Segmentation evaluation (IoU, Dice) in Computer Vision

Introduction

We use segmentation evaluation to check how well a model finds the exact shapes in images. IoU and Dice scores tell us how close the model's guess is to the real shape.

When you want to measure how well a model separates objects from the background in photos.

When comparing different models to see which one finds shapes more accurately.

When improving a model that detects tumors or organs in medical images.

When checking if a self-driving car correctly identifies road lanes or obstacles.

When validating models that segment animals or plants in nature photos.

Syntax

Computer Vision

def iou_score(pred_mask, true_mask):
    intersection = (pred_mask & true_mask).sum()
    union = (pred_mask | true_mask).sum()
    return intersection / union if union != 0 else 1.0

def dice_score(pred_mask, true_mask):
    intersection = (pred_mask & true_mask).sum()
    total = pred_mask.sum() + true_mask.sum()
    return 2 * intersection / total if total != 0 else 1.0

pred_mask and true_mask are binary masks (arrays of True/False or 1/0) of the same size.

IoU is also called Jaccard Index; Dice is similar but gives more weight to overlap.

Examples

This example calculates IoU for small masks where some pixels overlap.

Computer Vision

pred_mask = [0, 1, 1, 0]
true_mask = [1, 1, 0, 0]
iou = iou_score(pred_mask, true_mask)

Dice score is 1.0 here because the prediction perfectly matches the truth.

Computer Vision

pred_mask = [1, 1, 1, 1]
true_mask = [1, 1, 1, 1]
dice = dice_score(pred_mask, true_mask)

Sample Model

This program calculates IoU and Dice scores for two small example masks. It shows how much the predicted shape overlaps with the true shape.

Computer Vision

import numpy as np

def iou_score(pred_mask, true_mask):
    intersection = np.logical_and(pred_mask, true_mask).sum()
    union = np.logical_or(pred_mask, true_mask).sum()
    return intersection / union if union != 0 else 1.0

def dice_score(pred_mask, true_mask):
    intersection = np.logical_and(pred_mask, true_mask).sum()
    total = pred_mask.sum() + true_mask.sum()
    return 2 * intersection / total if total != 0 else 1.0

# Example masks
pred_mask = np.array([[0, 1, 1],
                      [0, 1, 0],
                      [0, 0, 0]], dtype=bool)
true_mask = np.array([[1, 1, 0],
                      [0, 1, 0],
                      [0, 0, 0]], dtype=bool)

print(f"IoU score: {iou_score(pred_mask, true_mask):.2f}")
print(f"Dice score: {dice_score(pred_mask, true_mask):.2f}")

Important Notes

IoU and Dice scores range from 0 to 1, where 1 means perfect overlap.

Always use masks of the same size and shape for correct evaluation.

Dice score tends to be higher than IoU for the same masks because it doubles the intersection.

Summary

IoU and Dice are simple ways to measure how well a model finds shapes in images.

They compare predicted and true masks by looking at overlap and total area.

Higher scores mean better segmentation quality.