Color Detection with HSV Color Space in OpenCV

    In image processing, color space refers to a specific representation method used to describe and organize the colors in an image. It provides a structured way to define and manipulate colors, allowing for various color-related operations such as color correction, color enhancement, color segmentation, and object detection. One of the widely used color space is HSV, which stands for Hue, Saturation, and Value. 

    In this tutorial, we'll delve into the fundamentals of the HSV color space and learn how to detect given color in an image by applying HSV method with OpenCV in Python. The tutorial covers:

1. Understanding HSV
2. Color detection with HSV
   
3. Source code listing
   

    We'll start by loading the required libraries.

import cv2

from matplotlib import pyplot as plt

import numpy as np

    

Understanding HSV

 

     The HSV (Hue, Saturation, Value) color space has various applications in image processing and computer vision. The HSV color space separates the color information into three components: hue, saturation, and value. The hue component represents the color itself, saturation represents the intensity or purity of the color, and value represents the brightness or lightness of the color.  

    The HSV color space is less affected by variations in lighting conditions compared to the RGB color space and its independent color order provides more consistent and accurate color detection in an image.

     We can transform image into the HSV color space by using cv2.cvtColor() function of OpencCV library. Below code shows how to display RGB and HSV representation of an image.

 

file = "/Users/user/Desktop/tmp/balloon.jpg"

# Load the image

image = cv2.imread(file)

 

# Display the the images

plt.figure(figsize = (10, 5))

plt.subplot(1, 2, 1)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))

plt.title('RGB')

plt.subplot(1, 2, 2)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2HSV))

plt.title('HSV')

plt.tight_layout()

plt.show()

  

 

Color detection with HSV

 

    We can detect colors in an image by using HSV color space. Below code shows how how to detect red colors and draw the bounding boxes around the detected color.

    First, we'll convert the image into HSV type and define the lower and upper thresholds for red color range to create mask. Then we apply morphological operations to remove noise in an image. To create bounding boxes we need contours of read areas. Finally we'll draw green bounding boxes around the area and display the final image.

 

 

# Convert the image to the HSV color space

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

# Define the lower and upper color thresholds for red

lower_red = np.array([0, 100, 100])

upper_red = np.array([10, 255, 255])

# Create a mask based on the color thresholds

mask = cv2.inRange(hsv_image, lower_red, upper_red)

# Apply morphological operations to remove noise

kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))

mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)

# Find contours of the red areas

contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Draw bounding boxes around the red areas

for contour in contours:

x, y, w, h = cv2.boundingRect(contour)

cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 3)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))

plt.show()

 

    In this tutorial, you've briefly learned about HSV color space and how to perform color detection with HSV method in Python. The full source code is listed below. 

 

Video Tutorial

 

 

Source code listing

 

 

import cv2

from matplotlib import pyplot as plt

import numpy as np

 

 

file = "/Users/user/Desktop/tmp/balloon.jpg"

# Load the image

image = cv2.imread(file)

 

# Display the the images

plt.figure(figsize = (10, 5))

plt.subplot(1, 2, 1)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))

plt.title('RGB')

plt.subplot(1, 2, 2)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2HSV))

plt.title('HSV')

plt.tight_layout()

plt.show()

 

 

# Convert the image to the HSV color space

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

# Define the lower and upper color thresholds for red

lower_red = np.array([0, 100, 100])

upper_red = np.array([10, 255, 255])

# Create a mask based on the color thresholds

mask = cv2.inRange(hsv_image, lower_red, upper_red)

# Apply morphological operations to remove noise

kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))

mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)

# Find contours of the red areas

contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Draw bounding boxes around the red areas

for contour in contours:

x, y, w, h = cv2.boundingRect(contour)

cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 3)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))

plt.show()

 

 

 

References:

1. OpenCV image processing