Scribd
Upload
3 views

Image Filtering

Uploaded by

Raj Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3 views

Image Filtering

Uploaded by

Raj Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Image filtering and feature detection

Sir Umair Abro


Image Filtering

 Image filtering is a computational technique used to modify or enhance digital


images by applying mathematical operations to individual pixels or groups of
pixels.

 Image filtering plays a crucial role in various fields including image


processing, computer vision, and computer graphics, enabling tasks such as
enhancing image quality, extracting important features, and improving the
interpretability of visual data.

 Applications: Noise Reduction, Smoothing And Bluring, edge detection and


Image Restoration.
Common filtering operations

 Blur (or Smoothing): Used to reduce noise or remove detail from an


image. Techniques like Gaussian blur or median filtering are
commonly employed.

 Edge Detection: Detecting edges in an image helps in identifying


object boundaries. Techniques like Sobel, Prewitt, and Canny edge
detectors are frequently used.

 Sharpening: Enhances the edges and details in an image. Techniques


like Laplacian filtering or unsharp masking are used for this purpose.
Conti…

 Noise Reduction: Removing noise from an image using filters like


mean filter, median filter, or bilateral filter.

 Morphological Operations: Techniques like erosion, dilation, opening,


and closing are used for tasks such as noise removal, object
extraction, and shape detection.
Feature Detection:
 Feature detection in computer vision refers to the process of
identifying and extracting distinctive and informative patterns or
structures from images.
 These patterns, known as features, can represent various
characteristics such as points, lines,edges, corners, blobs, or
regions of interest within the image.
 Applications: Object Recognition, Image Stitching , Camera
Calibration, Motion Tracking
Techniques for feature detection
 Corner Detection: Identifying points in an image where the intensity changes
significantly in all directions.

 Blob Detection: Detecting regions in an image with uniform intensity or color.

 Scale-Invariant Feature Transform (SIFT): Identifies key points in an image


that are invariant to scaling, rotation, and translation. SIFT is robust to
changes in viewpoint and illumination.
 Speeded-Up Robust Features (SURF): Similar to SIFT but computationally
more efficient, making it suitable for real-time applications.
 Histogram of Oriented Gradients (HOG): Used for object detection by
describing the distribution of local intensity gradients or edge directions.
Code
# Perform Canny edge detection
edges = cv2.Canny(blurred, 100, 200)
import cv2
# Read the image # Display the original image
image = cv2.imread("D:\\6th cv2.imshow('Original Image', image)
Semester\\Data Science\\
img1.jpg.jpeg") #blured Image
image = cv2.resize(image, (350,185)) cv2.imshow('Blured Image', image)

# Convert the image to grayscale # Display the image after edge


gray = cv2.cvtColor(image, detection
cv2.COLOR_BGR2GRAY) cv2.imshow('Edges Detected', edges)

# Apply Gaussian blur to reduce noise # Wait for any key press to close the
window
blurred = cv2.GaussianBlur(gray, (5,
cv2.waitKey(0)
5), 0)
v2.destroyAllWindows()

You might also like