Computer Vision Interview 20 essential Q&A Updated 2026
color spaces

Color Spaces: 20 Essential Q&A

How we represent color numerically—RGB vs perceptual models, conversions, and practical preprocessing choices.

~11 min read 20 questions Beginner
RGB/HSVLABgammaOpenCV cvtColor
1 What is a color space? ⚡ easy
Answer: A coordinate system for representing colors as numeric tuples (e.g. three numbers for trichromatic display). Different spaces emphasize different properties—device RGB for screens, HSV for intuitive hue/saturation edits, LAB for perceptual distance.
2 Describe the RGB additive model. ⚡ easy
Answer: Red, Green, Blue primary lights added for displays. Each channel 0–255 (8-bit) combines to reproduce colors on monitors. It is device-dependent unless tied to a standard like sRGB.
import cv2
hsv = cv2.cvtColor(bgr, cv2.COLOR_BGR2HSV)
3 Why mention BGR separately from RGB? ⚡ easy
Answer: Libraries like OpenCV store channels as B, G, R. Algorithms are identical if consistent, but visualization and pre-trained weights expecting RGB need an explicit swap.
4 What do H, S, V represent? 📊 medium
Answer: Hue (color tint on a wheel), Saturation (colorfulness vs gray), Value/Brightness (intensity). Cylindrical geometry separates chromatic from achromatic changes more intuitively than RGB for some tasks.
5 Interview: when preprocess with HSV? 📊 medium
Answer: Segmenting by hue ranges (e.g. colored objects), thresholding saturation/value to ignore shadows differently than RGB splits, and some augmentations that tweak hue/saturation while preserving identity.
6 Why is LAB used in vision and graphics? 🔥 hard
Answer: L* is lightness; a*, b* are color-opponent dimensions. Euclidean distance in LAB approximates perceptual difference better than RGB. Useful for color transfer, quality metrics, and some clustering tasks.
7 What is YCbCr? 📊 medium
Answer: Separates luma (Y) from chrominance (Cb, Cr). Used in JPEG and video codecs because human vision is more sensitive to brightness than color—enabling chroma subsampling.
8 Where does CMYK appear? ⚡ easy
Answer: Subtractive printing (cyan, magenta, yellow, key/black). Less common in core CV training; relevant for print QA, packaging inspection, and prepress—not for typical RGB camera pipelines.
9 Is grayscale a “color space”? ⚡ easy
Answer: It is a single-channel intensity representation, often derived from RGB via weighted sum. It discards chrominance—good for edge detection and speed when color is irrelevant.
10 What does linear RGB mean vs sRGB? 🔥 hard
Answer: Sensors measure roughly linear light; displays apply gamma encoding (sRGB transfer function) for perceptual uniformity. Some photometric algorithms (deblur, relighting) need linearization via inverse gamma before physical correctness.
11 What is gamma correction? 📊 medium
Answer: Nonlinear mapping between stored values and displayed intensity to match human brightness perception and legacy CRT behavior. Applying gamma wrong can break color statistics and blur/threshold results.
12 What is a color gamut? 📊 medium
Answer: The range of colors a device or space can represent. Wide-gamut displays (P3) vs sRGB differ; out-of-gamut colors clip or map when converting—important for medical imaging and professional color.
13 What is a white point / illuminant? 🔥 hard
Answer: Reference neutral light (e.g. D65) for interpreting RGB values. Different cameras/AWB change apparent colors; robust pipelines account for illumination via white balance or learning.
14 What is 4:2:0 chroma subsampling? 📊 medium
Answer: Full luma resolution but quarter resolution for chroma planes—exploits lower acuity for color. Can cause color fringing on sharp edges when decoded; relevant for video compression pipelines.
15 Should you normalize each RGB channel separately? ⚡ easy
Answer: Sometimes for model input (zero mean / unit var per channel). For photometric consistency, consider normalization that preserves color ratios—or work in a space suited to the task (e.g. LAB L channel only).
16 How do augmentations interact with color space? 📊 medium
Answer: Random brightness/contrast often in RGB or HSV; hue jitter in HSV. Extreme hue shifts may leave gamut or break class semantics—keep augmentations label-safe.
17 Why is thresholding harder in RGB than gray? 📊 medium
Answer: RGB thresholding needs rules in 3D (ranges per channel or distance to a color). HSV can separate hue cone from lighting via S/V gating—still not perfect under colored illumination.
18 Compare histogram equalization on RGB vs channels? ⚡ easy
Answer: Applying independently to R,G,B shifts colors (color cast). Often convert to LAB and equalize L only, or use CLAHE on luminance to preserve chroma.
19 Mention one approach to illumination invariance. 🔥 hard
Answer: Retinex-style ideas, white balance, homomorphic filtering (separate illumination/reflectance in log domain), or learning-based methods. Interviews reward naming tradeoffs (artifacts vs compute).
20 Typical order: decode → color convert → resize? 📊 medium
Answer: Often: load image → ensure correct color order → optional WB/gamma fix → resize/crop with good interpolation → normalize to tensor. Order matters: resize after linearization for photometric tasks; many DL pipelines keep it simple in sRGB uint8.

Color Spaces Cheat Sheet

Display / capture
  • RGB / BGR
  • sRGB gamma
  • Gamut limits
Analysis
  • HSV for ranges
  • LAB for distance
  • YCbCr in video
Pitfalls
  • BGR vs RGB
  • Histogram per channel
  • AWB / lighting

💡 Pro tip: Name your target space and whether distances should be perceptual or device-raw.

Full tutorial track

Go deeper with the matching tutorial chapter and code examples.