You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
sbb_binarization/sbb_binarize/sbb_binarize.py

229 lines
9.7 KiB
Python

"""
Tool to load model and binarize a given image.
"""
import sys
from os import listdir, environ, devnull
from os.path import join
from warnings import catch_warnings, simplefilter
import numpy as np
from PIL import Image
import cv2
environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
stderr = sys.stderr
sys.stderr = open(devnull, 'w')
from keras.models import load_model
sys.stderr = stderr
import tensorflow as tf
def resize_image(img_in, input_height, input_width):
return cv2.resize(img_in, (input_width, input_height), interpolation=cv2.INTER_NEAREST)
class SbbBinarizer:
# TODO use True/False for patches
def __init__(self, model, image=None, image_path=None, patches='false', save=None):
if (image is not None and image_path is not None) or \
(image is None and image_path is None):
raise ValueError("Must pass either a opencv2 image or an image_path")
if image is not None:
self.image = image
else:
self.image = cv2.imread(self.image)
self.patches = patches
self.save = save
self.model_dir = model
def start_new_session_and_model(self):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
self.session = tf.Session(config=config) # tf.InteractiveSession()
def load_model(self, model_name):
self.model = load_model(join(self.model_dir, model_name), compile=False)
self.img_height = self.model.layers[len(self.model.layers)-1].output_shape[1]
self.img_width = self.model.layers[len(self.model.layers)-1].output_shape[2]
self.n_classes = self.model.layers[len(self.model.layers)-1].output_shape[3]
def end_session(self):
self.session.close()
del self.model
del self.session
def predict(self,model_name):
self.load_model(model_name)
img = self.image
img_width_model = self.img_width
img_height_model = self.img_height
if self.patches in ('true', 'True'):
margin = int(0.1 * img_width_model)
width_mid = img_width_model - 2 * margin
height_mid = img_height_model - 2 * margin
img = img / float(255.0)
img_h = img.shape[0]
img_w = img.shape[1]
prediction_true = np.zeros((img_h, img_w, 3))
mask_true = np.zeros((img_h, img_w))
nxf = img_w / float(width_mid)
nyf = img_h / float(height_mid)
if nxf > int(nxf):
nxf = int(nxf) + 1
else:
nxf = int(nxf)
if nyf > int(nyf):
nyf = int(nyf) + 1
else:
nyf = int(nyf)
for i in range(nxf):
for j in range(nyf):
if i == 0:
index_x_d = i * width_mid
index_x_u = index_x_d + img_width_model
elif i > 0:
index_x_d = i * width_mid
index_x_u = index_x_d + img_width_model
if j == 0:
index_y_d = j * height_mid
index_y_u = index_y_d + img_height_model
elif j > 0:
index_y_d = j * height_mid
index_y_u = index_y_d + img_height_model
if index_x_u > img_w:
index_x_u = img_w
index_x_d = img_w - img_width_model
if index_y_u > img_h:
index_y_u = img_h
index_y_d = img_h - img_height_model
img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :]
label_p_pred = self.model.predict(img_patch.reshape(1, img_patch.shape[0], img_patch.shape[1], img_patch.shape[2]))
seg = np.argmax(label_p_pred, axis=3)[0]
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
if i == 0 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, 0:seg.shape[1] - margin]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i == nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - 0]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i == 0 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, 0:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i == nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - 0]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i == 0 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, 0:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i == nxf-1 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - 0]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i != 0 and i != nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - margin]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
elif i != 0 and i != nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin, :] = seg_color
else:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
prediction_true = prediction_true.astype(np.uint8)
else:
img_h_page = img.shape[0]
img_w_page = img.shape[1]
img = img / float(255.0)
img = resize_image(img, img_height_model, img_width_model)
label_p_pred = self.model.predict(
img.reshape(1, img.shape[0], img.shape[1], img.shape[2]))
seg = np.argmax(label_p_pred, axis=3)[0]
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
prediction_true = resize_image(seg_color, img_h_page, img_w_page)
prediction_true = prediction_true.astype(np.uint8)
return prediction_true[:,:,0]
def run(self):
self.start_new_session_and_model()
models_n = listdir(self.model_dir)
img_last = 0
for model_in in models_n:
res = self.predict(model_in)
img_fin = np.zeros((res.shape[0], res.shape[1], 3))
res[:, :][res[:, :] == 0] = 2
res = res-1
res = res*255
img_fin[:, :, 0] = res
img_fin[:, :, 1] = res
img_fin[:, :, 2] = res
img_fin = img_fin.astype(np.uint8)
img_fin = (res[:, :] == 0)*255
img_last = img_last+img_fin
kernel = np.ones((5, 5), np.uint8)
img_last[:, :][img_last[:, :] > 0] = 255
img_last = (img_last[:, :] == 0)*255
if self.save:
cv2.imwrite(self.save, img_last)
return img_last