Benchmark framework implementation and 3 models added:

* benchmark framework: benchmarks based on configs

* added impl and benchmark for YuNet (face detection)

* added impl and benchmark for DB (text detection)

* added impl and benchmark for CRNN (text recognition)

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,29 @@
+# CRNN
+
+An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
+
+`text_recognition_crnn.onnx` is trained using the code from https://github.com/zihaomu/deep-text-recognition-benchmark, which can only recognize english words. It is obtained from https://drive.google.com/drive/folders/1cTbQ3nuZG-EKWak6emD_s8_hHXWz7lAr and renamed from `CRNN_VGG_BiLSTM_CTC.onnx`. Visit https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html for more information.
+
+## Demo
+
+***NOTE**: This demo use [text_detection_db](../text_detection_db) as text detector.
+
+Run the following command to try the demo:
+```shell
+# detect on camera input
+python demo.py
+# detect on an image
+python demo.py --input /path/to/image
+```
+
+## License
+
+All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
+
+## Reference
+
+- https://arxiv.org/abs/1507.05717
+- https://github.com/bgshih/crnn
+- https://github.com/meijieru/crnn.pytorch
+- https://github.com/zihaomu/deep-text-recognition-benchmark
+- https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html

crnn.py

@@ -0,0 +1,72 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+import numpy as np
+import cv2 as cv
+
+class CRNN:
+    def __init__(self, modelPath):
+        self._model = cv.dnn.readNet(modelPath)
+        self._inputSize = [100, 32] # Fixed
+        self._targetVertices = np.array([
+            [0, self._inputSize[1] - 1],
+            [0, 0],
+            [self._inputSize[0] - 1, 0],
+            [self._inputSize[0] - 1, self._inputSize[1] - 1]
+        ], dtype=np.float32)
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackend(self, backend_id):
+        self._model.setPreferableBackend(backend_id)
+
+    def setTarget(self, target_id):
+        self._model.setPreferableTarget(target_id)
+
+    def _preprocess(self, image, rbbox):
+        # Remove conf, reshape and ensure all is np.float32
+        vertices = rbbox.reshape((4, 2)).astype(np.float32)
+
+        rotationMatrix = cv.getPerspectiveTransform(vertices, self._targetVertices)
+        cropped = cv.warpPerspective(image, rotationMatrix, self._inputSize)
+
+        cropped = cv.cvtColor(cropped, cv.COLOR_BGR2GRAY)
+
+        return cv.dnn.blobFromImage(cropped, size=self._inputSize, mean=127.5, scalefactor=1 / 127.5)
+
+    def infer(self, image, rbbox):
+        # Preprocess
+        inputBlob = self._preprocess(image, rbbox)
+
+        # Forward
+        self._model.setInput(inputBlob)
+        outputBlob = self._model.forward()
+
+        # Postprocess
+        results = self._postprocess(outputBlob)
+
+        return results
+
+    def _postprocess(self, outputBlob):
+        '''Decode charaters from outputBlob
+        '''
+        text = ""
+        alphabet = "0123456789abcdefghijklmnopqrstuvwxyz"
+        for i in range(outputBlob.shape[0]):
+            c = np.argmax(outputBlob[i][0])
+            if c != 0:
+                text += alphabet[c - 1]
+            else:
+                text += '-'
+
+        # adjacent same letters as well as background text must be removed to get the final output
+        char_list = []
+        for i in range(len(text)):
+            if text[i] != '-' and (not (i > 0 and text[i] == text[i - 1])):
+                char_list.append(text[i])
+        return ''.join(char_list)

demo.py

@@ -0,0 +1,124 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+import sys
+import argparse
+
+import numpy as np
+import cv2 as cv
+
+from crnn import CRNN
+
+sys.path.append('../text_detection_db')
+from db import DB
+
+def str2bool(v):
+    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
+        return True
+    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
+        return False
+    else:
+        raise NotImplementedError
+
+parser = argparse.ArgumentParser(
+    description="An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition (https://arxiv.org/abs/1507.05717)")
+parser.add_argument('--input', '-i', type=str, help='Path to the input image. Omit for using default camera.')
+parser.add_argument('--model', '-m', type=str, default='text_recognition_crnn.onnx', help='Path to the model.')
+parser.add_argument('--width', type=int, default=736,
+                    help='The width of input image being sent to the text detector.')
+parser.add_argument('--height', type=int, default=736,
+                    help='The height of input image being sent to the text detector.')
+parser.add_argument('--save', '-s', type=str, default=False, help='Set true to save results. This flag is invalid when using camera.')
+parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
+args = parser.parse_args()
+
+def visualize(image, boxes, texts, color=(0, 255, 0), isClosed=True, thickness=2):
+    output = image.copy()
+
+    pts = np.array(boxes[0])
+    output = cv.polylines(output, pts, isClosed, color, thickness)
+    for box, text in zip(boxes[0], texts):
+        cv.putText(output, text, (box[1].astype(np.int32)), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
+    return output
+
+if __name__ == '__main__':
+    # Instantiate CRNN for text recognition
+    recognizer = CRNN(modelPath=args.model)
+    # Instantiate DB for text detection
+    detector = DB(modelPath='../text_detection_db/text_detection_db.onnx',
+                  inputSize=[args.width, args.height],
+                  binaryThreshold=0.3,
+                  polygonThreshold=0.5,
+                  maxCandidates=200,
+                  unclipRatio=2.0
+    )
+
+    # If input is an image
+    if args.input is not None:
+        image = cv.imread(args.input)
+        image = cv.resize(image, [args.width, args.height])
+
+        # Inference
+        results = detector.infer(image)
+        texts = []
+        for box, score in zip(results[0], results[1]):
+            texts.append(
+                recognizer.infer(image, box.reshape(8))
+            )
+
+        # Draw results on the input image
+        image = visualize(image, results, texts)
+
+        # Save results if save is true
+        if args.save:
+            print('Resutls saved to result.jpg\n')
+            cv.imwrite('result.jpg', image)
+
+        # Visualize results in a new window
+        if args.vis:
+            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
+            cv.imshow(args.input, image)
+            cv.waitKey(0)
+    else: # Omit input to call default camera
+        deviceId = 0
+        cap = cv.VideoCapture(deviceId)
+
+        tm = cv.TickMeter()
+        while cv.waitKey(1) < 0:
+            hasFrame, frame = cap.read()
+            if not hasFrame:
+                print('No frames grabbed!')
+                break
+
+            frame = cv.resize(frame, [args.width, args.height])
+            # Inference of text detector
+            tm.start()
+            results = detector.infer(frame)
+            tm.stop()
+            latency_detector = tm.getFPS()
+            tm.reset()
+            # Inference of text recognizer
+            texts = []
+            tm.start()
+            for box, score in zip(results[0], results[1]):
+                result = np.hstack(
+                    (box.reshape(8), score)
+                )
+                texts.append(
+                    recognizer.infer(frame, result)
+                )
+            tm.stop()
+            latency_recognizer = tm.getFPS()
+            tm.reset()
+
+            # Draw results on the input image
+            frame = visualize(frame, results, texts)
+
+            cv.putText(frame, 'Latency - {}: {}'.format(detector.name, latency_detector), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
+            cv.putText(frame, 'Latency - {}: {}'.format(recognizer.name, latency_recognizer), (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
+
+            # Visualize results in a new Window
+            cv.imshow('{} Demo'.format(recognizer.name), frame)