Hello Object Detection

This Jupyter notebook can be launched on-line, opening an interactive environment in a browser window. You can also make a local installation. Choose one of the following options:

BinderGoogle ColabGithub

A very basic introduction to using object detection models with OpenVINO™.

The horizontal-text-detection-0001 model from Open Model Zoo is used. It detects horizontal text in images and returns a blob of data in the shape of [100, 5]. Each detected text box is stored in the [x_min, y_min, x_max, y_max, conf] format, where the (x_min, y_min) are the coordinates of the top left bounding box corner, (x_max, y_max) are the coordinates of the bottom right bounding box corner and conf is the confidence for the predicted class.

Table of contents:

# Install openvino package
%pip install -q "openvino>=2023.1.0" opencv-python tqdm
Note: you may need to restart the kernel to use updated packages.


import cv2
import matplotlib.pyplot as plt
import numpy as np
import openvino as ov
from pathlib import Path

# Fetch `notebook_utils` module
import requests

r = requests.get(

open("notebook_utils.py", "w").write(r.text)

from notebook_utils import download_file

Download model weights

base_model_dir = Path("./model").expanduser()

model_name = "horizontal-text-detection-0001"
model_xml_name = f"{model_name}.xml"
model_bin_name = f"{model_name}.bin"

model_xml_path = base_model_dir / model_xml_name
model_bin_path = base_model_dir / model_bin_name

if not model_xml_path.exists():
    model_xml_url = "https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.3/models_bin/1/horizontal-text-detection-0001/FP32/horizontal-text-detection-0001.xml"
    model_bin_url = "https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.3/models_bin/1/horizontal-text-detection-0001/FP32/horizontal-text-detection-0001.bin"

    download_file(model_xml_url, model_xml_name, base_model_dir)
    download_file(model_bin_url, model_bin_name, base_model_dir)
    print(f"{model_name} already downloaded to {base_model_dir}")
model/horizontal-text-detection-0001.xml:   0%|          | 0.00/680k [00:00<?, ?B/s]
model/horizontal-text-detection-0001.bin:   0%|          | 0.00/7.39M [00:00<?, ?B/s]

Select inference device

select device from dropdown list for running inference using OpenVINO

import ipywidgets as widgets

core = ov.Core()
device = widgets.Dropdown(
    options=core.available_devices + ["AUTO"],

Dropdown(description='Device:', index=1, options=('CPU', 'AUTO'), value='AUTO')

Load the Model

core = ov.Core()

model = core.read_model(model=model_xml_path)
compiled_model = core.compile_model(model=model, device_name=device.value)

input_layer_ir = compiled_model.input(0)
output_layer_ir = compiled_model.output("boxes")

Load an Image

# Download the image from the openvino_notebooks storage
image_filename = download_file(

# Text detection models expect an image in BGR format.
image = cv2.imread(str(image_filename))

# N,C,H,W = batch size, number of channels, height, width.
N, C, H, W = input_layer_ir.shape

# Resize the image to meet network expected input sizes.
resized_image = cv2.resize(image, (W, H))

# Reshape to the network input shape.
input_image = np.expand_dims(resized_image.transpose(2, 0, 1), 0)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB));
data/intel_rnb.jpg:   0%|          | 0.00/288k [00:00<?, ?B/s]

Do Inference

# Create an inference request.
boxes = compiled_model([input_image])[output_layer_ir]

# Remove zero only boxes.
boxes = boxes[~np.all(boxes == 0, axis=1)]

Visualize Results

# For each detection, the description is in the [x_min, y_min, x_max, y_max, conf] format:
# The image passed here is in BGR format with changed width and height. To display it in colors expected by matplotlib, use cvtColor function
def convert_result_to_image(bgr_image, resized_image, boxes, threshold=0.3, conf_labels=True):
    # Define colors for boxes and descriptions.
    colors = {"red": (255, 0, 0), "green": (0, 255, 0)}

    # Fetch the image shapes to calculate a ratio.
    (real_y, real_x), (resized_y, resized_x) = (
    ratio_x, ratio_y = real_x / resized_x, real_y / resized_y

    # Convert the base image from BGR to RGB format.
    rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)

    # Iterate through non-zero boxes.
    for box in boxes:
        # Pick a confidence factor from the last place in an array.
        conf = box[-1]
        if conf > threshold:
            # Convert float to int and multiply corner position of each box by x and y ratio.
            # If the bounding box is found at the top of the image,
            # position the upper box bar little lower to make it visible on the image.
            (x_min, y_min, x_max, y_max) = [
                (int(max(corner_position * ratio_y, 10)) if idx % 2 else int(corner_position * ratio_x)) for idx, corner_position in enumerate(box[:-1])

            # Draw a box based on the position, parameters in rectangle function are: image, start_point, end_point, color, thickness.
            rgb_image = cv2.rectangle(rgb_image, (x_min, y_min), (x_max, y_max), colors["green"], 3)

            # Add text to the image based on position and confidence.
            # Parameters in text function are: image, text, bottom-left_corner_textfield, font, font_scale, color, thickness, line_type.
            if conf_labels:
                rgb_image = cv2.putText(
                    (x_min, y_min - 10),

    return rgb_image
plt.figure(figsize=(10, 6))
plt.imshow(convert_result_to_image(image, resized_image, boxes, conf_labels=False));