Color space conversion in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Color Space Conversion Purpose

Why do we convert images from RGB to other color spaces like HSV or LAB in computer vision tasks?

A To reduce the image size by compressing color channels

B To separate color information from brightness, making color-based processing easier

C To increase the number of color channels for better detail

D To convert images into grayscale for simpler processing

💡 Hint

Think about how different color spaces help isolate color features.

Color spaces like HSV separate hue and saturation from brightness, which helps algorithms focus on color without brightness interference.

❓ Predict Output

intermediate

Output of RGB to Grayscale Conversion

What is the output of this Python code converting a pure red pixel to grayscale using OpenCV?

Computer Vision

import cv2
import numpy as np
red_pixel = np.array([[[0, 0, 255]]], dtype=np.uint8)
gray_pixel = cv2.cvtColor(red_pixel, cv2.COLOR_BGR2GRAY)
print(gray_pixel[0,0])

A 76

B 85

C 0

D 255

💡 Hint

OpenCV uses a weighted sum for grayscale: 0.299*R + 0.587*G + 0.114*B.

For pure red (B=0,G=0,R=255), grayscale = 0.299*255 ≈ 76.

❓ Model Choice

advanced

Choosing Color Space for Skin Detection

Which color space is generally best suited for detecting human skin tones robustly under varying lighting?

A RGB

B CMYK

C YUV

D HSV

💡 Hint

Consider which color space separates chromatic content from brightness.

HSV separates hue and saturation from brightness, making skin color detection more stable under different lighting.

❓ Hyperparameter

advanced

Effect of Threshold in HSV Color Masking

When creating a mask to isolate a color range in HSV space, what happens if the threshold range for hue is too wide?

A The mask includes many unwanted colors, reducing precision

B The mask becomes too small, missing target colors

C The mask converts the image to grayscale

D The mask removes all colors, resulting in a black image

💡 Hint

Think about what a wider hue range means for color selection.

A wider hue range captures more colors, including those not intended, which lowers the mask's precision.

🔧 Debug

expert

Debugging Incorrect Color Conversion Output

Given this code snippet, what is the cause of the incorrect color conversion output?

import cv2
import numpy as np
img = np.array([[[255, 0, 0]]], dtype=np.uint8)
converted = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)
print(converted[0,0])

A The dtype of the image array is incorrect; it should be float32

B The input image is in RGB format, but cvtColor expects BGR for COLOR_RGB2HSV

C The input image is in BGR format, but cvtColor expects RGB for COLOR_RGB2HSV

D The image array shape is wrong; it should be (3,3,3)

💡 Hint

OpenCV uses BGR by default; check the input color order.

OpenCV's default image format is BGR. The code provides RGB data but uses COLOR_RGB2HSV, which expects RGB input. However, the array is actually BGR order, causing wrong conversion.