One of the purposes of perception is to bridge between sensors and conceptual understanding. Marr's Primal Sketch combined initial edge-finding with multiple downstream processes to capture aspects of visual perception such as grouping and stereopsis. Given the progress made in multiple areas of AI since then, we have developed a new framework inspired by Marr's work, the Hybrid Primal Sketch, which combines computer vision components into an ensemble to produce sketch-like entities which are then further processed by CogSketch, our model of high-level human vision, to produce both more detailed shape representations and scene representations which can be used for data-efficient learning via analogical generalization. This paper describes our theoretical framework, summarizes several previous experiments, and outlines a new experiment in progress on diagram understanding.
@article{arxiv.2407.04859,
title = {Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understanding},
author = {Kenneth D. Forbus and Kezhen Chen and Wangcheng Xu and Madeline Usher},
journal= {arXiv preprint arXiv:2407.04859},
year = {2024}
}