forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #435 from LDOUBLEV/fixocr 

read gif read func
This commit is contained in:
littletomatodonkey 2020-07-29 22:51:58 +08:00 committed by GitHub
parent 301aac1cae aa6e29cf04
commit 8f175aade7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 56 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ppocr/data/det/db_process.py
View File

@ -17,7 +17,7 @@ import cv2
import numpy as np
import json
import sys
from ppocr.utils.utility import initial_logger
from ppocr.utils.utility import initial_logger, check_and_read_gif
logger = initial_logger()
from .data_augment import AugmentData
@ -100,7 +100,9 @@ class DBProcessTrain(object):
def __call__(self, label_infor):
img_path, gt_label = self.convert_label_infor(label_infor)
imgvalue = cv2.imread(img_path)
imgvalue, flag = check_and_read_gif(img_path)
if not flag:
imgvalue = cv2.imread(img_path)
if imgvalue is None:
logger.info("{} does not exist!".format(img_path))
return None

17
ppocr/utils/utility.py
View File

@ -15,6 +15,8 @@
import logging
import os
import imghdr
import cv2
from paddle import fluid
def initial_logger():
@ -62,7 +64,7 @@ def get_image_file_list(img_file):
if img_file is None or not os.path.exists(img_file):
raise Exception("not found any img file in {}".format(img_file))
img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff'}
img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif', 'GIF'}
if os.path.isfile(img_file) and imghdr.what(img_file) in img_end:
imgs_lists.append(img_file)
elif os.path.isdir(img_file):
@ -75,7 +77,18 @@ def get_image_file_list(img_file):
return imgs_lists
from paddle import fluid
def check_and_read_gif(img_path):
if os.path.basename(img_path)[-3:] in ['gif', 'GIF']:
gif = cv2.VideoCapture(img_path)
ret, frame = gif.read()
if not ret:
logging.info("Cannot read {}. This gif image maybe corrupted.")
return None, False
if len(frame.shape) == 2 or frame.shape[-1] == 1:
frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB)
imgvalue = frame[:, :, ::-1]
return imgvalue, True
return None, False
def create_multi_devices_program(program, loss_var_name):

6
tools/infer/predict_det.py
View File

@ -20,7 +20,7 @@ sys.path.append(os.path.join(__dir__, '../..'))
import tools.infer.utility as utility
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.utility import get_image_file_list
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
import cv2
from ppocr.data.det.east_process import EASTProcessTest
from ppocr.data.det.db_process import DBProcessTest
@ -139,7 +139,9 @@ if __name__ == "__main__":
if not os.path.exists(draw_img_save):
os.makedirs(draw_img_save)
for image_file in image_file_list:
img = cv2.imread(image_file)
img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file)
if img is None:
logger.info("error in loading image:{}".format(image_file))
continue

6
tools/infer/predict_rec.py
View File

@ -20,7 +20,7 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
import tools.infer.utility as utility
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.utility import get_image_file_list
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
import cv2
import copy
import numpy as np
@ -153,7 +153,9 @@ def main(args):
valid_image_file_list = []
img_list = []
for image_file in image_file_list:
img = cv2.imread(image_file, cv2.IMREAD_COLOR)
img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file)
if img is None:
logger.info("error in loading image:{}".format(image_file))
continue

46
tools/infer/predict_system.py
View File

@ -27,7 +27,7 @@ import copy
import numpy as np
import math
import time
from ppocr.utils.utility import get_image_file_list
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from PIL import Image
from tools.infer.utility import draw_ocr
from tools.infer.utility import draw_ocr_box_txt
@ -49,18 +49,23 @@ class TextSystem(object):
points[:, 0] = points[:, 0] - left
points[:, 1] = points[:, 1] - top
'''
img_crop_width = int(max(np.linalg.norm(points[0] - points[1]),
np.linalg.norm(points[2] - points[3])))
img_crop_height = int(max(np.linalg.norm(points[0] - points[3]),
np.linalg.norm(points[1] - points[2])))
pts_std = np.float32([[0, 0],
[img_crop_width, 0],
img_crop_width = int(
max(
np.linalg.norm(points[0] - points[1]),
np.linalg.norm(points[2] - points[3])))
img_crop_height = int(
max(
np.linalg.norm(points[0] - points[3]),
np.linalg.norm(points[1] - points[2])))
pts_std = np.float32([[0, 0], [img_crop_width, 0],
[img_crop_width, img_crop_height],
[0, img_crop_height]])
M = cv2.getPerspectiveTransform(points, pts_std)
dst_img = cv2.warpPerspective(img, M, (img_crop_width, img_crop_height),
borderMode=cv2.BORDER_REPLICATE,
flags=cv2.INTER_CUBIC)
dst_img = cv2.warpPerspective(
img,
M, (img_crop_width, img_crop_height),
borderMode=cv2.BORDER_REPLICATE,
flags=cv2.INTER_CUBIC)
dst_img_height, dst_img_width = dst_img.shape[0:2]
if dst_img_height * 1.0 / dst_img_width >= 1.5:
dst_img = np.rot90(dst_img)
@ -119,25 +124,27 @@ def main(args):
is_visualize = True
tackle_img_num = 0
for image_file in image_file_list:
img = cv2.imread(image_file)
img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file)
if img is None:
logger.info("error in loading image:{}".format(image_file))
continue
starttime = time.time()
tackle_img_num += 1
if not args.use_gpu and args.enable_mkldnn and tackle_img_num % 30 == 0:
tackle_img_num += 1
if not args.use_gpu and args.enable_mkldnn and tackle_img_num % 30 == 0:
text_sys = TextSystem(args)
dt_boxes, rec_res = text_sys(img)
elapse = time.time() - starttime
print("Predict time of %s: %.3fs" % (image_file, elapse))
drop_score = 0.5
dt_num = len(dt_boxes)
dt_boxes_final = []
for dno in range(dt_num):
text, score = rec_res[dno]
if score >= 0.5:
if score >= drop_score:
text_str = "%s, %.3f" % (text, score)
print(text_str)
dt_boxes_final.append(dt_boxes[dno])
if is_visualize:
image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
@ -146,7 +153,12 @@ def main(args):
scores = [rec_res[i][1] for i in range(len(rec_res))]
draw_img = draw_ocr(
image, boxes, txts, scores, draw_txt=True, drop_score=0.5)
image,
boxes,
txts,
scores,
draw_txt=True,
drop_score=drop_score)
draw_img_save = "./inference_results/"
if not os.path.exists(draw_img_save):
os.makedirs(draw_img_save)