def predict()

in source/containers/face-comparison/recognizer/predictor.py [0:0]

• 35 lines of code
• 3 McCabe index (conditional complexity)

    def predict(cls, source_image_base64, target_image_base64, min_confidence_thresh=0.40):
        source_image = cv2.imdecode(np.frombuffer(base64.b64decode(source_image_base64), np.uint8), cv2.IMREAD_COLOR)
        target_image = cv2.imdecode(np.frombuffer(base64.b64decode(target_image_base64), np.uint8), cv2.IMREAD_COLOR)

        t1 = time.time()
        source_detected_face = cls.detect_and_align(source_image, is_source_image=True, threshold=min_confidence_thresh)
        target_detected_faces = cls.detect_and_align(target_image, is_source_image=False, threshold=min_confidence_thresh)
        t2 = time.time()
        print('Time Cost of Face Detecting & Aligning for 2 Images = {} seconds'.format(t2 - t1))

        response = {
            'SourceImageFace': None,
            'FaceMatches': []
        }

        if source_detected_face is not None:
            [x_min, y_min, x_max, y_max] = source_detected_face.bbox
            response['SourceImageFace'] = {
                'BoundingBox': [x_min, y_min, x_max, y_max],
                'Confidence': source_detected_face.confidence,
                'KeyPoints': source_detected_face.key_points
            }
        else:
            return response

        for target_comp_face in target_detected_faces:
            base_feat_representation = cls.get_feature(source_detected_face.aligned_face_img)
            target_feat_representation = cls.get_feature(target_comp_face.aligned_face_img)
            similarity_score = np.dot(base_feat_representation, target_feat_representation)

            # add comparison to response body
            [x_min, y_min, x_max, y_max] = target_comp_face.bbox
            response['FaceMatches'].append({
                'Similarity': float(similarity_score),
                'Face': {
                    'BoundingBox': [x_min, y_min, x_max, y_max],
                    'Confidence': target_comp_face.confidence,
                    'KeyPoints': target_comp_face.key_points
                }
            })

        return response