def scan(file):
img_array = np.asarray(bytearray(file.stream.read()), dtype=np.uint8)
image = cv2.imdecode(img_array,0)
split_images = utils.splitImg(image)
ocr_texts = []
for i, split_image in enumerate(split_images):
image =utils.img2bwinv(split_image)
image = utils.dropZeroEdges(image)
image = utils.resize(image, ocr.image_height)
utils.save(image,os.path.join(curr_dir,"test","%s.png"%i))
maxImageWidth = image.shape[1]+5
image_vec = utils.img2vec(image,ocr.image_height,maxImageWidth)
ocr_inputs = np.zeros([1, maxImageWidth, ocr.image_height])
ocr_inputs[0,:] = np.transpose(image_vec.reshape((ocr.image_height,maxImageWidth)))
ocr_seq_len = np.ones(ocr_inputs.shape[0]) * maxImageWidth
feed = {inputs: ocr_inputs, seq_len: ocr_seq_len, input_keep_prob: 1.0}
start = time.time()
decoded_list = session.run(decoded[0], feed)
seconds = round(time.time() - start,2)
print("filished ocr %s , paid %s seconds" % (i,seconds))
detected_list = ocr.decode_sparse_tensor(decoded_list)
for detect_number in detected_list:
ocr_texts.append(ocr.list_to_chars(detect_number))
return ocr_texts
def scan(file):
img = Image.open(file.stream)
image = np.array(img)
image = utils.img2gray(image)
image = utils.clearImgGray(image)
utils.save(image, os.path.join(curr_dir,"test","src.png"))
split_images = utils.splitImg(image)
ocr_texts = []
for i, split_image in enumerate(split_images):
# image = utils.img2bwinv(split_image)
image = utils.clearImgGray(split_image)
# image = utils.clearBackgroundColor(image, 255)
image = 255. - image
image = utils.dropZeroEdges(image)
image = utils.resize(image, ocr.image_height)
utils.save(image,os.path.join(curr_dir,"test","%s.png"%i))
image = image / 255.
maxImageWidth = image.shape[1]
maxImageWidth = maxImageWidth + (ocr.POOL_SIZE - maxImageWidth % ocr.POOL_SIZE)
image_vec = utils.img2vec(image,ocr.image_height,maxImageWidth)
ocr_inputs = np.zeros([1, maxImageWidth, ocr.image_height])
ocr_inputs[0,:] = np.transpose(image_vec.reshape((ocr.image_height,maxImageWidth)))
ocr_seq_len = np.ones(ocr_inputs.shape[0]) * (maxImageWidth * ocr.image_height) // (ocr.POOL_SIZE * ocr.POOL_SIZE)
feed = {inputs: ocr_inputs, seq_len: ocr_seq_len, input_keep_prob: 1.0}
start = time.time()
decoded_list = session.run(decoded[0], feed)
seconds = round(time.time() - start,2)
print("filished ocr %s , paid %s seconds" % (i,seconds))
detected_list = ocr.decode_sparse_tensor(decoded_list)
for detect_number in detected_list:
ocr_texts.append(ocr.list_to_chars(detect_number))
return ocr_texts
def scan(file):
img = Image.open(file.stream)
image = np.array(img)
image = utils.img2gray(image)
utils.save(image * 255, os.path.join(curr_dir, "test", "p0.png"))
# image = utils.clearImgGray(image)
# utils.save(image * 255, os.path.join(curr_dir,"test","p1.png"))
split_images = utils.splitImg(image)
ocr_texts = []
for i, split_image in enumerate(split_images):
inv_image = utils.img2bwinv(split_image)
inv_image = utils.clearImg(inv_image)
image = 255. - split_image
image = utils.dropZeroEdges(inv_image, image)
image = utils.resize(image, ocr.image_height)
image = image / 255.
ocr_inputs = np.zeros([1, ocr.image_size, ocr.image_size])
ocr_inputs[0, :] = utils.square_img(
image, np.zeros([ocr.image_size, ocr.image_size]))
ocr_seq_len = np.ones(1) * (ocr.image_size * ocr.image_size) // (
ocr.POOL_SIZE * ocr.POOL_SIZE)
start = time.time()
p_net_g = session.run(net_g, {inputs: ocr_inputs})
p_net_g = np.squeeze(p_net_g, axis=3)
debug_net_g = np.copy(p_net_g)
for j in range(1):
_t_img = utils.unsquare_img(p_net_g[j], ocr.image_height)
_t_img_bin = np.copy(_t_img)
_t_img_bin[_t_img_bin <= 0.2] = 0
_t_img = utils.dropZeroEdges(_t_img_bin, _t_img, min_rate=0.1)
_t_img = utils.resize(_t_img, ocr.image_height)
if _t_img.shape[0] * _t_img.shape[
1] <= ocr.image_size * ocr.image_size:
p_net_g[j] = utils.square_img(
_t_img, np.zeros([ocr.image_size, ocr.image_size]),
ocr.image_height)
_img = np.vstack((ocr_inputs[0], debug_net_g[0], p_net_g[0]))
utils.save(_img * 255, os.path.join(curr_dir, "test", "%s.png" % i))
decoded_list = session.run(res_decoded[0], {
inputs: p_net_g,
seq_len: ocr_seq_len
})
seconds = round(time.time() - start, 2)
print("filished ocr %s , paid %s seconds" % (i, seconds))
detected_list = utils.decode_sparse_tensor(decoded_list)
for detect_number in detected_list:
ocr_texts.append(ocr.list_to_chars(detect_number))
return ocr_texts