feat: 切换后端至PaddleOCR-NCNN，切换工程为CMake

1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试
2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程
3.重整权利声明文件，重整代码工程，确保最小化侵权风险

Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake
Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c

3rdparty/opencv-4.5.4/samples/python/_coverage.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python
+
+'''
+Utility for measuring python opencv API coverage by samples.
+'''
+
+# Python 2/3 compatibility
+from __future__ import print_function
+
+from glob import glob
+import cv2 as cv
+import re
+
+if __name__ == '__main__':
+    cv2_callable = set(['cv.'+name for name in dir(cv) if callable( getattr(cv, name) )])
+
+    found = set()
+    for fn in glob('*.py'):
+        print(' --- ', fn)
+        code = open(fn).read()
+        found |= set(re.findall('cv2?\.\w+', code))
+
+    cv2_used = found & cv2_callable
+    cv2_unused = cv2_callable - cv2_used
+    with open('unused_api.txt', 'w') as f:
+        f.write('\n'.join(sorted(cv2_unused)))
+
+    r = 1.0 * len(cv2_used) / len(cv2_callable)
+    print('\ncv api coverage: %d / %d  (%.1f%%)' % ( len(cv2_used), len(cv2_callable), r*100 ))