| import argparse |
| import os |
|
|
| import cv2 as cv |
| import numpy as np |
|
|
| here = os.path.dirname(os.path.abspath(__file__)) |
|
|
|
|
| def main(): |
| parser = argparse.ArgumentParser(description="EAST scene-text detection (ONNX) demo") |
| parser.add_argument("--model", default=os.path.join(here, "east_text_detection_2026jul.onnx")) |
| parser.add_argument("--image", default=os.path.join(here, "example_outputs", "input_image.png")) |
| parser.add_argument("--output", default=os.path.join(here, "example_outputs", "output_image.png")) |
| parser.add_argument("--conf", type=float, default=0.5, help="confidence threshold") |
| parser.add_argument("--nms", type=float, default=0.4, help="NMS threshold") |
| args = parser.parse_args() |
|
|
| img = cv.imread(args.image) |
| if img is None: |
| raise SystemExit("could not read image: %s" % args.image) |
|
|
| model = cv.dnn.TextDetectionModel_EAST(args.model) |
| model.setConfidenceThreshold(args.conf).setNMSThreshold(args.nms) |
| model.setInputParams(1.0, (320, 320), (123.68, 116.78, 103.94), True, False) |
|
|
| boxes, confidences = model.detectTextRectangles(img) |
| print("detections", len(boxes)) |
|
|
| out = img.copy() |
| for box in boxes: |
| pts = cv.boxPoints(box).astype(np.int32) |
| cv.polylines(out, [pts], True, (0, 255, 0), 2) |
| cv.imwrite(args.output, out) |
| print("wrote", args.output) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|