Artist-drawn images with distinctly colored, piecewise continuous boundaries, which are referred to as semi-structured imagery in this thesis, are very common in online raster databases and typically allow for a perceptually unambiguous mental vector interpretation. Yet, perhaps surprisingly, existing vectorization algorithms frequently fail to generate these viewer-expected interpretations on such imagery. In particular, the vectorized region boundaries they produce frequently diverge from those anticipated by viewers. This thesis proposes a new approach to region boundary vectorization that targets semi-structured inputs, and leverages observations about human perception of shapes to generate vector images consistent with viewer expectations. When viewing raster imagery, observers expect the vector output to be an accurate representation of the raster input. However, perception studies suggest that viewers implicitly account for the lossy nature of the rasterization process and mentally smooth and simplify the observed boundaries. The core algorithmic challenge is to balance these conflicting cues and obtain a piecewise continuous vectorization whose discontinuities, or corners, are aligned with human expectations.This work centers around a simultaneous spline fitting and corner detection method that combines a learned metric, that approximates human perception of boundary discontinuities on raster inputs, with perception-driven algorithmic discontinuity analysis. The resulting method balances local cues provided by the learned metric with global cues obtained by balancing simplicity and continuity expectations.Given the finalized set of corners, the proposed framework connects those using simple, continuous curves that capture input regularities. The proposed method is demonstrated on a range of inputs, with its superiority validated over existing alternatives via an extensive comparative user study.iii Lay SummarySemi-structured images with visually distinct regions and perceptually clear region boundaries are natural candidates for vector representation. However, due to historic reasons, large numbers of such images are saved in raster form. Converting them to vector would enable more compact representations, artifact-free resizing, and other applications. Surprisingly, existing state-of-the-art vectorization methods produce multiple visible artifacts when processing such inputs. This thesis presents a perception-driven vectorization method designed for such semi-structured inputs that produces output vectorizations wellaligned with viewer expectation.iv . The implementation of the methods and the data analysis has been done by Shayan Hoshyari. Edoardo Dominici implemented the method of Chapter 6, and helped with the conduction of the user study. Shayan Hoshyari was provided with invaluable guidance from Alla Sheffer, Nathan Carr, Duygu Ceylan, and Zhaowen Wang throughout the process.The user study in Chapter 7 has been conducted with the approval of the University of British Columbia (UBC BREB Number H16-02...
Raster clip-art images, which consist of distinctly colored regions separated by sharp boundaries typically allow for a clear mental vector interpretation. Converting these images into vector format can facilitate compact lossless storage and enable numerous processing operations. Despite recent progress, existing vectorization methods that target such data frequently produce vectorizations that fail to meet viewer expectations. We present PolyFit , a new clip-art vectorization method that produces vectorizations well aligned with human preferences. Since segmentation of such inputs into regions had been addressed successfully, we specifically focus on fitting piecewise smooth vector curves to the raster input region boundaries, a task prior methods are particularly prone to fail on. While perceptual studies suggest the criteria humans are likely to use during mental boundary vectorization, they provide no guidance as to the exact interaction between them; learning these interactions directly is problematic due to the large size of the solution space. To obtain the desired solution, we first approximate the raster region boundaries with coarse intermediate polygons leveraging a combination of perceptual cues with observations from studies of human preferences. We then use these intermediate polygons as auxiliary inputs for computing piecewise smooth vectorizations of raster inputs. We define a finite set of potential polygon to curve primitive maps, and learn the mapping from the polygons to their best fitting primitive configurations from human annotations, arriving at a compact set of local raster and polygon properties whose combinations reliably predict human-expected primitive choices. We use these primitives to obtain a final globally consistent spline vectorization. Extensive comparative user studies show that our method outperforms state-of-the-art approaches on a wide range of data, where our results are preferred three times as often as those of the closest competitor across multiple types of inputs with various resolutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.