OpenCV Tutorial

Image Processing

Feature Detection and Description

Drawing Functions

Video Processing

Applications and Projects

Draw rectangular shape and extract objects in OpenCV

Drawing a rectangular shape around objects and extracting them is a common task in computer vision. This can be done by identifying the contours (boundaries) of the object and then drawing a bounding rectangle around it.

In this tutorial, we'll explore how to do this using OpenCV:

Prerequisites:

  • Install necessary libraries:
pip install opencv-python

Step-by-Step Tutorial:

  • Import necessary libraries:
import cv2
import numpy as np
  • Read the Image and Convert to Grayscale:
image = cv2.imread('path_to_image.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
  • Binarize the Image: Using thresholding, convert the image to a binary format (black and white).
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV)
  • Find Contours: Contours are continuous curves that bound or cover the full boundary of an object in an image.
(contours, _) = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
  • Draw Rectangular Bounding Boxes and Extract Objects: Loop through each contour, draw a rectangle around it, and save the extracted object if needed.
for contour in contours:
    # Get the bounding rectangle
    x, y, w, h = cv2.boundingRect(contour)

    # Draw the rectangle
    cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)

    # Extract the object and save (optional)
    roi = image[y:y+h, x:x+w]
    cv2.imwrite(f"object_{contour[0][0][0]}.jpg", roi)
  • Display the Result:
cv2.imshow('Detected Objects', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

Tips:

  • The binarization threshold (127 in the tutorial) can be adjusted based on the image's characteristics. For images with varying illumination, adaptive thresholding (cv2.adaptiveThreshold()) might yield better results.

  • Depending on the image, you might need to perform morphological operations like dilation or erosion to enhance or reduce noise before finding contours.

  • The extracted objects (roi) can be processed further, for example, for OCR or classification tasks.

Conclusion:

Drawing a rectangle around objects and extracting them is a fundamental operation in computer vision. OpenCV provides efficient tools to identify, outline, and extract objects in an image. Proper preprocessing, like adaptive thresholding or morphological operations, can improve the accuracy and reliability of object detection.

  1. Drawing Rectangles Around Objects in OpenCV:

    • Description: Introduction to drawing rectangles around objects in images using OpenCV.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Define the coordinates of the rectangle (x, y, width, height)
rectangle = (50, 100, 200, 150)

# Draw the rectangle on the image
img_with_rectangle = cv2.rectangle(img.copy(), (rectangle[0], rectangle[1]),
                                   (rectangle[0] + rectangle[2], rectangle[1] + rectangle[3]),
                                   (0, 255, 0), 2)

# Display the result
cv2.imshow('Rectangle around Object', img_with_rectangle)
cv2.waitKey(0)
cv2.destroyAllWindows()

  2. Object Detection and Extraction using Rectangular Bounding Boxes in OpenCV:

    • Description: Demonstrates how to detect and extract objects using rectangular bounding boxes.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply object detection technique (e.g., thresholding)
_, binary_img = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)

# Find contours
contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Extract objects using rectangular bounding boxes
for contour in contours:
    x, y, w, h = cv2.boundingRect(contour)
    img_with_boxes = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)

# Display the result
cv2.imshow('Object Detection and Extraction', img_with_boxes)
cv2.waitKey(0)
cv2.destroyAllWindows()

  3. Drawing Rectangles on Detected Objects in OpenCV:

    • Description: Illustrates drawing rectangles on detected objects using OpenCV.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Apply object detection technique (e.g., thresholding)
_, binary_img = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY)

# Find contours
contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Draw rectangles on detected objects
for contour in contours:
    x, y, w, h = cv2.boundingRect(contour)
    img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)

# Display the result
cv2.imshow('Rectangles on Detected Objects', img_with_rectangles)
cv2.waitKey(0)
cv2.destroyAllWindows()

  4. Contour-Based Object Extraction with Rectangles in OpenCV:

    • Description: Shows how to extract objects based on contours and draw rectangles around them.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply object detection technique (e.g., thresholding)
_, binary_img = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)

# Find contours
contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Extract objects based on contours and draw rectangles
for contour in contours:
    x, y, w, h = cv2.boundingRect(contour)
    object_roi = img[y:y+h, x:x+w]
    img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)

# Display the result
cv2.imshow('Contour-Based Object Extraction', img_with_rectangles)
cv2.waitKey(0)
cv2.destroyAllWindows()

  5. Extracting Regions of Interest with Rectangular Masks in OpenCV:

    • Description: Demonstrates extracting regions of interest (ROIs) using rectangular masks.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Define the coordinates of the rectangular mask (x, y, width, height)
mask_coords = (50, 100, 200, 150)

# Extract the region of interest (ROI) using the mask
roi = img[mask_coords[1]:mask_coords[1] + mask_coords[3], mask_coords[0]:mask_coords[0] + mask_coords[2]]

# Display the extracted ROI
cv2.imshow('Extracted ROI with Rectangular Mask', roi)
cv2.waitKey(0)
cv2.destroyAllWindows()

  6. OpenCV Rectangle Drawing and Object Extraction Example:

    • Description: Provides a complete example of rectangle drawing and object extraction in OpenCV.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply object detection technique (e.g., thresholding)
_, binary_img = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)

# Find contours
contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Draw rectangles and extract objects
for contour in contours:
    x, y, w, h = cv2.boundingRect(contour)
    img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)
    object_roi = img[y:y+h, x:x+w]

# Display the result
cv2.imshow('Rectangle Drawing and Object Extraction', img_with_rectangles)
cv2.imshow('Extracted Object', object_roi)
cv2.waitKey(0)
cv2.destroyAllWindows()

  7. Python Script for Drawing Bounding Boxes and Extracting Objects in OpenCV:

    • Description: Presents a script for drawing bounding boxes and extracting objects from an image.
    • Code:
      import cv2
import numpy as np

def draw_rectangles_and_extract_objects(image_path):
    # Read the image
    img = cv2.imread(image_path)

    # Convert to grayscale
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # Apply object detection technique (e.g., thresholding)
    _, binary_img = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)

    # Find contours
    contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # Draw rectangles and extract objects
    for contour in contours:
        x, y, w, h = cv2.boundingRect(contour)
        img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)
        object_roi = img[y:y+h, x:x+w]

    # Display the result
    cv2.imshow('Rectangle Drawing and Object Extraction', img_with_rectangles)
    cv2.imshow('Extracted Object', object_roi)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

# Example usage
draw_rectangles_and_extract_objects('objects.jpg')

  8. Rectangular Shape Detection and Object Extraction in OpenCV:

    • Description: Covers the detection of rectangular shapes and subsequent object extraction.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply edge detection (e.g., Canny)
edges = cv2.Canny(gray, 50, 150)

# Find contours
contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Filter rectangular contours (assume a rectangle if it has 4 corners)
rectangular_contours = [cnt for cnt in contours if len(cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt, True), True)) == 4]

# Draw rectangles and extract objects
for contour in rectangular_contours:
    x, y, w, h = cv2.boundingRect(contour)
    img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)
    object_roi = img[y:y+h, x:x+w]

# Display the result
cv2.imshow('Rectangular Shape Detection and Object Extraction', img_with_rectangles)
cv2.imshow('Extracted Object', object_roi)
cv2.waitKey(0)
cv2.destroyAllWindows()

  9. Contour Approximation for Rectangular Shapes in OpenCV:

    • Description: Demonstrates contour approximation for detecting rectangular shapes.
    • Code:
      import cv2
import numpy as np

# Read the image
img = cv2.imread('objects.jpg')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply edge detection (e.g., Canny)
edges = cv2.Canny(gray, 50, 150)

# Find contours
contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Approximate contours to reduce points (assume rectangles)
rectangular_contours = [cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt, True), True) for cnt in contours]

# Filter rectangles (assume a rectangle if it has 4 corners)
rectangular_contours = [cnt for cnt in rectangular_contours if len(cnt) == 4]

# Draw rectangles and extract objects
for contour in rectangular_contours:
    x, y, w, h = cv2.boundingRect(contour)
    img_with_rectangles = cv2.rectangle(img.copy(), (x, y), (x + w, y + h), (0, 255, 0), 2)
    object_roi = img[y:y+h, x:x+w]

# Display the result
cv2.imshow('Contour Approximation for Rectangular Shapes', img_with_rectangles)
cv2.imshow('Extracted Object', object_roi)
cv2.waitKey(0)
cv2.destroyAllWindows()

  10. Real-Time Object Extraction with Rectangle Drawing in OpenCV:

    • Description: Shows how to perform real-time object extraction with rectangle drawing.
    • Code:
      import cv2

# Initialize camera
cap = cv2.VideoCapture(0)

while True:
    # Capture frame-by-frame
    ret, frame = cap.read()

    # Convert to grayscale
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # Apply object detection technique (e.g., thresholding)
    _, binary_img = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)

    # Find contours
    contours, _ = cv2.findContours(binary_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # Draw rectangles and extract objects
    for contour in contours:
        x, y, w, h = cv2.boundingRect(contour)
        frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)

    # Display the result
    cv2.imshow('Real-Time Object Extraction', frame)

    # Break the loop on 'q' key press
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release the camera and close windows
cap.release()
cv2.destroyAllWindows()

  11. Drawing Rectangles with OpenCV and NumPy:

    • Description: Provides a simple example of drawing rectangles using OpenCV and NumPy.
    • Code:
      import cv2
import numpy as np

# Create a black image
img = np.zeros((400, 600, 3), dtype=np.uint8)

# Define the coordinates of the rectangle (x, y, width, height)
rectangle = (50, 100, 200, 150)

# Draw the rectangle on the image
img = cv2.rectangle(img, (rectangle[0], rectangle[1]),
                    (rectangle[0] + rectangle[2], rectangle[1] + rectangle[3]),
                    (0, 255, 0), 2)

# Display the result
cv2.imshow('Rectangle Drawing with NumPy', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Copyright © devanddep.com | All Rights Reserved