Publication

Categorical object properties outweigh local visual information in object recognition

2024

Abstract

Certain parts of an object are more critical for recognition than others. Despite decades of research, it is not well understood what these parts are and how they interact with each other. This study investigates if and to which extent categorical object properties interact with local visual information in object recognition. Fifty participants classified fragmented objects from 12 categories, each consisting of 4 unique exemplars (48 objects in total). Exemplars differed in orientation and shape. Their outlines were presented as either curved segments or dots, providing high and low local visual information respectively. Spatial frequencies and fragment’s size were comparable. We gradually increased the number of fragments to quantify the minimum number of fragments necessary to recognize objects. A linear mixed model indicates that participants required significantly fewer curved segments than dots to recognize objects (F(1,48) = 248.05, p

Official source

https://infoscience.epfl.ch/entities/publication/fbe1c611-d29f-416c-8504-57e0529cabc7

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2024

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/fbe1c611-d29f-416c-8504-57e0529cabc7

About this result

Related concepts (32)

Object recognition (cognitive science)

Visual object recognition refers to the ability to identify the objects in view based on visual input. One important signature of visual object recognition is "object invariance", or the ability to identify objects across changes in the detailed context in which objects are viewed, including changes in illumination, object pose, and background context. Neuropsychological evidence affirms that there are four specific stages identified in the process of object recognition.

Visual system

The visual system comprises the sensory organ (the eye) and parts of the central nervous system (the retina containing photoreceptor cells, the optic nerve, the optic tract and the visual cortex) which gives organisms the sense of sight (the ability to detect and process visible light) as well as enabling the formation of several non-image photo response functions. It detects and interprets information from the optical spectrum perceptible to that species to "build a representation" of the surrounding environment.

Monoidal category

In mathematics, a monoidal category (or tensor category) is a equipped with a bifunctor that is associative up to a natural isomorphism, and an I that is both a left and right identity for ⊗, again up to a natural isomorphism. The associated natural isomorphisms are subject to certain coherence conditions, which ensure that all the relevant s commute. The ordinary tensor product makes vector spaces, abelian groups, R-modules, or R-algebras into monoidal categories. Monoidal categories can be seen as a generalization of these and other examples.

Related publications (4)

Categorical object properties outweigh local visual information in object recognition

Chat with Graph Search

Temporal Human Visual Attention in Window Views: Dynamic Gaze Patterns Analysis and Deep Learning-Based Spatio-Temporal Saliency Estimation

CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments

Qualified Inheritance in Spatio-Temporal Databases