def show(camera):
while True:
frame, img = camera.getStreaming()
if auto:
imgP.imageProcess(img)
cv2.waitKey(41) # Rasp
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n')
def DoCutImage(resImageIndex, imageFilenameX, atxBaseDirStr, resTitlePy):
if atxBaseDirStr != None:
imageFileDir, imageFileName = os.path.split(imageFilenameX)
imageFilenameX = os.path.join(atxBaseDirStr, imageFileDir, imageFileName)
imageProcessObj = imageProcess.imageProcess()
imageProcessObj.OpenPNG(imageFilenameX)
iWidth, iHeight = imageProcessObj.imageObj.size
cutedImageObj = imageProcessObj.CutBlackBorder()
cutedImageData = imageProcessObj.GetRGB555Data()
resCutedWidth, resCutedHeight = cutedImageObj.size
## #根据图片动态计算 resTitlePy
## resCutedTop = imageProcessObj.cutTop
## resTitlePy = resCutedTop - 5
## #根据 resCutedTop 计算出 resTitlePy
## resCutedTop = imageProcessObj.cutTop
## resTitlePy = 0
## if resCutedTop >= 40:
## resTitlePy = 40
## if resCutedTop >= 45:
## resTitlePy = 40
## if resCutedTop >= 70:
## resTitlePy = 65
## if resCutedTop >= 95:
## resTitlePy = 90
## if resCutedTop >= 115:
## resTitlePy = 110
imageHeaderAndDataDict = {
'resImageIndex' : resImageIndex,
'resSize' : len(cutedImageData), #RGB555
'resTitlePy' : resTitlePy,
'resCutedLeft' : imageProcessObj.cutLeft,
'resCutedTop' : imageProcessObj.cutTop,
'resCutedWidth' : resCutedWidth,
'resCutedHeight' : resCutedHeight,
'cutedImageData' : cutedImageData,
}
global lock
lock.acquire()
##print '%s' % resImageIndex
if imageProcessObj.isBlackImage:
print '%s' % resImageIndex,
else:
print '.',
lock.release()
return imageHeaderAndDataDict
def PrintImageInfo(self):
imageProcessObj = imageProcess.imageProcess()
print 'len(self.packageImageHeaderList):', len(self.packageImageHeaderList)
print 'len(self.packageImageDatalist):', len(self.packageImageDatalist)
for x in range(len(self.packageImageHeaderList)):
#计算出图片宽度
packageImageHeaderX = self.packageImageHeaderList[x]
width = packageImageHeaderX['resCutedWidth']
height = packageImageHeaderX['resCutedHeight']
print width, height, packageImageHeaderX['resSize']
imageProcessObj.PrintRGB555Data(width, height, self.packageImageDatalist[x])
return
def getProfilePicture(self):
url = "https://graph.facebook.com/" + self.username + "/picture?width=400&height=400"
savingToDirectory = "/srv/www/davidguo.ca/public_html/hackathon2013/hackathon2013/core/images/"
imgFileName = self.id + "img.jpg"
fileExist = False
for files in os.listdir(savingToDirectory):
if files == imgFileName and files.endswith(".jpg"):
fileExist = True
break
if fileExist == False:
urllib.urlretrieve(url, savingToDirectory + imgFileName)
self.ip = imageProcess.imageProcess()
self.ip.fileName = savingToDirectory + imgFileName
self.ip.pixelate()
return imgFileName
def GetPNGFromAnRPFile(self,packageName = None):
if packageName == None:
packageName = self.packageName
lenth = len(self.packageImageDatalist)
for i in range(lenth):
imageDataX = self.packageImageDatalist[i]
imageHeaderDictX = self.packageImageHeaderList[i]
width = imageHeaderDictX['resCutedWidth']
height = imageHeaderDictX['resCutedHeight']
rgb555Data = imageDataX
rgb555Data = []
f = open('%s.anrp' % packageName, 'rb')
f.seek(imageHeaderDictX['resImageDataPos'])
packFormatStr = '%dB' % imageHeaderDictX['resSize']
packBufferStr = f.read(imageHeaderDictX['resSize'])
rgb555Data = struct.unpack(packFormatStr, packBufferStr)
imageProcessObj = imageProcess.imageProcess()
rgb888DataList = imageProcessObj.GetRGB888from555(width, height, rgb555Data)
imageObj = imageProcessObj.CreateFromRGB888(width, height, rgb888DataList)
imageProcessObj.Save2PNG(imageObj, '%s_%s' %(packageName,i))
#del anrpObj
return
def getTaggedPhoto(self):
url = self.makeURL("me?fields=friends.uid(" + self.id + ").fields(photos.fields(tags,id))")
request = urllib.urlopen(url)
response = json.loads(request.read())
listOfPhotos = response["friends"]["data"][0]["photos"]["data"]
for photo in listOfPhotos:
if "tags" not in photo:
continue
for tag in photo["tags"]["data"]:
if tag["id"] == self.id:
photoId = photo["id"]
tagXCoor = tag["x"] # x coordinate of tag
tagYCoor = tag["y"]
url = self.makeURL(photoId)
img = Image()
imgFileName = self.id + "img.jpg"
urllib.urlretrieve(url, imgFileName)
self.ip = imageProcess.imageProcess()
self.ip.fileName = imgFileName
img
return imgFileName
"(Default: C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Phase1\\Hands_test2\\) : "
)
if path == '':
path = 'C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Phase1\\Hands_test2\\'
dim = dimReduction(path, '*.jpg')
feature = input(
'Please choose a feature model - SIFT(s), Moments(m), LBP(l), Histogram(h): '
)
if feature not in ('s', 'm', 'l', 'h'):
print('Please enter a valid feature model!')
exit()
technique = input(
'Please choose a dimensionality reduction technique - PCA(pca), SVD(svd), NMF(nmf), LDA(lda)'
)
image = input("Insert the name of your image: ")
k = input('Please provide the number of latent semantics(k): ')
db = 'imagedata_' + feature + '_' + technique
task2 = imageProcess(
"/home/anhnguyen/ASU/CSE-515/Project/Phase 2/Project - Phase 2/Data/testset1/"
)
task2.similarity(feature, technique, db, int(k), image)
# similarity(feature, technique, db, int(k), image)
# imgs_sort, feature_sort = dim.saveDim(feature, technique, db, int(k))
# phase1 = imageProcess("/home/anhnguyen/ASU/CSE-515/Project/Phase 2/Project - Phase 2/Data/testset1/")
# print('\n')
# print('Data Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Data_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
# print('\n')
# print('Feature Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Feature_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
def saveDim(self,
feature,
model,
dbase,
k,
password='******',
host='localhost',
database='mwdb',
user='******',
port=5432,
label=None,
meta=False,
negative_handle='n'):
imageDB = imageProcess(self.dirpath)
imgs = imageDB.dbProcess(password=password,
process='f',
model=feature,
dbase=dbase)
kmeans_model = 'kmeans_' + str(no_clusters)
technique_model = feature + '_' + model
if label is not None:
filteredImage = imageDB.CSV(label)
label = label.replace(" ", "_")
dbase += '_' + model + '_' + label
kmeans_model += '_' + label
technique_model += '_' + label
else:
dbase += '_' + model
# print(technique_model)
imgs_data = []
imgs_meta = []
i = -1
while i < len(imgs) - 1:
# print (x[1].shape)
i += 1
if label is not None and imgs[i][0] not in filteredImage:
# print("label")
del imgs[i]
i -= 1
continue
if feature != "s":
imgs_data.append(imgs[i][1].reshape((-1)))
else:
imgs_data.extend(imgs[i][1])
# print (image_cmp.shape)
imgs_meta.append(imgs[i][0])
# print(i)
# print(len(imgs))
#Handle Negative Value of NMF
if feature == 'm':
if negative_handle == 'h':
imgs_data = self.hist(imgs_data)
else:
imgs_data = self.normalize(imgs_data)
imgs_data = np.asarray(imgs_data)
# print(imgs_data.shape)
# print(imgs_meta)
# imgs_meta = [x[0] if x[0] in filteredImage for x in imgs]
imgs_zip = list(zip(imgs_meta, imgs_data))
db = PostgresDB(password=password,
host=host,
database=database,
user=user,
port=port)
conn = db.connect()
if meta:
imageDB.createInsertMeta(conn)
model = model.lower()
if feature == "s":
if imgs_data.shape[0] < no_clusters:
Kmeans = KMeans_SIFT(imgs_data.shape[0] // 2)
else:
Kmeans = KMeans_SIFT(no_clusters)
clusters = Kmeans.kmeans_process(imgs_data)
# print (imgs_zip)
imgs_data = Kmeans.newMatrixSift(imgs, clusters, kmeans_model)
imgs_zip = list(zip(imgs_meta, imgs_data))
if model == 'nmf':
w, h = self.nmf(imgs_data, k, technique_model)
imgs_red = np.dot(imgs_data, h.T).tolist()
print(np.asarray(w).shape)
print(np.asarray(h).shape)
imgs_sort = self.imgSort(w.T, imgs_meta)
feature_sort = self.imgFeatureSort(h, imgs_zip)
elif model == 'lda':
w, h = self.lda(imgs_data, k, technique_model)
imgs_red = np.dot(imgs_data, h.T).tolist()
print(np.asarray(w).shape)
print(np.asarray(h).shape)
imgs_sort = self.imgSort(w.T, imgs_meta)
feature_sort = self.imgFeatureSort(h, imgs_zip)
elif model == 'pca':
data, U, Vt = self.pca(imgs_data, k, technique_model)
imgs_red = data.tolist()
imgs_sort = self.imgSort(U.T, imgs_meta)
feature_sort = self.imgFeatureSort(Vt, imgs_zip)
elif model == 'svd':
# print(imgs_data.shape)
data, U, Vt = self.svd(imgs_data, k, technique_model)
imgs_red = data.tolist()
# print(im)
# U[:,:self.k].dot(Sigma[:self.k, :self.k]).dot(V[:self.k,:])
imgs_sort = self.imgSort(U.T, imgs_meta)
feature_sort = self.imgFeatureSort(Vt, imgs_zip)
# print("=======================")
# print(imgs_sort)
# print("=======================")
# print(feature_sort)
# Process the reduced Images
imgs_red = list(zip(imgs_meta, imgs_red))
# print (np.asarray(imgs_sort).shape)
# print(img_sort)
# print (np.asarray(feature_sort).shape)
# imgs_red = self.convString(imgs_red)
print(imgs_red)
self.createInsertDB(dbase, imgs_red, conn)
return imgs_sort, feature_sort
import imageProcess
import numpy as np
ip = imageProcess.imageProcess()
arg = input("Which task would you like to run (1/2/3)? ")
if arg == '1':
inp = input(
"Would you like to save SIFT features or Moment features (s/m)?")
ip.dbProcess(password='******', model=inp, process='s')
elif arg == '2':
inp1 = input(
"Would you like to fetch SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
rec = ip.dbProcess(password='******', model=inp1, process='f')
rec_arr = np.array(rec[0][1])
print('Features:', np.array(rec_arr))
print('Size', rec_arr.shape)
ip.writeFile(rec[0][1], 'Output\\Task2\\task2_{x}_{y}.txt'.format(x=inp1,
y=inp))
print('File saved to Output folder')
elif arg == '3':
inp1 = input(
"Would you like to Compare SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
inp2 = input(
"Provide the number of similar images you would like to return?")
recs = ip.dbProcess(password='******', model=inp1, process='f')
sim = ip.SimCalc(inp, recs, imgmodel=inp1, k=int(inp2))
"Please enter the home directory for the images "
"(Default: C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Dataset\\) : "
)
if path == '':
path = 'C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Dataset\\'
dim = dimReduction(path, '*.jpg')
feature = input(
'Please choose a feature model - SIFT(s), Moments(m), LBP(l), Histogram(h): '
)
if feature not in ('s', 'm', 'l', 'h'):
print('Please enter a valid feature model!')
exit()
technique = input(
'Please choose a dimensionality reduction technique - PCA(pca), SVD(svd), NMF(nmf), LDA(lda): '
)
image = input("Insert the name of your image: ")
k = input('Please provide the number of latent semantics(k): ')
label = input("Which label do you want: ")
label = label.replace(" ", "_")
db = 'imagedata_' + feature + '_' + technique + '_' + label
dim = dimReduction(path, '*.jpg')
task4 = imageProcess(path)
# filteredImage = task4.CSV(label)
task4.similarity(feature, technique, db, int(k), image, label)
# print('\n')
# print('Data Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Data_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
# print('\n')
# print('Feature Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Feature_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
import imageProcess
import numpy as np
ip = imageProcess.imageProcess(
dirpath='C:\\ASU\\Fall 2019\\MWDB\\Project\\Phase 2\\Dataset2\\')
arg = input("Which task would you like to run (1/2/3)? ")
if arg == '1':
# inp = input("Would you like to save SIFT features or Moment features (s/m)?")
for inp in ['s', 'm', 'l', 'h']:
print(inp)
ip.dbProcess(password='******', model=inp, process='s')
elif arg == '2':
inp1 = input(
"Would you like to fetch SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
rec = ip.dbProcess(password='******', model=inp1, process='f')
rec_arr = np.array(rec[0][1])
print('Features:', np.array(rec_arr))
print('Size', rec_arr.shape)
ip.writeFile(rec[0][1], 'Output\\Task2\\task2_{x}_{y}.txt'.format(x=inp1,
y=inp))
print('File saved to Output folder')
elif arg == '3':
inp1 = input(
"Would you like to Compare SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
inp2 = input(
"Provide the number of similar images you would like to return?")
if __name__ == "__main__":
video = cv2.VideoCapture(videoName)
showTrackbar()
while True:
success, img = video.read()
if not success:
video = cv2.VideoCapture(videoName)
continue
else:
img = cv2.resize(img, (640, 480))
ret, buffer = cv2.imencode('.jpg', img)
frame = buffer.tobytes()
img_show, detected, i_param = imageProcess(img)
# if videocap is None:
# videocap = cv2.VideoWriter(saveName, fourcc, 20.0, (640, 480))
# else:
# videocap.write(img_show)
k = cv2.waitKey(33) & 0xff
if k == 27: # press 'ESC' to quit
break
elif k == 64:
time.sleep(10)
# videocap.release()
video.release()
cv2.destroyAllWindows()
for d in kp:
idx = kmeans.predict([d])
histo[
idx] += 1 / nkp # Because we need normalized histograms, I prefere to add 1/nkp directly
histo_list.append(histo)
# print(np.asarray(histo_list).shape)
path = os.path.normpath(os.getcwd() + os.sep + os.pardir + os.sep +
'Models' + os.sep)
with open(path + os.sep + model + '.joblib', 'wb') as f1:
joblib.dump(kmeans, f1)
return np.asarray(histo_list)
imageDB = imageProcess(
'/home/anhnguyen/ASU/CSE-515/Project/Phase 2/Project - Phase 2/Data/Dataset2/'
)
imgs = imageDB.dbProcess(password='******',
process='f',
model='s',
dbase='imagedata_s')
# imgs_data = np.asarray(imgs)
imgs_data = []
i = -1
while i < len(imgs) - 1:
# print (x[1].shape)
i += 1
imgs_data.extend(imgs[i][1])
imgs_data = np.asarray(imgs_data)
import imageProcess
import numpy as np
ip = imageProcess.imageProcess('C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Dataset\\')
arg = input("Which task would you like to run (1/2/3)? ")
if arg == '1':
for x in ['s', 'l', 'h', 'm']:
print(x)
ip.dbProcess(password='******', model=x, process='s')
elif arg == '2':
inp1 = input("Would you like to fetch SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
rec = ip.dbProcess(password='******', model=inp1, process='f')
rec_arr = np.array(rec[0][1])
print('Features:', np.array(rec_arr))
print('Size', rec_arr.shape)
ip.writeFile(rec[0][1], 'Output\\Task2\\task2_{x}_{y}.txt'.format(x=inp1,
y=inp))
print('File saved to Output folder')
elif arg == '3':
inp1 = input("Would you like to Compare SIFT features or Moment features (s/m)?")
inp = input("Provide the image ID which you would like to display:")
inp2 = input("Provide the number of similar images you would like to return?")
recs = ip.dbProcess(password='******', model=inp1, process='f')
sim = ip.SimCalc(inp, recs, imgmodel=inp1, k=int(inp2))
sim_list = [im[0] for im in sim]
sim_list.insert(0, inp)
print('\n')
def saveDim(self,
feature,
model,
dbase,
k,
password='******',
host='localhost',
database='postgres',
user='******',
port=5432,
label=None,
meta=True,
negative_handle='n'):
imageDB = imageProcess(self.dirpath)
imgs = imageDB.dbProcess(password=password,
process='f',
model=feature,
dbase=dbase)
kmeans_model = 'kmeans_' + str(no_clusters) + '_' + feature
technique_model = feature + '_' + model
db = PostgresDB(password=password,
host=host,
database=database,
user=user,
port=port)
conn = db.connect()
if meta:
imageDB.createInsertMeta(conn)
if label is not None:
imgs = imageDB.CSV(conn, dbase, label)
label = label.replace(" ", "_")
dbase += '_' + model + '_' + label
kmeans_model += '_' + label
technique_model += '_' + label
else:
dbase += '_' + model
# print(technique_model)
imgs_data = []
imgs_meta = []
for img in imgs:
if feature == "s" or (feature == "m" and model in ("nmf", "lda")):
imgs_data.extend(img[1])
else:
imgs_data.append(img[1].reshape((-1)))
# print (image_cmp.shape)
imgs_meta.append(img[0])
# print(i)
# print(len(imgs))
# print(imgs_meta)
# print(len(imgs_meta))
#Handle Negative Value of NMF
# if feature == 'm' and (model == 'lda' or model == 'nmf'):
# print ("Normalize")
# if negative_handle == 'h':
# imgs_data = self.hist(imgs_data)
# else:
# imgs_data = self.normalize(imgs_data)
imgs_data = np.asarray(imgs_data)
# print(imgs_data.shape)
# print(imgs_data.shape)
# print(imgs_meta)
# imgs_meta = [x[0] if x[0] in filteredImage for x in imgs]
imgs_zip = list(zip(imgs_meta, imgs_data))
model = model.lower()
if feature == "s" or (feature == "m" and model in ("nmf", "lda")):
if imgs_data.shape[0] < no_clusters:
Kmeans = KMeans_SIFT(imgs_data.shape[0] // 2)
else:
Kmeans = KMeans_SIFT(no_clusters)
clusters = Kmeans.kmeans_process(imgs_data)
# print (imgs_zip)
imgs_data = Kmeans.newMatrixSift(imgs, clusters, kmeans_model)
imgs_zip = list(zip(imgs_meta, imgs_data))
if model == 'nmf':
w, h = self.nmf(imgs_data, k, technique_model)
imgs_red = np.dot(imgs_data, h.T).tolist()
# print(np.asarray(w).shape)
# print(np.asarray(h).shape)
imgs_sort = self.imgSort(w.T, imgs_meta)
feature_sort = self.imgFeatureSort(h, imgs_zip)
U = w
Vt = h
elif model == 'lda':
w, h = self.lda(imgs_data, k, technique_model)
imgs_red = np.dot(imgs_data, h.T).tolist()
# print(np.asarray(w).shape)
# print(np.asarray(h).shape)
imgs_sort = self.imgSort(w.T, imgs_meta)
feature_sort = self.imgFeatureSort(h, imgs_zip)
U = w
Vt = h
elif model == 'pca':
data, U, Vt = self.pca(imgs_data, k, technique_model)
imgs_red = data.tolist()
imgs_sort = self.imgSort(U.T, imgs_meta)
feature_sort = self.imgFeatureSort(Vt, imgs_zip)
elif model == 'svd':
# print(imgs_data.shape)
data, U, Vt = self.svd(imgs_data, k, technique_model)
imgs_red = data.tolist()
# print(im)
# U[:,:self.k].dot(Sigma[:self.k, :self.k]).dot(V[:self.k,:])
# print(U.T.shape)
# print(imgs_meta.shape)
imgs_sort = self.imgSort(U.T, imgs_meta)
feature_sort = self.imgFeatureSort(Vt, imgs_zip)
# print("=======================")
# print(imgs_sort)
# print("=======================")
# print(feature_sort)
# Process the reduced Images
imgs_red = list(zip(imgs_meta, imgs_red))
# print (np.asarray(imgs_sort).shape)
# print(img_sort)
# print (np.asarray(feature_sort).shape)
self.createInsertDB(dbase, imgs_red, conn)
return imgs_sort, feature_sort, U, Vt
import cv2
import numpy as np
import imageProcess
if __name__ == "__main__":
camera = cv2.VideoCapture(0)
camera.set(cv2.CAP_PROP_FRAME_WIDTH, 1280)
camera.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)
camera.set(cv2.CAP_PROP_FPS, 30)
imageProcess.showTrackbar()
while True:
success, ori_img = camera.read()
if not success:
break
else:
img = cv2.resize(ori_img[:, 160:1120], (640, 480))
ret, buffer = cv2.imencode('.jpg', img)
frame = buffer.tobytes()
imageProcess.imageProcess(img)
k = cv2.waitKey(33) & 0xff
if k == 27: # press 'ESC' to quit
break
elif k == 64:
time.sleep(5)
camera.release()
cv2.destroyAllWindows()
import numpy as np
from imageProcess import imageProcess
path = input("Please enter the home directory for the images "
"(Default: C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Hands_test2\\) : ")
if path == '':
path = 'C:\\Users\\pylak\\Documents\\Fall 2019\\MWDB\\Project\\Dataset\\'
dim = dimReduction(path, '*.jpg')
feature = input('Please choose a feature model - SIFT(s), Moments(m), LBP(l), Histogram(h): ')
if feature not in ('s', 'm', 'l', 'h'):
print('Please enter a valid feature model!')
exit()
technique = input('Please choose a dimensionality reduction technique - PCA(pca), SVD(svd), NMF(nmf), LDA(lda): ')
image = input("Insert the name of your image: ")
k = input('Please provide the number of latent semantics(k): ')
db = 'imagedata_' + feature + '_' + technique
task2 = imageProcess(path)
task2.similarity(feature, technique, db, int(k), image)
# similarity(feature, technique, db, int(k), image)
# imgs_sort, feature_sort = dim.saveDim(feature, technique, db, int(k))
# phase1 = imageProcess("/home/anhnguyen/ASU/CSE-515/Project/Phase 2/Project - Phase 2/Data/testset1/")
# print('\n')
# print('Data Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Data_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
# print('\n')
# print('Feature Latent Semantics Saved to Output Folder!')
# dim.writeFile(imgs_sort, 'Output\\Task1\\Feature_ls_{x}_{y}_{z}.txt'.format(x=feature,y=technique,z=k))
