Detect Specific Color From Image using Python OpenCV

In this article, you will learn how to detect a specific colour or similar colour from an image using the Python OpenCV. Colour detection is important to recognise objects. It is also used as a tool in various image editing and drawing applications.

The OpenCV module is being used for a very wide range of image processing and analysis tasks, like object identification, colour detection, optical character recognition, photo editing, and so on. It provides lots of functions for image processing.

The colour detection process is mostly in demand in computer vision. A colour detection algorithm identifies pixels in an image that match a specified colour or colour range. The colour of detected pixels can then be changed to distinguish them from the rest of the image. This process can be easily done using the OpenCV.

Project Necessity

• Python 3.x
• OpenCV 4.5
• Numpy 1.20.3

In this article, we import two modules- cv2 and numpy. After this, we load the image using the imread. Then, we convert the color-space from BGR to HSV using the cv2.cvtColor(), like the following-

hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)

Next, we define the lower and upper color(blue) rgb values in two variables, i.e.,-

light_blue = np.array([110,50,50])
dark_blue = np.array([130,255,255])

The OpenCV provides the cv2.inRange() method to set the colour range. It accepts three parameters, the source image in the first parameter and the lower and upper colour boundaries of the threshold region. This function returns a binary mask, which we will pass into the bitwise AND operator.

mask = cv2.inRange(hsv, light_blue, dark_blue)

output = cv2.bitwise_and(image,image, mask= mask)

Complete Code

Above, we have explained the code flow of colour detection. Here is the complete code-

import cv2
import numpy as np


image = cv2.imread("blue_flowers.jpg")                
# Convert BGR to HSV
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)

# define blue color range
light_blue = np.array([110,50,50])
dark_blue = np.array([130,255,255])

# Threshold the HSV image to get only blue colors
mask = cv2.inRange(hsv, light_blue, dark_blue)

# Bitwise-AND mask and original image
output = cv2.bitwise_and(image,image, mask= mask)
    
cv2.imshow("Color Detected", np.hstack((image,output)))
cv2.waitKey(0)
cv2.destroyAllWindows()

The above code returns the following output-

Related Articles