Abstract
Shape is a defining feature of objects, and human observers can effortlessly compare shapes to determine how similar they are. Yet, to date, no image-computable model can predict how visually similar or different shapes appear. Such a model would be an invaluable tool for neuroscientists and could provide insights into computations underlying human shape perception. To address this need, we developed a model ('ShapeComp'), based on over 100 shape features (e.g., area, compactness, Fourier descriptors). When trained to capture the variance in a database of >25,000 animal silhouettes, ShapeComp accurately predicts human shape similarity judgments between pairs of shapes without fitting any parameters to human data. To test the model, we created carefully selected arrays of complex novel shapes using a Generative Adversarial Network trained on the animal silhouettes, which we presented to observers in a wide range of tasks. Our findings show that incorporating multiple ShapeComp dimensions facilitates the prediction of human shape similarity across a small number of shapes, and also captures much of the variance in the multiple arrangements of many shapes. ShapeComp outperforms both conventional pixel-based metrics and state-of-the-art convolutional neural networks, and can also be used to generate perceptually uniform stimulus sets, making it a powerful tool for investigating shape and object representations in the human brain.
Highlights
One of the most important goals for biological and artificial vision is the estimation and representation of shape
Different shape descriptors are measured in different units, so to combine the features into a consistent multidimensional space requires identifying a common scale
We find that the mean perceived similarity relationships between shapes were quite well predicted by distance in this feature space (Fig 2D–2F, r = 0.63, p < 0.01) suggesting that the 109 shape descriptors explain a substantial portion of the variance in human shape similarity of familiar objects
Summary
One of the most important goals for biological and artificial vision is the estimation and representation of shape. Shape is central to many other disciplines, including computational morphology [27], anatomy [28], molecular biology [29], geology [30], meteorology [31], computer vision [32], and computer graphics [33]. For all these fields, it would be exceedingly useful to be able to characterize and quantify the visual similarity between different shapes automatically and objectively (Fig 1A).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
