Scribd
Upload
17 views16 pages

Lab Program 9

ssssss

Uploaded by

Vinutha H M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
17 views16 pages

Lab Program 9

ssssss

Uploaded by

Vinutha H M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

• Read an image and extract and display low-level

features such as edges, textures using filtering


techniques.
import cv2 // Import the cv2 module

import numpy as np // import numpy library


image = cv2.imread('images.jpg', cv2.IMREAD_GRAYSCALE)
'images.jpg':
• This is the file path of the image you want to read.
cv2.IMREAD_GRAYSCALE:
• This is a flag used with cv2.imread() to specify how
the image should be read.

• cv2.IMREAD_GRAYSCALE indicates that the image


should be read as a grayscale image.
Note:

Original Image Detected edges


Image gradient
• Image gradient is defined as a directional change in
image intensity.
• Gradient measures the change in pixel intensity in a
given direction.
• By estimating the direction or orientation along with
the magnitude (i.e. how strong the change in
direction is), we are able to detect regions of an
image that look like edges.
• Image gradients are estimated using kernels or filters.

• The first derivative of an image measures the rate of


change of pixel intensity.
• It is useful for detecting edges because edges are
locations in the image where the intensity changes
rapidly.

• The first derivative can be approximated using gradient


operators like the Sobel.
• sobel_x = cv2.Sobel(image, cv2.CV_64F, 1, 0, ksize=3)
image
• The input image (grayscale or color) on which the Sobel operation will be
applied.
cv2.CV_64F
• The desired depth of the output image. CV_64F specifies a 64-bit
floating-point output.
1
The order of the derivative in the x-direction (Sobel kernel used for horizontal
gradient).
0
The order of the derivative in the y-direction (Sobel kernel used for vertical
gradient).
ksize :
Size of the kernel
Example of Sobel Edge Detection
• sobel_y = cv2.Sobel(image, cv2.CV_64F, 0, 1, ksize=3)
image
• The input image (grayscale or color) on which the Sobel operation will be
applied.
cv2.CV_64F
• The desired depth of the output image. CV_64F specifies a 64-bit
floating-point output.
0
The order of the derivative in the x-direction (Sobel kernel used for horizontal
gradient).
1
The order of the derivative in the y-direction (Sobel kernel used for vertical
gradient).
ksize :
Size of the kernel
sobel_edge = cv2.magnitude(sobel_x, sobel_y)

• Computes the magnitude of the gradient for each


pixel in the image.
sobel_x: Gradient image in the x-direction (horizontal
gradient).

sobel_y: Gradient image in the y-direction (vertical


gradient).
laplacian_edge = cv2.Laplacian(image, cv2.CV_64F)
• Laplacian is a second order derivative filter.
• Laplacian function applies the Laplacian operator to
the input image (image) to compute the second
derivative of the image intensity.

cv2.CV_64F: Specifies the output image data type


(64-bit floating point) to handle negative Laplacian
values correctly.
# Apply Gaussian blur for texture extraction
gaussian_blur = cv2.GaussianBlur(image, (5, 5), 0)
Gaussian Blur
Syntax:
cv2. GaussianBlur(image, kernelsize, sigmaX )
Image
The image you need to blur
kernelsize
• This parameter specifies the size of the Gaussian kernel
• It should be a tuple (width, height) specifying the kernel
size.
• Both width and height should be odd and positive
numbers.
5 x 5 Kernel
sigmaX

• The Gaussian kernel standard deviation which is the


default set to 0.
cv2.imshow('Original Image', image)
cv2.imshow('Sobel Edge Detection',
np.uint8(sobel_edge))
cv2.imshow('Laplacian Edge Detection',
np.uint8(laplacian_edge))

cv2.imshow('Gaussian Blurred Image', gaussian_blur)

cv2.waitKey(0)
cv2.destroyAllWindows()
• np.uint8() is used to convert the image data to 8-bit
unsigned integer format.

You might also like