Computer Vision Week 1 NPTEL Assignment Answers 2025
Need help with this week’s assignment? Get detailed and trusted solutions for Computer Vision Week 1 NPTEL Assignment Answers. Our expert-curated answers help you solve your assignments faster while deepening your conceptual clarity.
✅ Subject: Computer Vision
📅 Week: 1
🎯 Session: NPTEL 2025 July-October
🔗 Course Link: Click Here
🔍 Reliability: Verified and expert-reviewed answers
📌 Trusted By: 5000+ Students
For complete and in-depth solutions to all weekly assignments, check out 👉 NPTEL Computer Vision Week 1 NPTEL Assignment Answers
🚀 Stay ahead in your NPTEL journey with fresh, updated solutions every week!
NPTEL Computer Vision Week 1 Assignment Answers 2025
1. Which transform is most commonly used in frequency domain image processing?
a) Laplace Transform
b) Fourier Transform
c) Z-Transform
d) Hadamard Transform
Answer : For Answers Click Here
2. Note: Note that the probability of a normal variable P(z > 2.0) = 0.0228
X is a normally distributed variable with mean + = 30 and standard deviation o = 4.
Compute P(26 < X < 38).
a) 0.0238
b) 0.9380
c) 0.8185
d) 0.9772
Answer :
3.
Answer :
4. A continuous time signal is given by xt) = e-2t u(t), its fourier transform Xjw) is given by
a) 1/(1 + jw)
b) 1/(2 + jw)
c) 1/3 + jw)
d) 1/(1 + 2jw)
Answer :
5. Consider two images each of size 32×32, namely I1 and 12. Image l1, has 612 and 412 pixels for foreground and background, respectively. Image 1 has 412 and 612 pixels for foreground and background, respectively. One pixel is selected at random from one of the two images and it is found to be a background pixel. Find the probability that it was drawn from image 11?
a) 0.4
b) 0.04
c) 0.6
d) 0.24
Answer : For Answers Click Here
6. Which of the following statements about image processing fundamentals are correct?
a) Grayscale conversion reduces an image to a single channel by averaging RGB values.
b) Histogram equalization increases contrast by redistributing pixel intensities non-linearly.
c) Frequency-domain filtering (e.g., Fourier Transform) modifies an image by altering its frequency components.
d) Morphological operations (e.g., erosion/dilation) are only applicable to binary images.
Answer :
7.
Answer :
8.
Answer :
9. Consider a 10-bit grey scale image with dimension 32 x 32. What will be the range of values in the X-axis of its histogram?
a) 0 to 1024
b) 1 to 1024
c) 0 to 1023
d) 1 to 1023
Answer :
10.
Answer : For Answers Click Here
NPTEL Computer Vision Week 1 Assignment Answers 2024
1. What is the value after histogram equalization at location (3,2) shown with asterisk mark in the image array?
a) 2
b) 3
c) 4
d) 5
✅ Answer: c
Explanation:
Histogram equalization redistributes pixel intensities to enhance contrast. The exact new pixel value is determined by computing the cumulative distribution function (CDF) and mapping it accordingly. The value at location (3,2) becomes 4 after equalization as per the transformation.
2. X is a normally distributed variable with mean μ = 30 and standard deviation σ = 4. Compute P(X < 40).
Given: P(z > 2.5) = 0.062
a) 0.0238
b) 0.9380
c) 0.1538
d) 0.0918
✅ Answer: b
Explanation:
Z = (X – μ)/σ = (40 – 30)/4 = 2.5
P(Z < 2.5) = 1 – P(Z > 2.5) = 1 – 0.062 = 0.938
3. Two images I1 (192 FG, 64 BG) and I2 (64 FG, 192 BG). One pixel is selected and found to be background. Find P(it’s from I1 | BG).
a) 1/4
b) 2/5
c) 12/7
d) 5/7
✅ Answer: a
Explanation:
Use Bayes’ Theorem:
Let A = I1, B = I2
P(BG|I1) = 64/256 = 0.25
P(BG|I2) = 192/256 = 0.75
P(I1) = P(I2) = 0.5
P(I1|BG) = [P(BG|I1) * P(I1)] / [P(BG|I1)P(I1) + P(BG|I2)P(I2)]
= (0.250.5) / [(0.250.5)+(0.75*0.5)] = 0.125 / 0.5 = 0.25 = 1/4
4. Software detects enhancement with 96% accuracy. 75% images are enhanced. What is P(actual enhanced | predicted enhanced)?
a) 0.9663
b) 0.9930
c) 0.9863
d) 0.5940
✅ Answer: c
Explanation:
Using Bayes’ Theorem:
Let E = enhanced, NE = not enhanced
P(Predict E | E) = 0.96
P(Predict E | NE) = 0.04
P(E) = 0.75, P(NE) = 0.25
P(E | Predict E) = (0.96×0.75) / [(0.96×0.75)+(0.04×0.25)]
= 0.72 / (0.72 + 0.01) = 0.72 / 0.73 ≈ 0.9863
5. x(t) = e^−2t * u(t), find its Fourier Transform X(jω).
a) 1/(2 + jω)
b) 1/(3 + jω)
c) 1/(1 + jω)
d) 1/(4 + jω)
✅ Answer: a
Explanation:
Fourier Transform of e^−at * u(t) is 1/(a + jω)
Here, a = 2 ⇒ 1/(2 + jω)
6. Binary image with a small white circle on black background. Apply image gradient operation. How does it look?
a) Same as original
b) Thin line around boundary of circle
c) Thin line around whole image
d) White dot at center
✅ Answer: b
Explanation:
Gradient operations (like Sobel/Prewitt) highlight edges. So, the boundary of the circle becomes visible as a thin white line.
7. Value after applying vertical & horizontal Sobel operator on orange pixel?
a) 0 and 2
b) 7 and 3
c) 10 and 2
d) 2 and 10
✅ Answer: b
Explanation:
Sobel operator detects changes in intensity. Based on the kernel computation over the given pixel neighborhood, the vertical and horizontal responses come out to be 7 and 3.
8. In Direct Linear Transform, if x′ ∼ Hx then which is true?
a) x′ and Hx may have same magnitude but different direction
b) Same direction, different magnitude
c) Same direction and magnitude
d) Cross(x′, Hx) = 0
✅ Answer: b, c, d
Explanation:
In projective geometry, “∼” denotes equivalence up to a scale. So, direction is same, magnitude may differ.
Also, cross product is zero, indicating they’re collinear.
9. A 3-bit grayscale image has dimensions 32×32. What is the range of X-axis values?
a) 0 to 7
b) 1 to 7
c) 0 to 15
d) 0 to 255
✅ Answer: a
Explanation:
3-bit image → 2³ = 8 levels ⇒ values from 0 to 7
10. Value when vertical and horizontal Prewitt operators are applied to the orange pixel?
a) 0 and 2
b) −4 and −2
c) 4 and −2
d) −4 and 2
✅ Answer: b
Explanation:
Prewitt operators approximate derivatives. Applying the kernel over the given pixel region results in vertical = −4, horizontal = −2
