def calculat_hsv_model(part_of_data, image_temp_dir):
content = []
for line in part_of_data:
line_fields = line.rsplit(',')
if (len(line_fields) == 1):
line_fields = line.rsplit("\t")
image_url = line_fields[0]
utils.crawl_image_from_url(image_url, image_temp_dir + '/temp.jpg')
im = Image.open(image_temp_dir + '/temp.jpg')
pix = im.load()
hue = []
satuation = []
value = []
(image_width, image_height) = im.size
for index_x in range(image_width):
for index_y in range(image_height):
pixel = pix[index_x, index_y]
(red, green, blue, alpha) = (0, 0, 0, 0)
if len(pixel) == 3:
(red, green, blue) = pixel
elif len(pixel) == 4:
(red, green, blue, alpha) = pixel
red /= float(255)
green /= float(255)
blue /= float(255)
(h, s, v) = colorsys.rgb_to_hsv(red, green, blue)
hue.append(h)
satuation.append(s)
value.append(v)
#print(str(red) + " " + str(green) + " " + str(blue))
#print(str(h) + " " + str(s) + " " + str(v))
mean_hsu = mean(hue)
mean_satuation = mean(satuation)
mean_value = mean(value)
line_fields.append(str(mean_hsu))
line_fields.append(str(mean_satuation))
line_fields.append(str(mean_value))
content.append(",".join(line_fields))
return content
def calculat_hsv_model(part_of_data, image_temp_dir):
content = []
for line in part_of_data:
line_fields = line.rsplit(",")
if len(line_fields) == 1:
line_fields = line.rsplit("\t")
image_url = line_fields[0]
utils.crawl_image_from_url(image_url, image_temp_dir + "/temp.jpg")
im = Image.open(image_temp_dir + "/temp.jpg")
pix = im.load()
hue = []
satuation = []
value = []
(image_width, image_height) = im.size
for index_x in range(image_width):
for index_y in range(image_height):
pixel = pix[index_x, index_y]
(red, green, blue, alpha) = (0, 0, 0, 0)
if len(pixel) == 3:
(red, green, blue) = pixel
elif len(pixel) == 4:
(red, green, blue, alpha) = pixel
red /= float(255)
green /= float(255)
blue /= float(255)
(h, s, v) = colorsys.rgb_to_hsv(red, green, blue)
hue.append(h)
satuation.append(s)
value.append(v)
# print(str(red) + " " + str(green) + " " + str(blue))
# print(str(h) + " " + str(s) + " " + str(v))
mean_hsu = mean(hue)
mean_satuation = mean(satuation)
mean_value = mean(value)
line_fields.append(str(mean_hsu))
line_fields.append(str(mean_satuation))
line_fields.append(str(mean_value))
content.append(",".join(line_fields))
return content
def main():
parser = argparse.ArgumentParser(description = 'Analyze HIT results submitted by Amazon Mechnical Turk workers.')
parser.add_argument('-f', help = 'The mtk data source file.')
parser.add_argument('-d', help = 'The image path')
args = parser.parse_args()
if (args.f != None):
file_urls = utils.load_file(args.f)
data_metainfo = hit.regex_datasource(file_urls)
# data_labels: flickr high interesting 1, flickr low interesting 2, pinterest [3, 4, 5]
data_labels = data_metainfo[0]
# data_ids: (flickr, pinterest) image id
data_ids = data_metainfo[1]
count = 0
for url in file_urls:
utils.crawl_image_from_url(url, args.d + '/' + data_ids[count] + '.jpg')
count += 1
def calculat_facedetection_model(part_of_data, image_temp_dir,
cascade_filename):
cascade = facedetect.load_cascade(cascade_filename)
content = []
for line in part_of_data:
line_fields = line.rsplit(',')
if (len(line_fields) == 1):
line_fields = line.rsplit("\t")
image_url = line_fields[0]
utils.crawl_image_from_url(image_url, image_temp_dir + '/temp.jpg')
level = facedetect.detect(image_temp_dir + '/temp.jpg', cascade)
print(level)
line_fields.append(str(level))
content.append(",".join(line_fields))
return content
def calculat_facedetection_model(part_of_data, image_temp_dir, cascade_filename):
cascade = facedetect.load_cascade(cascade_filename)
content = []
for line in part_of_data:
line_fields = line.rsplit(',')
if (len(line_fields) == 1):
line_fields = line.rsplit("\t")
image_url = line_fields[0]
utils.crawl_image_from_url(image_url, image_temp_dir + '/temp.jpg')
level = facedetect.detect(image_temp_dir + '/temp.jpg', cascade)
print(level)
line_fields.append(str(level))
content.append(",".join(line_fields))
return content
