├── .gitignore ├── LICENSE ├── README.md ├── augment.py ├── demo.py ├── imgs ├── demo.png ├── distort.gif ├── perspective.gif └── stretch.gif └── warp_mls.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Text Image Augmentation 2 | 3 | [![Build Status](https://travis-ci.org/Canjie-Luo/Text-Image-Augmentation.svg?branch=master)](https://travis-ci.org/Canjie-Luo/Text-Image-Augmentation) 4 | 5 | A general geometric augmentation tool for text images in the CVPR 2020 paper "Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition". We provide the tool to avoid overfitting and gain robustness of text recognizers. 6 | 7 | Note that this is a general toolkit. Please customize for your specific task. If the repo benefits your work, please cite the papers. 8 | 9 | ## Requirements 10 | 11 | - [Python](https://www.python.org/) 3.6.4 12 | - [Numpy](https://numpy.org/) 1.14.0 13 | 14 | ## Demo 15 | 16 | - Distortion 17 | 18 | ![](imgs/distort.gif) 19 | 20 | - Stretch 21 | 22 | ![](imgs/stretch.gif) 23 | 24 | - Perspective 25 | 26 | ![](imgs/perspective.gif) 27 | 28 | ## Speed 29 | 30 | To transform an image with size (H:64, W:200), it takes less than 14ms using a 2.5GHz CPU. It is possible to accelerate the process by calling multi-process batch samplers in an on-the-fly manner, such as setting [**\"num_workers\"**](https://pytorch.org/docs/0.3.1/data.html?highlight=dataset#torch.utils.data.DataLoader) in [PyTorch](https://pytorch.org/docs/0.3.1/data.html?highlight=dataset#torch.utils.data.DataLoader). 31 | 32 | ## Attention 33 | Modify from https://github.com/Canjie-Luo/Text-Image-Augmentation.git. 34 | -------------------------------------------------------------------------------- /augment.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # Author: RubanSeven 3 | 4 | # import cv2 5 | import numpy as np 6 | # from transform import get_perspective_transform, warp_perspective 7 | from warp_mls import WarpMLS 8 | 9 | 10 | def distort(src, segment): 11 | img_h, img_w = src.shape[:2] 12 | 13 | cut = img_w // segment 14 | thresh = cut // 3 15 | # thresh = img_h // segment // 3 16 | # thresh = img_h // 5 17 | 18 | src_pts = list() 19 | dst_pts = list() 20 | 21 | src_pts.append([0, 0]) 22 | src_pts.append([img_w, 0]) 23 | src_pts.append([img_w, img_h]) 24 | src_pts.append([0, img_h]) 25 | 26 | dst_pts.append([np.random.randint(thresh), np.random.randint(thresh)]) 27 | dst_pts.append([img_w - np.random.randint(thresh), np.random.randint(thresh)]) 28 | dst_pts.append([img_w - np.random.randint(thresh), img_h - np.random.randint(thresh)]) 29 | dst_pts.append([np.random.randint(thresh), img_h - np.random.randint(thresh)]) 30 | 31 | half_thresh = thresh * 0.5 32 | 33 | for cut_idx in np.arange(1, segment, 1): 34 | src_pts.append([cut * cut_idx, 0]) 35 | src_pts.append([cut * cut_idx, img_h]) 36 | dst_pts.append([cut * cut_idx + np.random.randint(thresh) - half_thresh, 37 | np.random.randint(thresh) - half_thresh]) 38 | dst_pts.append([cut * cut_idx + np.random.randint(thresh) - half_thresh, 39 | img_h + np.random.randint(thresh) - half_thresh]) 40 | 41 | trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h) 42 | dst = trans.generate() 43 | 44 | return dst 45 | 46 | 47 | def stretch(src, segment): 48 | img_h, img_w = src.shape[:2] 49 | 50 | cut = img_w // segment 51 | thresh = cut * 4 // 5 52 | # thresh = img_h // segment // 3 53 | # thresh = img_h // 5 54 | 55 | src_pts = list() 56 | dst_pts = list() 57 | 58 | src_pts.append([0, 0]) 59 | src_pts.append([img_w, 0]) 60 | src_pts.append([img_w, img_h]) 61 | src_pts.append([0, img_h]) 62 | 63 | dst_pts.append([0, 0]) 64 | dst_pts.append([img_w, 0]) 65 | dst_pts.append([img_w, img_h]) 66 | dst_pts.append([0, img_h]) 67 | 68 | half_thresh = thresh * 0.5 69 | 70 | for cut_idx in np.arange(1, segment, 1): 71 | move = np.random.randint(thresh) - half_thresh 72 | src_pts.append([cut * cut_idx, 0]) 73 | src_pts.append([cut * cut_idx, img_h]) 74 | dst_pts.append([cut * cut_idx + move, 0]) 75 | dst_pts.append([cut * cut_idx + move, img_h]) 76 | 77 | trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h) 78 | dst = trans.generate() 79 | 80 | return dst 81 | 82 | 83 | def perspective(src): 84 | img_h, img_w = src.shape[:2] 85 | 86 | thresh = img_h // 2 87 | 88 | src_pts = list() 89 | dst_pts = list() 90 | 91 | src_pts.append([0, 0]) 92 | src_pts.append([img_w, 0]) 93 | src_pts.append([img_w, img_h]) 94 | src_pts.append([0, img_h]) 95 | 96 | dst_pts.append([0, np.random.randint(thresh)]) 97 | dst_pts.append([img_w, np.random.randint(thresh)]) 98 | dst_pts.append([img_w, img_h - np.random.randint(thresh)]) 99 | dst_pts.append([0, img_h - np.random.randint(thresh)]) 100 | 101 | trans = WarpMLS(src, src_pts, dst_pts, img_w, img_h) 102 | dst = trans.generate() 103 | 104 | return dst 105 | 106 | # def distort(src, segment): 107 | # img_h, img_w = src.shape[:2] 108 | # dst = np.zeros_like(src, dtype=np.uint8) 109 | # 110 | # cut = img_w // segment 111 | # thresh = img_h // 8 112 | # 113 | # src_pts = list() 114 | # # dst_pts = list() 115 | # 116 | # src_pts.append([-np.random.randint(thresh), -np.random.randint(thresh)]) 117 | # src_pts.append([-np.random.randint(thresh), img_h + np.random.randint(thresh)]) 118 | # 119 | # # dst_pts.append([0, 0]) 120 | # # dst_pts.append([0, img_h]) 121 | # dst_box = np.array([[0, 0], [0, img_h], [cut, 0], [cut, img_h]], dtype=np.float32) 122 | # 123 | # half_thresh = thresh * 0.5 124 | # 125 | # for cut_idx in np.arange(1, segment, 1): 126 | # src_pts.append([cut * cut_idx + np.random.randint(thresh) - half_thresh, 127 | # np.random.randint(thresh) - half_thresh]) 128 | # src_pts.append([cut * cut_idx + np.random.randint(thresh) - half_thresh, 129 | # img_h + np.random.randint(thresh) - half_thresh]) 130 | # 131 | # # dst_pts.append([cut * i, 0]) 132 | # # dst_pts.append([cut * i, img_h]) 133 | # 134 | # src_box = np.array(src_pts[-4:-2] + src_pts[-2:-1] + src_pts[-1:], dtype=np.float32) 135 | # 136 | # # mat = cv2.getPerspectiveTransform(src_box, dst_box) 137 | # # print(mat) 138 | # # dst[:, cut * (cut_idx - 1):cut * cut_idx] = cv2.warpPerspective(src, mat, (cut, img_h)) 139 | # 140 | # mat = get_perspective_transform(dst_box, src_box) 141 | # dst[:, cut * (cut_idx - 1):cut * cut_idx] = warp_perspective(src, mat, (cut, img_h)) 142 | # # print(mat) 143 | # 144 | # src_pts.append([img_w + np.random.randint(thresh) - half_thresh, 145 | # np.random.randint(thresh) - half_thresh]) 146 | # src_pts.append([img_w + np.random.randint(thresh) - half_thresh, 147 | # img_h + np.random.randint(thresh) - half_thresh]) 148 | # src_box = np.array(src_pts[-4:-2] + src_pts[-2:-1] + src_pts[-1:], dtype=np.float32) 149 | # 150 | # # mat = cv2.getPerspectiveTransform(src_box, dst_box) 151 | # # dst[:, cut * (segment - 1):] = cv2.warpPerspective(src, mat, (img_w - cut * (segment - 1), img_h)) 152 | # mat = get_perspective_transform(dst_box, src_box) 153 | # dst[:, cut * (segment - 1):] = warp_perspective(src, mat, (img_w - cut * (segment - 1), img_h)) 154 | # 155 | # return dst 156 | -------------------------------------------------------------------------------- /demo.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # Author: RubanSeven 3 | 4 | import cv2 5 | import imageio 6 | from augment import distort, stretch, perspective 7 | 8 | 9 | def create_gif(image_list, gif_name, duration=0.1): 10 | frames = [] 11 | for image in image_list: 12 | frames.append(image) 13 | imageio.mimsave(gif_name, frames, 'GIF', duration=duration) 14 | return 15 | 16 | 17 | if __name__ == '__main__': 18 | im = cv2.imread("imgs/demo.png") 19 | im = cv2.resize(im, (200, 64)) 20 | cv2.imshow("im_CV", im) 21 | distort_img_list = list() 22 | stretch_img_list = list() 23 | perspective_img_list = list() 24 | for i in range(12): 25 | distort_img = distort(im, 4) 26 | distort_img_list.append(distort_img) 27 | cv2.imshow("distort_img", distort_img) 28 | 29 | stretch_img = stretch(im, 4) 30 | cv2.imshow("stretch_img", stretch_img) 31 | stretch_img_list.append(stretch_img) 32 | 33 | perspective_img = perspective(im) 34 | cv2.imshow("perspective_img", perspective_img) 35 | perspective_img_list.append(perspective_img) 36 | cv2.waitKey(100) 37 | 38 | create_gif(distort_img_list, r'imgs/distort.gif') 39 | create_gif(stretch_img_list, r'imgs/stretch.gif') 40 | create_gif(perspective_img_list, r'imgs/perspective.gif') 41 | -------------------------------------------------------------------------------- /imgs/demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RubanSeven/Text-Image-Augmentation-python/a4b190d5e188b932cf7fc69c26568be156383c89/imgs/demo.png -------------------------------------------------------------------------------- /imgs/distort.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RubanSeven/Text-Image-Augmentation-python/a4b190d5e188b932cf7fc69c26568be156383c89/imgs/distort.gif -------------------------------------------------------------------------------- /imgs/perspective.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RubanSeven/Text-Image-Augmentation-python/a4b190d5e188b932cf7fc69c26568be156383c89/imgs/perspective.gif -------------------------------------------------------------------------------- /imgs/stretch.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RubanSeven/Text-Image-Augmentation-python/a4b190d5e188b932cf7fc69c26568be156383c89/imgs/stretch.gif -------------------------------------------------------------------------------- /warp_mls.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # Author: RubanSeven 3 | import math 4 | 5 | import numpy as np 6 | 7 | 8 | class WarpMLS: 9 | def __init__(self, src, src_pts, dst_pts, dst_w, dst_h, trans_ratio=1.): 10 | self.src = src 11 | self.src_pts = src_pts 12 | self.dst_pts = dst_pts 13 | self.pt_count = len(self.dst_pts) 14 | self.dst_w = dst_w 15 | self.dst_h = dst_h 16 | self.trans_ratio = trans_ratio 17 | self.grid_size = 100 18 | self.rdx = np.zeros((self.dst_h, self.dst_w)) 19 | self.rdy = np.zeros((self.dst_h, self.dst_w)) 20 | 21 | @staticmethod 22 | def __bilinear_interp(x, y, v11, v12, v21, v22): 23 | return (v11 * (1 - y) + v12 * y) * (1 - x) + (v21 * (1 - y) + v22 * y) * x 24 | 25 | def generate(self): 26 | self.calc_delta() 27 | return self.gen_img() 28 | 29 | def calc_delta(self): 30 | w = np.zeros(self.pt_count, dtype=np.float32) 31 | 32 | if self.pt_count < 2: 33 | return 34 | 35 | i = 0 36 | while 1: 37 | if self.dst_w <= i < self.dst_w + self.grid_size - 1: 38 | i = self.dst_w - 1 39 | elif i >= self.dst_w: 40 | break 41 | 42 | j = 0 43 | while 1: 44 | if self.dst_h <= j < self.dst_h + self.grid_size - 1: 45 | j = self.dst_h - 1 46 | elif j >= self.dst_h: 47 | break 48 | 49 | sw = 0 50 | swp = np.zeros(2, dtype=np.float32) 51 | swq = np.zeros(2, dtype=np.float32) 52 | new_pt = np.zeros(2, dtype=np.float32) 53 | cur_pt = np.array([i, j], dtype=np.float32) 54 | 55 | k = 0 56 | for k in range(self.pt_count): 57 | if i == self.dst_pts[k][0] and j == self.dst_pts[k][1]: 58 | break 59 | 60 | w[k] = 1. / ((i - self.dst_pts[k][0]) * (i - self.dst_pts[k][0]) + 61 | (j - self.dst_pts[k][1]) * (j - self.dst_pts[k][1])) 62 | 63 | sw += w[k] 64 | swp = swp + w[k] * np.array(self.dst_pts[k]) 65 | swq = swq + w[k] * np.array(self.src_pts[k]) 66 | 67 | if k == self.pt_count - 1: 68 | pstar = 1 / sw * swp 69 | qstar = 1 / sw * swq 70 | 71 | miu_s = 0 72 | for k in range(self.pt_count): 73 | if i == self.dst_pts[k][0] and j == self.dst_pts[k][1]: 74 | continue 75 | pt_i = self.dst_pts[k] - pstar 76 | miu_s += w[k] * np.sum(pt_i * pt_i) 77 | 78 | cur_pt -= pstar 79 | cur_pt_j = np.array([-cur_pt[1], cur_pt[0]]) 80 | 81 | for k in range(self.pt_count): 82 | if i == self.dst_pts[k][0] and j == self.dst_pts[k][1]: 83 | continue 84 | 85 | pt_i = self.dst_pts[k] - pstar 86 | pt_j = np.array([-pt_i[1], pt_i[0]]) 87 | 88 | tmp_pt = np.zeros(2, dtype=np.float32) 89 | tmp_pt[0] = np.sum(pt_i * cur_pt) * self.src_pts[k][0] - \ 90 | np.sum(pt_j * cur_pt) * self.src_pts[k][1] 91 | tmp_pt[1] = -np.sum(pt_i * cur_pt_j) * self.src_pts[k][0] + \ 92 | np.sum(pt_j * cur_pt_j) * self.src_pts[k][1] 93 | tmp_pt *= (w[k] / miu_s) 94 | new_pt += tmp_pt 95 | 96 | new_pt += qstar 97 | else: 98 | new_pt = self.src_pts[k] 99 | 100 | self.rdx[j, i] = new_pt[0] - i 101 | self.rdy[j, i] = new_pt[1] - j 102 | 103 | j += self.grid_size 104 | i += self.grid_size 105 | 106 | def gen_img(self): 107 | src_h, src_w = self.src.shape[:2] 108 | dst = np.zeros_like(self.src, dtype=np.float32) 109 | 110 | for i in np.arange(0, self.dst_h, self.grid_size): 111 | for j in np.arange(0, self.dst_w, self.grid_size): 112 | ni = i + self.grid_size 113 | nj = j + self.grid_size 114 | w = h = self.grid_size 115 | if ni >= self.dst_h: 116 | ni = self.dst_h - 1 117 | h = ni - i + 1 118 | if nj >= self.dst_w: 119 | nj = self.dst_w - 1 120 | w = nj - j + 1 121 | 122 | di = np.reshape(np.arange(h), (-1, 1)) 123 | dj = np.reshape(np.arange(w), (1, -1)) 124 | delta_x = self.__bilinear_interp(di / h, dj / w, 125 | self.rdx[i, j], self.rdx[i, nj], 126 | self.rdx[ni, j], self.rdx[ni, nj]) 127 | delta_y = self.__bilinear_interp(di / h, dj / w, 128 | self.rdy[i, j], self.rdy[i, nj], 129 | self.rdy[ni, j], self.rdy[ni, nj]) 130 | nx = j + dj + delta_x * self.trans_ratio 131 | ny = i + di + delta_y * self.trans_ratio 132 | nx = np.clip(nx, 0, src_w - 1) 133 | ny = np.clip(ny, 0, src_h - 1) 134 | nxi = np.array(np.floor(nx), dtype=np.int32) 135 | nyi = np.array(np.floor(ny), dtype=np.int32) 136 | nxi1 = np.array(np.ceil(nx), dtype=np.int32) 137 | nyi1 = np.array(np.ceil(ny), dtype=np.int32) 138 | 139 | if len(self.src.shape) == 3: 140 | x = np.tile(np.expand_dims(ny - nyi, axis=-1), (1, 1, 3)) 141 | y = np.tile(np.expand_dims(nx - nxi, axis=-1), (1, 1, 3)) 142 | else: 143 | x = ny - nyi 144 | y = nx - nxi 145 | dst[i:i + h, j:j + w] = self.__bilinear_interp(x, 146 | y, 147 | self.src[nyi, nxi], 148 | self.src[nyi, nxi1], 149 | self.src[nyi1, nxi], 150 | self.src[nyi1, nxi1] 151 | ) 152 | 153 | # for di in range(h): 154 | # for dj in range(w): 155 | # # print(ni, nj, i, j) 156 | # delta_x = self.__bilinear_interp(di / h, dj / w, self.rdx[i, j], self.rdx[i, nj], 157 | # self.rdx[ni, j], self.rdx[ni, nj]) 158 | # delta_y = self.__bilinear_interp(di / h, dj / w, self.rdy[i, j], self.rdy[i, nj], 159 | # self.rdy[ni, j], self.rdy[ni, nj]) 160 | # nx = j + dj + delta_x * self.trans_ratio 161 | # ny = i + di + delta_y * self.trans_ratio 162 | # nx = min(src_w - 1, max(0, nx)) 163 | # ny = min(src_h - 1, max(0, ny)) 164 | # nxi = int(nx) 165 | # nyi = int(ny) 166 | # nxi1 = math.ceil(nx) 167 | # nyi1 = math.ceil(ny) 168 | # 169 | # dst[i + di, j + dj] = self.__bilinear_interp(ny - nyi, nx - nxi, 170 | # self.src[nyi, nxi], 171 | # self.src[nyi, nxi1], 172 | # self.src[nyi1, nxi], 173 | # self.src[nyi1, nxi1] 174 | # ) 175 | 176 | dst = np.clip(dst, 0, 255) 177 | dst = np.array(dst, dtype=np.uint8) 178 | 179 | return dst 180 | --------------------------------------------------------------------------------