def experiment_yen_threshold(image=None):
images = image_generator()
if image is not None:
img_path = os.path.join(BASE_DIR, "data/imgs/")
fn = os.path.join(img_path, image)
im = load_images([fn])[0].astype("int32")
images = itertools.chain([(fn, im)], images)
for fn, im in images:
imgs = [im]
titles = ["Original"]
print("computing yen threshold")
yen = threshold_yen(im)
channels = threshold_by_channel(im, yen)
titles.append("Yen Thresholded")
imgs.append(channels[0])
for cp in [175, 200, 225, 250]:
titles.append("Cutpoint %d" % cp)
print("cutting")
rtn = np.zeros(im.shape)
rtn[np.average(im, axis=2, weights=[0.7, 0.1, 0.2]) > cp, 0] = 255
for i in range(1, 3):
rtn[:, :, i] = rtn[:, :, 0]
imgs.append(rtn)
print("plotting")
plot_images(imgs, titles=titles, suptitle=fn.split("/")[-1])
def add_image_to_image_generator(images, file=None):
if file is not None:
path = os.path.join(BASE_DIR, "data/imgs/")
path = os.path.join(path, file)
image = load_images(path).astype("int32")
images = itertools.chain([(path, image)], images)
return images
def image_generator():
csv_path = os.path.join(BASE_DIR, "data/train.csv")
img_path = os.path.join(BASE_DIR, "data/imgs/")
images = os.listdir(img_path)
shuffle(images)
for idx, im in enumerate(images):
im = os.path.join(img_path, im)
image = load_images([im])[0].astype("int32")
yield im, image
def main(csv_path=os.path.join(BASE_DIR, 'data/train.csv'),
img_path=os.path.join(BASE_DIR, 'data/imgs/')):
whale_index = pd.read_csv(csv_path)
image_file_names = lookup_whale_images(whale_index, whale_id='whale_78785')
image_arrays = load_images(image_file_names)
image_file = image_file_names[0]
image = image_arrays[0]
resized_array = resize_images(image_arrays)
transformed_array = transform_images(resized_array)
t_im_1 = transformed_array[0].reshape((3, 300, 300)).transpose(1, 2, 0)
t_im_2 = transformed_array[1].reshape((3, 300, 300)).transpose(1, 2, 0)
plot_images([t_im_1, t_im_2],['transformed image 1','transformed image 2'])