PaddleOCR/ppocr/data/rec/text_image_aug/augment.py

108 lines
2.8 KiB
Python

# -*- coding:utf-8 -*-
# Author: RubanSeven
# Reference: https://github.com/RubanSeven/Text-Image-Augmentation-python
# import cv2
import numpy as np
from .warp_mls import WarpMLS
def tia_distort(src, segment=4):
img_h, img_w = src.shape[:2]
cut = img_w // segment
thresh = cut // 3
src_pts = list()
dst_pts = list()
src_pts.append([0, 0])
src_pts.append([img_w, 0])
src_pts.append([img_w, img_h])
src_pts.append([0, img_h])
dst_pts.append([np.random.randint(thresh), np.random.randint(thresh)])
dst_pts.append(
[img_w - np.random.randint(thresh), np.random.randint(thresh)])
dst_pts.append(
[img_w - np.random.randint(thresh), img_h - np.random.randint(thresh)])
dst_pts.append(
[np.random.randint(thresh), img_h - np.random.randint(thresh)])
half_thresh = thresh * 0.5
for cut_idx in np.arange(1, segment, 1):
src_pts.append([cut * cut_idx, 0])
src_pts.append([cut * cut_idx, img_h])
dst_pts.append([
cut * cut_idx + np.random.randint(thresh) - half_thresh,
np.random.randint(thresh) - half_thresh
])
dst_pts.append([
cut * cut_idx + np.random.randint(thresh) - half_thresh,
img_h + np.random.randint(thresh) - half_thresh
])
trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h)
dst = trans.generate()
return dst
def tia_stretch(src, segment=4):
img_h, img_w = src.shape[:2]
cut = img_w // segment
thresh = cut * 4 // 5
src_pts = list()
dst_pts = list()
src_pts.append([0, 0])
src_pts.append([img_w, 0])
src_pts.append([img_w, img_h])
src_pts.append([0, img_h])
dst_pts.append([0, 0])
dst_pts.append([img_w, 0])
dst_pts.append([img_w, img_h])
dst_pts.append([0, img_h])
half_thresh = thresh * 0.5
for cut_idx in np.arange(1, segment, 1):
move = np.random.randint(thresh) - half_thresh
src_pts.append([cut * cut_idx, 0])
src_pts.append([cut * cut_idx, img_h])
dst_pts.append([cut * cut_idx + move, 0])
dst_pts.append([cut * cut_idx + move, img_h])
trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h)
dst = trans.generate()
return dst
def tia_perspective(src):
img_h, img_w = src.shape[:2]
thresh = img_h // 2
src_pts = list()
dst_pts = list()
src_pts.append([0, 0])
src_pts.append([img_w, 0])
src_pts.append([img_w, img_h])
src_pts.append([0, img_h])
dst_pts.append([0, np.random.randint(thresh)])
dst_pts.append([img_w, np.random.randint(thresh)])
dst_pts.append([img_w, img_h - np.random.randint(thresh)])
dst_pts.append([0, img_h - np.random.randint(thresh)])
trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h)
dst = trans.generate()
return dst