Learning a classification model for segmentation

TLDR

The study proposes a two‑class classification model to group image segments. The authors train a linear classifier on Gestalt‑cue features extracted from over‑segmented super‑pixels, using human segmentations as positives and random matches as negatives, and evaluate feature power with information‑theoretic analysis. Results demonstrate the model’s effectiveness across a wide range of images.

Abstract

We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is over-segmented into super-pixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightness and good continuation. Information-theoretic analysis is applied to evaluate the power of these grouping cues. We train a linear classifier to combine these features. To demonstrate the power of the classification model, a simple algorithm is used to randomly search for good segmentations. Results are shown on a wide range of images.