Reasoning with shapes: profiting cognitive susceptibilities to infer linear mapping transformations between shapes

TL;DR

This paper introduces a hierarchical, iterative method for inferring linear shape transformations in images, inspired by human scene understanding, with efficient computation and robustness to noise and deformation.

Contribution

It proposes a novel hierarchical approach using polar coordinates and graph traversal to accurately and efficiently determine shape transformations, inspired by cognitive science insights.

Findings

Method achieves high accuracy on normal, noisy, and deformed images.

Optimal transformations found in logarithmic iterations.

Computational cost is resolution-independent.

Abstract

Visual information plays an indispensable role in our daily interactions with environment. Such information is manipulated for a wide range of purposes spanning from basic object and material perception to complex gesture interpretations. There have been novel studies in cognitive science for in-depth understanding of visual information manipulation, which lead to answer questions such as: how we infer 2D/3D motion from a sequence of 2D images? how we understand a motion from a single image frame? how we see forest avoiding trees? Leveraging on congruence, linear mapping transformation determination between a set of shapes facilitate motion perception. Present study methodizes recent discoveries of human cognitive ability for scene understanding. The proposed method processes images hierarchically, that is an iterative analysis of scene abstractions using a rapidly converging heuristic iterative method. The method hierarchically abstracts images; the abstractions are represented in polar coordinate system, and any two consecutive abstractions have incremental level of details. The method then creates a graph of approximated linear mapping transformations based on circular shift permutations of hierarchical abstractions. The graph is then traversed in best-first fashion to find best linear mapping transformation. The accuracy of the proposed method is assessed using normal, noisy, and deformed images. Additionally, the present study deduces (i) the possibility of determining optimal mapping linear transformations in logarithmic iterations with respect to the precision of results, and (ii) computational cost is independent from the resolution of input shapes.