Detecting Objects with OpenCV Cascade Classifiers

→ Article about detecting objects with pretrained OpenCV Cascade Classifiers implemented in Python.

For Object Detection, there are popular models like YOLO, Faster R-CNN, and SSD, and they all have different advantages:

YOLO models are a perfect choice for real-time applications,
Faster R-CNN model works better with small objects,
SSD models have a great balance between accuracy and performance

But these advanced models are not the only choices for object detection. These models are powerful, but training and running them are computationally expensive and time-consuming.

You have other options like OpenCV cascade classifiers; they are not complex models, therefore you don’t need powerful GPUs or anything else. You just need to install the OpenCV library, and with a few simple lines of code, you’re good to go.

Object Detection with OpenCV Cascade Classifiers, Python (video source)

When to use OpenCV Cascade Classifiers ?

Before starting, I must warn you: OpenCV Cascade Classifiers are not powerful models. Most of the time, they won’t be enough for you, but if you have a simple task like face detection, body detection, or eye detection, you can use OpenCV Cascade Classifiers.

Advantages: Lightweight, pre-trained models are available, good for simple detection tasks, easy to implement.
Disadvantages: Perform poorly when the object has significant variations, high false positives, not good for complex objects.

Detecting Objects with OpenCV Cascade Classifiers — **Object Detection using OpenCV Cascade Classifier**s (image source)

Pretrained Cascade Classifier Models

There are a bunch of pretrained models that OpenCV has published on their official repository, and you can take a look at the models from the image below. (pretrained models)
Most of the pretrained models are for body, eye, and face detection.

Object Detection with OpenCV Cascade Classifiers on Images

For loading a pretrained model, you need to create an object of the cv2.CascadeClassifier class and provide the pretrained model file as a parameter.

For detection, use the detectMultiScale method, and here is the explanation of the parameters:

minSize → It specifies the minimum size of the object to be detected.

image → Input image in grayscale. Face detection works more efficiently in grayscale.

scaleFactor → This parameter specifies how much the image size is reduced at each image scale.

minNeighbors → The detection algorithm finds multiple candidates, and minNeighbors controls how many detections around the same region are needed to declare if it is an object.

import cv2
import matplotlib.pyplot as plt

# Load the pre-trained Haar Cascade classifier for face detection
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_fullbody.xml')

# Read the image
image = cv2.imread(r"C:\Users\sirom\Downloads\pexels-chinmay-singh-251922-843563.jpg")

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

# Detect faces in the image
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(10, 10))

# Draw rectangles around the detected faces
for (x, y, w, h) in faces:
    cv2.rectangle(image, (x, y), (x+w, y+h), (255, 0, 0), 2)

# Display the output
plt.imshow(cv2.cvtColor(image,cv2.COLOR_BGR2RGB))

Object Detection with OpenCV Cascade Classifiers on Videos

Nearly everything is the same as in the image, and don’t forget to change:

Path to the pretrained model
Path to the video

# Load the pre-trained Haar Cascade classifier for full body detection (you can use a face detector if needed)
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_fullbody.xml')

# Capture video from a file or camera (use 0 for the default camera)
video_capture = cv2.VideoCapture(r"C:\Users\sirom\Downloads\7236898-hd_1280_720_25fps.mp4")  # For a file
# video_capture = cv2.VideoCapture(0)  # For camera input

# Start the time counter
prev_frame_time = time.time() 
new_frame_time = 0

# Loop over frames from the video
while video_capture.isOpened():
    # Capture frame-by-frame
    ret, frame = video_capture.read()

    if not ret:
        print("Finished processing or cannot read the video.")
        break

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

    # Detect faces in the frame
    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=10, minSize=(10, 10))

    # Draw rectangles around the detected faces
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 4)
        cv2.putText(frame, 'Face', (x + 75, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 0, 0), 2)


    # Calculate the FPS
    new_frame_time = time.time()
    fps = 1 / (new_frame_time - prev_frame_time)
    prev_frame_time = new_frame_time

    # Convert FPS to an integer for display
    fps = int(fps)
    fps_text = f'FPS: {fps}'

    # Put the FPS text on the top-right corner of the frame
    cv2.putText(frame, fps_text, (frame.shape[1] - 150, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 3)

    # Display the resulting frame
    cv2.imshow('Face Detection in Video with FPS', frame)

    # Break the loop when 'q' is pressed
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release the video capture object and close all windows
video_capture.release()
cv2.destroyAllWindows()

Object Detection with OpenCV Cascade Classifiers, Python (video source)

When to use OpenCV Cascade Classifiers ?

Pretrained Cascade Classifier Models

Object Detection with OpenCV Cascade Classifiers on Images

Object Detection with OpenCV Cascade Classifiers on Videos

Related Posts

A Multi-Purpose GUI for YOLO Object Detection Models

Pipeline for Training Custom YOLO-NAS Object Detection Models

Pipeline For Training Custom YOLO Object Detection Models

Trending now