Surface segmentation based on the luminance and color statistics of natural scenes.

J Opt Soc Am A Opt Image Sci Vis

Department of Psychology, Box 0109, 9500 Gilman Drive, University of California, San Diego, San Diego, California 92093-0109, USA.

Published: July 2003

The luminance and color of surfaces in natural scenes are relatively independent under certain linear transformations, with the luminance of a surface providing little information about the color of that surface, and vice versa. However, differences in luminance between two locations in a natural scene remain strongly associated with differences in color. We used the statistics of the spatiochromatic structure of natural scenes as the priors for a Bayesian model that decides whether or not two points within an image fall on the same surface. This model provides a biologically plausible algorithm for surface segmentation that models observer segmentations well.

Download full-text PDF

Source
http://dx.doi.org/10.1364/josaa.20.001283DOI Listing

Publication Analysis

Top Keywords

natural scenes
12
surface segmentation
8
luminance color
8
color statistics
8
surface
5
segmentation based
4
luminance
4
based luminance
4
color
4
natural
4

Similar Publications

Right data, wrong data: Statistical sampling and the making of modern agriculture in India.

Soc Stud Sci

January 2025

Amity Institute of Social Sciences, Amity University, Noida, Uttar Pradesh, India.

The size of India's food deficit became a pressing question for the Indian state in the early years of independence. As different organizations, government bodies, and individuals debated over the ways, means, and expertise needed to tide over the food crisis, policymakers realized that the primary requirement was to have a numerical understanding of the problem. Data became crucial to accurately assess production trends and compare them with requirements.

View Article and Find Full Text PDF

Objective: Family caregivers (FCGs) of cancer patients who are in hospice experience psychological challenges and poor quality of life (QOL) as a consequence of caregiving demands and anticipatory loss. Supportive interventions are needed. Exposure to nature offers a source of relaxation; however, FCGs are often homebound and have limited opportunities for respite.

View Article and Find Full Text PDF
Article Synopsis
  • The study focuses on using a recurrent neural network with complex numbers to perform image segmentation by analyzing spatiotemporal dynamics.
  • The network can effectively group different parts of an image based on the scene's structural features, demonstrating its versatility across various image types.
  • An exact mathematical solution of the network's dynamics is provided, clarifying how a single recurrent neural network with fixed weights can achieve object segmentation efficiently.
View Article and Find Full Text PDF

Time Course of Orientation Ensemble Representation in the Human Brain.

J Neurosci

January 2025

School of Psychological and Cognitive Sciences and Beijing Key Laboratory of Behavior and Mental Health, Peking University, Beijing 100871, People's Republic of China

Natural scenes are filled with groups of similar items. Humans employ ensemble coding to extract the summary statistical information of the environment, thereby enhancing the efficiency of information processing, something particularly useful when observing natural scenes. However, the neural mechanisms underlying the representation of ensemble information in the brain remain elusive.

View Article and Find Full Text PDF

Generation of Multiple-Depth 3D Computer-Generated Holograms from 2D-Image-Datasets Trained CNN.

Adv Sci (Weinh)

December 2024

Department of Information Communication, Army Academy of Armored Forces, Beijing, 100072, China.

Generating computer-generated holograms (CGHs) for 3D scenes by learning-based methods can reconstruct arbitrary 3D scenes with higher quality and faster speed. However, the homogenization and difficulty of obtaining 3D high-resolution datasets seriously limit the generalization ability of the model. A novel approach is proposed to train 3D encoding models based on convolutional neural networks (CNNs) using 2D image datasets.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!