Category-Epitomes : Discriminatively Minimalist Representations for Object Categories

TL;DR

This paper introduces category-epitomes, sparse discriminative sketch-based representations of object categories derived from sequential stroke analysis, providing insights into the semantic structure and sparseness of freehand sketches.

Contribution

It proposes a novel method for creating minimal yet discriminative sketch representations called category-epitomes, along with a measure of sparseness called epitome-score.

Findings

Category-epitomes effectively distinguish object categories.

Epitome-scores quantify sketch sparseness.

Analysis offers new semantic insights into object categories.

Abstract

Freehand line sketches are an interesting and unique form of visual representation. Typically, such sketches are studied and utilized as an end product of the sketching process. However, we have found it instructive to study the sketches as sequentially accumulated composition of drawing strokes added over time. Studying sketches in this manner has enabled us to create novel sparse yet discriminative sketch-based representations for object categories which we term category-epitomes. Our procedure for obtaining these epitomes concurrently provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We construct and analyze category-epitomes and epitome-scores for freehand sketches belonging to various object categories. Our analysis provides a novel viewpoint for studying the semantic nature of object categories.