Emergence Model of Perception With Global-Contour Precedence Based on Gestalt Theory and Primary Visual Cortex

Perceptual edge grouping is a technique for organizing the cluttered edge pixels into meaningful structures and further serves high-level vision tasks, which has long been a basic and critical task in computer vision. Existing methods usually have a poor performance when coping with the junctions ca...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 34; pp. 2721 - 2736
Main Authors: Li, Jingmeng, Wei, Hui
Format: Journal Article
Language:English
Published: United States IEEE 01.01.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Computational modeling
Computer vision
Error reduction
Gestalt Theory
global precedence effect
Graph theory
Humans
Image edge detection
Image Processing, Computer-Assisted - methods
Image segmentation
Noise
Object detection
Occlusion
Organizations
perceptual edge grouping
Perceptual organization
primary visual cortex
Primary Visual Cortex - diagnostic imaging
Primary Visual Cortex - physiology
Psychology
Segments
Vectors
Visual Cortex - physiology
Visual Perception - physiology
Visual systems
Visual tasks
Visualization
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Perceptual edge grouping is a technique for organizing the cluttered edge pixels into meaningful structures and further serves high-level vision tasks, which has long been a basic and critical task in computer vision. Existing methods usually have a poor performance when coping with the junctions caused by occlusion and noise in natural images. In this paper, we present GPGrouper, a perceptual edge grouping model based on gestalt theory and the primary visual cortex (V1). Different from the existing methods, GPGrouper leverages the edge representation and grouping matrix (ERGM), a functional structure inspired by V1 mechanisms, to represent edges in a way that can effectively reduce grouping errors caused by occlusion between objects. ERGM is trained with natural image contours and further provides a priori guidance for the construction of the edge connection graph (ECG) that is useful to minimize the impact of noise on grouping. In the experiment, we compared GPGrouper and the state-of-the-art (SOTA) method of perceptual grouping on the visual psychology pathfinder challenge. The results demonstrate that GPGrouper outperforms the SOTA method in grouping performance. Furthermore, in the grouping experiments involving line segments with varying lengths detected by the Line Segment Detector (LSD), as well as those involving superpixel segmentation results with significant levels of interfering noise using the SLIC algorithm, GPGrouper was superior to the existing methods in terms of grouping effect and robustness. Moreover, the results of applying the grouping results to the vision tasks objectness demonstrate that GPGrouper can contribute significantly to high-level visual tasks.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2025.3562054