Abstract
AbstracL Recently there has been a resurgence of interest in the properties of natural images. Their statistics are important not only in image compression but also far the study of sensory processing in biology, which can be viewed as satisfying cettain ‘design criteria’. This review summarizes previous work on image statistics and presents our own data Perhaps the most notable property of natural images is an invariance to scale. We present data to support this claim as well 35 evidence for a hierarchical invariance in natural scenes. These symmetries provide a powerful description of natunl images as they g ~ d y resttiit the class of allowed d i s Vib ut ions. 1.
Keywords
Affiliated Institutions
Related Publications
Dynamic scene understanding: The role of orientation features in space and time in scene classification
Natural scene classification is a fundamental challenge in computer vision. By far, the majority of studies have limited their scope to scenes from single image stills and there...
Configuration based scene classification and image indexing
Scene classification is a major open challenge in machine vision. Most solutions proposed so far such as those based on color histograms and local texture statistics cannot capt...
Statistics of natural images and models
Large calibrated datasets of 'random' natural images have recently become available. These make possible precise and intensive statistical studies of the local nature of images....
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
This paper presents a database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quanti...
Unified Perceptual Parsing for Scene Understanding
Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the object...
Publication Info
- Year
- 1994
- Type
- article
- Volume
- 5
- Issue
- 4
- Pages
- 517-548
- Citations
- 871
- Access
- Closed
External Links
Social Impact
Social media, news, blog, policy document mentions
Citation Metrics
Cite This
Identifiers
- DOI
- 10.1088/0954-898x_5_4_006