How to Blur Faces in Images using OpenCV in Python?

Last Updated : 03 Jan, 2023

Prerequisite: OpenCV

OpenCV is a huge open-source library for computer vision, machine learning, and image processing. It can process images and videos to identify objects, faces, or even the handwriting of a human. When it is integrated with various libraries, such as Numpy which is a highly optimized library for numerical operations, then the number of weapons increases in your Arsenal i.e whatever operations one can do in Numpy can be combined with OpenCV.

This article discusses how a face in an image can be blurred using OpenCV.

Requirements:

Apart from OpenCV module, to obtain this functionality we also need Haar Cascade frontal-face classifier needs to be downloaded. It is available as XML file and is used for detecting faces in an image

Approach

Import module
Reading an image using OpenCV
Plotting it
Detect face
Draw a rectangle on the detected face
Blur the rectangle
Display output

Below is the implementation.

Input image:

Python3

# Importing libraries
import numpy as np
import cv2
import matplotlib.pyplot as plt

# A function for plotting the images


def plotImages(img):
    plt.imshow(img, cmap="gray")
    plt.axis('off')
    plt.style.use('seaborn')
    plt.show()


# Reading an image using OpenCV
# OpenCV reads images by default in BGR format
image = cv2.imread('my_img.jpg')

# Converting BGR image into a RGB image
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# plotting the original image
plotImages(image)

face_detect = cv2.CascadeClassifier('haarcascade_frontalface_alt.xml')
face_data = face_detect.detectMultiScale(image, 1.3, 5)

# Draw rectangle around the faces which is our region of interest (ROI)
for (x, y, w, h) in face_data:
    cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
    roi = image[y:y+h, x:x+w]
    # applying a gaussian blur over this new rectangle area
    roi = cv2.GaussianBlur(roi, (23, 23), 30)
    # impose this blurred image on original image to get final image
    image[y:y+roi.shape[0], x:x+roi.shape[1]] = roi


# Display the output
plotImages(image)