Perform the following steps to implement text detection and recognition using the opencv-python functions:
- Define the following function to decode the predictions by EAST and extract the bounding boxes (locations of the texts detected) and associated confidences:
min_confidence = 0.5def decode_predictions(scores, geometry): (num_rows, num_cols) = scores.shape[2:4] rects, confidences = [], [] for y in range(0, num_rows): scores_data = scores[0, 0, y] x_data0, x_data1 = geometry[0, 0, y], geometry[0, 1, y] x_data2, x_data3 = geometry[0, 2, y], geometry[0, 3, y] angles_data = geometry[0, 4, y] for x in range(0, num_cols): if scores_data[x] < min_confidence: continue (offset_x, offset_y) = (x * 4.0, y * 4.0) angle = angles_data[x] ...
