Merge pull request #8126 from LDOUBLEV/26

[feature] support min_area_rect crop

tools/infer/predict_system.py

@@ -34,7 +34,7 @@ import tools.infer.predict_det as predict_det
 import tools.infer.predict_cls as predict_cls
 from ppocr.utils.utility import get_image_file_list, check_and_read
 from ppocr.utils.logging import get_logger
-from tools.infer.utility import draw_ocr_box_txt, get_rotate_crop_image
+from tools.infer.utility import draw_ocr_box_txt, get_rotate_crop_image, get_minarea_rect_crop
 logger = get_logger()
 
 
@@ -80,7 +80,10 @@ class TextSystem(object):
 
         for bno in range(len(dt_boxes)):
             tmp_box = copy.deepcopy(dt_boxes[bno])
-            img_crop = get_rotate_crop_image(ori_im, tmp_box)
+            if self.args.det_box_type == "quad":
+                img_crop = get_rotate_crop_image(ori_im, tmp_box)
+            else:
+                img_crop = get_minarea_rect_crop(ori_im, tmp_box)
             img_crop_list.append(img_crop)
         if self.use_angle_cls and cls:
             img_crop_list, angle_list, elapse = self.text_classifier(

tools/infer/utility.py

@@ -629,6 +629,29 @@ def get_rotate_crop_image(img, points):
     return dst_img
 
 
+def get_minarea_rect_crop(img, points):
+    bounding_box = cv2.minAreaRect(np.array(points).astype(np.int32))
+    points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
+
+    index_a, index_b, index_c, index_d = 0, 1, 2, 3
+    if points[1][1] > points[0][1]:
+        index_a = 0
+        index_d = 1
+    else:
+        index_a = 1
+        index_d = 0
+    if points[3][1] > points[2][1]:
+        index_b = 2
+        index_c = 3
+    else:
+        index_b = 3
+        index_c = 2
+
+    box = [points[index_a], points[index_b], points[index_c], points[index_d]]
+    crop_img = get_rotate_crop_image(img, np.array(box))
+    return crop_img
+
+
 def check_gpu(use_gpu):
     if use_gpu and not paddle.is_compiled_with_cuda():
         use_gpu = False