Surface versus edge-based determinants of visual recognition.

By Irving Biederman, Ginny Ju. 1988

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (2020, background): “For example, humans can recognize visual scenes from line drawings as quickly and accurately as they can from photographs [3].”
The Bank of Standardized Stimuli (BOSS), a New Set of 480 Normative Photos of Objects to Be Used as Visual Stimuli in Cognitive Research (2010, background): “This difference was observed between colored and grayscale photos [54] but also between Snodgrass and Vanderwart’s original pictures and colored versions of these pictures [20,55], as well as between line-drawn pictures and colored photos [56,57].”
Psychology of Aesthetics, Creativity, and the Arts (2011, background): “…carry information about the global configuration of images (Goffaux et al., 2005) useful for rendering accurate spatial relationships and HSFs carry edge and detail information (Biederman, 1987; Biederman & Ju, 1988; Marr & Hildreth, 1980) useful for rendering individual facial features in detail.”
Revisiting Snodgrass and Vanderwart's Object Pictorial Set: The Role of Surface Detail in Basic-Level Object Recognition (2004, background): “Yet, it has been argued that these conditions are particular, and that color and other surface details do not play a role in basic-level object recognition, under normal viewing conditions ( èveryday object recognition', Biederman and Ju 1988).”
Perceived Shape Similarity among Unfamiliar Objects and the Organization of the Human Object Vision Pathway (2008, background): “Object shape and shape similarity among objects is important for the categorization and identification of objects (Rosch et al., 1976; Tversky and Hemenway, 1984; Biederman and Ju, 1988).”
Multiscale Categorical Object Recognition Using Contour Fragments (2008, background): “This simple demonstration confirms the intuition that fragments of contour can be used to successfully recognize objects in images, and detailed psychophysical studiessuchas[ 9 ],[17]bearthisout.Withthisinspiration,we set out to build an automatic object recognition system that uses only the cue of ”
Shape discovery from unlabeled image collections (2009, methodology): “We propose a shape discovery method in which local appearance (patch) matches serve to anchor the surrounding edge fragments, yielding a more reliable affinity function for images that accounts for both shape and appearance.”
From a Set of Shapes to Object Discovery (2010, background): “In psychophysics, it is widely recognized that shape is one of the most categorical object properties [1].”
Face Recognition Using Line Edge Map (2002, background): “This section overviews the major human face recognition techniques that apply mostly to frontal faces.”
Why Do Line Drawings Work? A Realism Hypothesis (2020, background): “Yet, we easily perceive shape and object identity in line drawings, with nearly the same accuracy and speed as we do for photorealistic images, see Biederman and Ju (1988) and Cole et al. (2009).”
Separate channels for processing form, texture, and color: evidence from FMRI adaptation and visual object agnosia. (2010, background): “Surface cues can be highly diagnostic for object identification in natural versus manufactured objects (Biederman and Ju 1988; Tanaka and Presnell 1999), when recognition takes place among objects belonging to the same structural category (Price and Humphreys 1989), or when shape diagnosticity is re”