Abstract
Interest point detectors (e.g. SIFT, SURF, and MSER) have been successfully applied to numerous applications in high level computer vision tasks such as object detection, and image classification. Despite their popularity, the perceptual relevance of these detectors has not been thoroughly studied. Here, perceptual relevance is meant to define the correlation between these point detectors and free-viewing human fixations on images. In this work, we provide empirical evidence to shed light on the fundamental question: 'Do humans fixate on interest points in images?'. We believe that insights into this question may play a role in improving the performance of vision systems that utilize these interest point detectors. We conduct an extensive quantitative comparison between the spatial distributions of human fixations and automatically detected interest points on a recently released dataset of 1003 images. This comparison is done at both the global (image) level as well as the local (region) level. Our experimental results show that there exists a weak correlation between the spatial distributions of human fixation and interest points.
| Original language | English (US) |
|---|---|
| Title of host publication | ICPR 2012 - 21st International Conference on Pattern Recognition |
| Pages | 2784-2787 |
| Number of pages | 4 |
| State | Published - 2012 |
| Event | 21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan Duration: Nov 11 2012 → Nov 15 2012 |
Publication series
| Name | Proceedings - International Conference on Pattern Recognition |
|---|---|
| ISSN (Print) | 1051-4651 |
Other
| Other | 21st International Conference on Pattern Recognition, ICPR 2012 |
|---|---|
| Country/Territory | Japan |
| City | Tsukuba |
| Period | 11/11/12 → 11/15/12 |
Bibliographical note
Funding Information:The prevention of avoidable blindness requires long-term provision to take effect1. The budget for such programs allocated by the government is usually limited, temporary and irregular, and therefore the operating expense of an MVVU project is frequently unsustainable. Furthermore, the support of the village chief, funding from an NGO (such as the Tzu Chi Foundation and Mennonite Foundation), and the policy of the administrative bureau are important supporting factors for operating an MVVU. The continued support of NGOs in funding and manpower, increased efforts in cataract surgery referral, and the inclusion of a low-vision aid professional as an eyecare team member are crucial for the success of an MVVU project.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition