Fix resizing / cropping image, and return cropped image from imageclassifier

Author: janjongboom

edge_impulse_linux/image.py

@@ -50,16 +50,39 @@ def classifier(self, videoDeviceId = 0):
             success, img = self.videoCapture.read()
             if success:
                 features = []
+
+                EI_CLASSIFIER_INPUT_WIDTH = self.dim[0]
+                EI_CLASSIFIER_INPUT_HEIGHT = self.dim[1]
+
+                in_frame_cols = img.shape[1]
+                in_frame_rows = img.shape[0]
+
+                factor_w = EI_CLASSIFIER_INPUT_WIDTH / in_frame_cols
+                factor_h = EI_CLASSIFIER_INPUT_HEIGHT / in_frame_rows
+
+                largest_factor = factor_w if factor_w > factor_h else factor_h
+
+                resize_size_w = int(largest_factor * in_frame_cols)
+                resize_size_h = int(largest_factor * in_frame_rows)
+                resize_size = (resize_size_w, resize_size_h)
+
+                resized = cv2.resize(img, resize_size, interpolation = cv2.INTER_AREA)
+
+                crop_x = int((resize_size_w - resize_size_h) / 2) if resize_size_w > resize_size_h else 0
+                crop_y = int((resize_size_h - resize_size_w) / 2) if resize_size_h > resize_size_w else 0
+
+                crop_region = (crop_x, crop_y, EI_CLASSIFIER_INPUT_WIDTH, EI_CLASSIFIER_INPUT_HEIGHT)
+
+                cropped = resized[crop_region[1]:crop_region[1]+crop_region[3], crop_region[0]:crop_region[0]+crop_region[2]]
+
                 if self.isGrayscale:
-                    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-                    resizedImg = cv2.resize(img, self.dim, interpolation = cv2.INTER_AREA)
-                    pixels = np.array(resizedImg).flatten().tolist()
+                    cropped = cv2.cvtColor(cropped, cv2.COLOR_BGR2GRAY)
+                    pixels = np.array(cropped).flatten().tolist()
 
                     for p in pixels:
                         features.append((p << 16) + (p << 8) + p)
                 else:
-                    resizedImg = cv2.resize(img, self.dim, interpolation = cv2.INTER_AREA)
-                    pixels = np.array(resizedImg).flatten().tolist()
+                    pixels = np.array(cropped).flatten().tolist()
 
                     for ix in range(0, len(pixels), 3):
                         b = pixels[ix + 0]
@@ -68,4 +91,4 @@ def classifier(self, videoDeviceId = 0):
                         features.append((r << 16) + (g << 8) + b)
 
                 res = self.classify(features)
-                yield res, img
+                yield res, cropped

examples/image/classify.py

@@ -8,6 +8,7 @@
 from edge_impulse_linux.image import ImageImpulseRunner
 
 runner = None
+show_camera = False
 
 def now():
     return round(time.time() * 1000)
@@ -80,7 +81,7 @@ def main(argv):
             camera = cv2.VideoCapture(videoCaptureDeviceId)
             ret = camera.read()[0]
             if ret:
-                backendName =camera.getBackendName()
+                backendName = camera.getBackendName()
                 w = camera.get(3)
                 h = camera.get(4)
                 print("Camera %s (%s x %s) in port %s selected." %(backendName,h,w, videoCaptureDeviceId))
@@ -94,18 +95,20 @@ def main(argv):
                 if (next_frame > now()):
                     time.sleep((next_frame - now()) / 1000)
 
-                #print(res["result"])
+                # print('classification runner response', res)
+
                 if "classification" in res["result"].keys():
                     print('Result (%d ms.) ' % (res['timing']['dsp'] + res['timing']['classification']), end='')
                     for label in labels:
                         score = res['result']['classification'][label]
                         print('%s: %.2f\t' % (label, score), end='')
                     print('', flush=True)
-                    #cv2.imshow('edgeimpulse',img)
-                    #if cv2.waitKey(1) == ord('q'):
-                    #    break
-            
-                
+
+                    if (show_camera):
+                        cv2.imshow('edgeimpulse', img)
+                        if cv2.waitKey(1) == ord('q'):
+                            break
+
                 elif "bounding_boxes" in res["result"].keys():
                     print('Found %d bounding boxes (%d ms.)' % (len(res["result"]["bounding_boxes"]), res['timing']['dsp'] + res['timing']['classification']))
                     for bb in res["result"]["bounding_boxes"]:

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = edge_impulse_linux
-version = 1.0.0
+version = 1.0.1
 author = EdgeImpulse Inc.
 author_email = hello@edgeimpulse.com
 description = Python runner for real-time ML classification