Segmentation Overview MCQ 15 Questions
Time: ~25 mins Intermediate

Segmentation Overview MCQ

Partitioning images into meaningful regions: cues, energy minimization, oversegmentation, and bridges to semantic/instance segmentation.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Regions

Group pixels

Watershed

Flooding

Graph cuts

Energy min

Clustering

k-means etc.

Image segmentation overview

Segmentation assigns pixels to coherent regions or objects. Classical methods use intensity/color continuity, edges, or optimize an energy balancing data fidelity and smoothness.

Beyond thresholding

Global thresholds fail under complex scenes—region growing, mean-shift, watershed, and graph cuts add spatial coupling.

Methods

Region growing

Start seeds, merge pixels similar to region statistics—sensitive to seeds and thresholds.

Watershed

Treat gradient magnitude as topography; markers reduce oversegmentation.

Graph cuts

Pixels as nodes, pairwise smoothness + unary data terms; min-cut finds a partition.

Deep segmentation

FCN, U-Net, Mask R-CNN move toward semantic/instance tasks with learned features.

Goal

Pixels → regions or object masks with consistent labels

Pro tip: Always define evaluation (IoU, boundary F-score) when comparing segmenters.