Predicting Region of Interest in Human Visual Search Based on Statistical Texture and Gabor Features

PubMed 2026 Preprint Open access

Read full text
Authors: Hongwei Lin, Andrade, Diego, Mini Das, Howard C. Gifford
DOI: 10.48550/arxiv.2601.07998
Cited by: 0
References: 1

Abstract

) is observed between GLCM mean and Gabor feature responses, indicating that these features encode related image information despite their different formulations. Eye-tracking data from human observers further suggest consistency between predicted fixation regions and early-stage gaze behavior. These findings highlight the value of combining structural and texture-based features for modeling visual search and support the development of perceptually informed observer models.

Fields of Study & Subjects

Visual Attention and Saliency Detection Visual perception and processing mechanisms Image Retrieval and Classification Techniques

Publication details

Journal / source
PubMed
Publication date
12 January 2026
Language
EN
Document type
Preprint