Imageability is a measure of how easily a physical object, word or environment will evoke a clear mental image in the mind of any person observing it. It is used in architecture and city planning, in psycholinguistics, and in automated computer vision research. In automated image recognition, training models to connect images with concepts that have low imageability can lead to biased and harmful results.

History and components

Kevin A. Lynch first introduced the term, "imageability" in his 1960 book, '' The Image of the City''. In the book, Lynch argues cities contain a key set of physical elements that people use to understand the environment, orient themselves inside of it, and assign it meaning. Lynch argues the five key elements that impact the imageability of a city are Paths, Edges, Districts, Nodes, and Landmarks. * Paths: channels in which people travel. ''Examples:

street A street is a public thoroughfare in a built environment. It is a public parcel of land adjoining buildings in an urban context, on which people may freely assemble, interact, and move about. A street can be as simple as a level patch of d ...

sidewalk A sidewalk (North American English), pavement (British English), footpath in Australia, India, New Zealand and Ireland, or footway, is a path along the side of a street, highway, terminals. Usually constructed of concrete, pavers, brick, stone ...

s, trails,

canal Canals or artificial waterways are waterways or engineered channels built for drainage management (e.g. flood control and irrigation) or for conveyancing water transport vehicles (e.g. water taxi). They carry free, calm surface fl ...

railroad Rail transport (also known as train transport) is a means of transport that transfers passengers and goods on wheeled vehicles running on rails, which are incorporated in tracks. In contrast to road transport, where the vehicles run on a pre ...

s.'' * Edges: objects that form boundaries around space. ''Examples:

wall A wall is a structure and a surface that defines an area; carries a load; provides security, shelter, or soundproofing; or, is decorative. There are many kinds of walls, including: * Walls in buildings that form a fundamental part of the su ...

s, buildings,

shore A shore or a shoreline is the fringe of land at the edge of a large body of water, such as an ocean, sea, or lake. In physical oceanography, a shore is the wider fringe that is geologically modified by the action of the body of water p ...

line,

curbstone A curb (North American English), or kerb (Commonwealth English except Canada; see spelling differences), is the edge where a raised sidewalk or road median/central reservation meets a street or other roadway. History Although curbs have ...

, streets, and

overpass An overpass (called an overbridge or flyover in the United Kingdom and some other Commonwealth countries) is a bridge, road, railway or similar structure that crosses over another road or railway. An ''overpass'' and ''underpass'' together form ...

es.'' *

District A district is a type of administrative division that, in some countries, is managed by the local government. Across the world, areas known as "districts" vary greatly in size, spanning regions or county, counties, several municipality, municipa ...

s: medium to large areas people can enter into and out of that have a common set of identifiable characteristics. * Nodes: large areas people can enter, that serve as the foci of the city, neighborhood, district, etc. *

Landmark A landmark is a recognizable natural or artificial feature used for navigation, a feature that stands out from its near environment and is often visible from long distances. In modern use, the term can also be applied to smaller structures or f ...

s: memorable points of reference people cannot enter into. ''Examples: signs, mountains and public art.'' In 1914, half a century before ''The Image of the City'' was published, Paul Stern discussed a concept similar to imageability in the context of art. Stern, in Susan Langer's ''Reflections on Art,'' names the attribute that describes how vividly and intensely an artistic object could be experienced ''apparency.''

In computer vision

Automated image recognition was developed by using machine learning to find patterns in large, annotated datasets of photographs, like ImageNet. Images in ImageNet are labelled using concepts in

WordNet WordNet is a lexical database of semantic relations between words in more than 200 languages. WordNet links words into semantic relations including synonyms, hyponyms, and meronyms. The synonyms are grouped into ''synsets'' with short definit ...

. Concepts that are easily expressed verbally, like "early", are seen as less "imageable" than nouns referring to physical objects like "leaf". Training AI models to associate concepts with low imageability with specific images can lead to problematic bias in image recognition algorithms. This has particularly been critiqued as it relates to the "person" category of WordNet and therefore also ImageNet. Trevor Pagan and

Kate Crawford Kate Crawford (born 1976) is a writer, composer, producer and academic. Crawford is a principal researcher at Microsoft Research (Social Media Collective), the co-founder and former director of research at the AI Now Institute at NYU, a visiting ...

demonstrated in their essay "Excavating AI" and their art project ImageNet Roulette how this leads to photos of ordinary people being labelled by AI systems as "terrorists" or "sex offenders".{{Cite journal , last1=Crawford , first1=Kate , author-link=Kate Crawford , last2=Trevor , first2=Pagan , author-link2=Trevor Paglen , date=2019 , title=Excavating AI: The Politics of Images in Machine Learning Datasets , url=https://www.excavating.ai , journal=The AI Now Institute Images in datasets are often labelled as having a certain level of imageability. As described by Kaiyu Yang,

Fei-Fei Li Fei-Fei Li (; born 1976) is a Chinese-American computer scientist who is known for establishing ImageNet, the dataset that enabled rapid advances in computer vision in the 2010s. She is the Sequoia Capital Professor of Computer Science at Sta ...

and co-authors, this is often done following criteria from

Allan Paivio Allan Urho Paivio (March 29, 1925 – June 19, 2016) was a professor of psychology at the University of Western Ontario and former bodybuilder. He earned his Ph.D. from McGill University in 1959 and taught at the University of Western Ontario ...

and collaborators' 1968 psycholinguistic study of nouns. Yang el.al. write that dataset annotators tasked with labelling imageability "see a list of words and rate each word on a 1-7 scale from 'low imagery' to 'high imagery'. To avoid biased or harmful image recognition and image generation, Yang et.al. recommend not training vision recognition models on concepts with low imageability, especially when the concepts are offensive (such as sexual or racial slurs) or sensitive (their examples for this category include "orphan", "separatist", "Anglo-Saxon" and "crossover voter"). Even "safe" concepts with low imageability, like "great-niece" or "vegetarian" can lead to misleading results and should be avoided.

References

Psychogeography Environmental psychology Knowledge representation

History and components

In computer vision

See also

Further reading

References