + 1
hog_values = list(hog_feature_map.values())
return hog_values, training_files
def startTask4():
print("starting task4")
print("Enter the folder path containing the labeled images")
training_folder = input()
print("Choose one of the below classifier")
print("1. SVM classifer\n2. Decision-Tree classifier\n3. PPR based classifier")
classifier = int(input())
print("Enter the folder path containing the test images")
test_folder = input()
hog_feature_map = {}
counter = 1
training_files = os.listdir(training_folder)
print("Extracting features for the training images!")
for trainingFile in training_files:
trainingFileJson = os.fsdecode(trainingFile).split('.')[0] + '.' + os.fsdecode(trainingFile).split('.')[
1] + '.json'
fileExists = os.path.exists(join(config.FEATURES_FOLDER, trainingFileJson))
if fileExists:
with open(join(config.FEATURES_FOLDER, trainingFileJson), "r") as f:
data = json.load(f)
hog_feature_map.update(data)
else:
data = HOG().HOGForSingleImage(training_folder, trainingFile)
hog_feature_map.update(data)
progress(counter, len(training_files))
counter = counter + 1
reducer_object = list(hog_feature_map.values())
print("Performing PCA!")
pca = PCA_Reducer(reducer_object)
data = pca.reduceDimension(pca.featureDescriptor)
print("Done performing PCA!")
if classifier == 1:
# image labels are added to the imageLabels list. -1 for dorsal and 1 for palmar
metadata = pd.read_csv(config.METADATA_FOLDER)
image_lables = get_labels(training_folder, metadata)
svm_object = SVM()
print("Training SVM")
svm_object.svm_fit(data, image_lables)
print("Done Training SVM")
test_labels_map = {}
predicted_values = []
actual_values = get_labels(test_folder, metadata)
for file in os.listdir(test_folder):
test_file = file
test_file_json = file + '.json'
file_exists = os.path.exists(join(config.FEATURES_FOLDER, test_file_json))
if file_exists:
with open(join(config.FEATURES_FOLDER, test_file_json), "r") as f:
data = json.load(f)
else:
data = HOG().HOGForSingleImage(test_folder, test_file)
pca_output = pca.reduceDimension(list(data.values()))
output_label = np.asarray(svm_object.predict(pca_output))[0]
predicted_values.append(output_label)
if output_label == -1:
test_labels_map[test_file] = "dorsal"
else:
test_labels_map[test_file] = "palmar"
print(test_labels_map)
accuracy = accuracy_score(actual_values, predicted_values)
plotInChromeForTask4(test_labels_map, "Task_4_SVM", accuracy)
print("Test Accuracy: ", accuracy)
if classifier == 2:
data = data.values.tolist() # decision tree takes data as 2d array
class_labels = [-1, 1]
i = 0
metadata = pd.read_csv(config.METADATA_FOLDER)
for file in os.listdir(training_folder):
training_file = os.fsdecode(file)
label = metadata.loc[metadata['imageName'] == training_file]['aspectOfHand'].iloc[0]
if "dorsal" in label:
data[i].append(-1)
else:
data[i].append(1)
i = i + 1
dtree_object = decisionTree()
root = dtree_object.construct_dt(data, class_labels, 5, 2)
test_labels_map = {}
predicted_values = []
actual_values = get_labels(test_folder, metadata)
for file in os.listdir(test_folder):
test_file = os.fsdecode(file).split('.')[0] + '.' + os.fsdecode(file).split('.')[1]
test_file_json = os.fsdecode(file).split('.')[0] + '.' + os.fsdecode(file).split('.')[1] + '.json'
file_exists = os.path.exists(join(config.FEATURES_FOLDER, test_file_json))
if file_exists:
with open(join(config.FEATURES_FOLDER, test_file_json), "r") as f:
data = json.load(f)
else:
data = HOG().HOGForSingleImage(test_folder, test_file)
pca_output = pca.reduceDimension(list(data.values()))
pca_output = pca_output.values.tolist()[0]
output_label = dtree_object.predict(root, pca_output)
predicted_values.append(output_label)
if output_label == -1:
test_labels_map[test_file] = "dorsal"
else:
test_labels_map[test_file] = "palmar"
accuracy = accuracy_score(actual_values, predicted_values)
plotInChromeForTask4(test_labels_map, "Task_4_DECISION", accuracy)
print("Test Accuracy: ", accuracy)
if classifier == 3:
pca_for_all = data
i = 0
imageNames = []
latentFeatureDict = {}
# Preprocessing for UnLabelled set
ppr_hog_map = {}
for test_file in os.listdir(test_folder):
trainingFileJson = str(test_file) + '.json'
fileExists = os.path.exists(join(config.FEATURES_FOLDER, trainingFileJson))
if fileExists:
with open(join(config.FEATURES_FOLDER, trainingFileJson), "r") as f:
data = json.load(f)
ppr_hog_map.update(data)
else:
data = HOG().HOGForSingleImage(test_folder, test_file)
ppr_hog_map.update(data)
# Appending the labelled data values with unlabelled images data
reducer_object = list(hog_feature_map.values())
pp_reducer_object = list(ppr_hog_map.values())
pp_reducer_object = reducer_object + pp_reducer_object
pca = PCA_Reducer(pp_reducer_object)
unlabelled_ppr_data = pca.reduceDimension(pca.featureDescriptor)
pca_for_all = unlabelled_ppr_data
for file in os.listdir(str(training_folder)):
filename = os.fsdecode(file)
latent = pca_for_all.iloc[i][:]
imageNames.append(filename)
latentFeatureDict[filename] = latent
i = i + 1
for file in os.listdir(join(test_folder)):
filename = os.fsdecode(file)
latent = pca_for_all.iloc[i][:]
imageNames.append(filename)
latentFeatureDict[filename] = latent
i = i + 1
# seed = pd.Series(0, index=imageNames)
print("Generating Adjacency Matrix..")
adjacency_matrix = [[0 for _ in range(len(latentFeatureDict))] for _ in range(len(latentFeatureDict))]
for i in range(len(latentFeatureDict)):
distances = []
for j in range(len(latentFeatureDict)):
# print(len(latentFeatureDict[imageNames[i]]), len(latentFeatureDict[imageNames[j]]))
distances.append(find_distance_2_vectors(latentFeatureDict[imageNames[i]],
latentFeatureDict[imageNames[j]]))
distances = np.asarray(distances)
ind = np.argpartition(distances, 20)[:20]
total = 0
for distance_index in ind:
if distances[distance_index] != 0:
total += 1 / distances[distance_index]
for distance_index in ind:
# This is adding only k nearest neighbours into the matrix and doing ratio to get probablistic matrix
if distances[distance_index] != 0:
adjacency_matrix[distance_index][i] = 1 / distances[distance_index] / total
rowDict = {}
i = 0
for image in imageNames:
rowDict[i] = image
i = i + 1
df = pd.DataFrame(adjacency_matrix, columns=imageNames)
df.rename(index=rowDict, inplace=True)
df.to_csv(join(config.DATABASE_FOLDER, "adjacency_matrix_for_task_4.csv"))
I = np.identity(df.shape[1])
seed = pd.Series(0, index=imageNames)
metadata = pd.read_csv(config.METADATA_FOLDER)
image_lables = get_labels(training_folder, metadata)
count = image_lables.count(-1)
val = 1 / count
for i in range(len(os.listdir(training_folder))):
if image_lables[i] == -1:
seed.loc[imageNames[i]] = val
# print(seed)
seed2 = pd.Series(0, index=imageNames)
count2 = image_lables.count(1)
val2 = 1 / count2
for i in range(len(os.listdir(training_folder))):
if image_lables[i] == 1:
seed2.loc[imageNames[i]] = val
page_rank = np.matmul(np.linalg.inv(I - .75 * df), 0.25 * seed)
page_rank2 = np.matmul(np.linalg.inv(I - .75 * df), 0.25 * seed2)
steady_state = pd.Series(page_rank, index=df.index)
steady_state2 = pd.Series(page_rank2, index=df.index)
test_labels_map = {}
predicted_values = []
for file in os.listdir(join(test_folder)):
if steady_state[file] >= steady_state2[file]:
test_labels_map[file] = "dorsal"
predicted_values.append(-1)
else:
test_labels_map[file] = "palmer"
predicted_values.append(1)
actual_values = get_labels(test_folder, metadata)
accuracy = accuracy_score(actual_values, predicted_values)
plotInChromeForTask4(test_labels_map, "Task_4_PPR", accuracy)
print("Test Accuracy: ", accuracy)
steady_state = steady_state.sort_values(ascending=True)
steady_state.to_csv(join(config.DATABASE_FOLDER, "steady_state_matrix_for_task_4.csv"))
steady_state.plot()
plt.show()