Preattentive Colour Features by Steerable Filters
نویسندگان
چکیده
Abst ract. Visual search is the task of nding objects in an image which are described in a high dimensional space, spanned by preattentive features , e.g. orientation, scale, and colour. By using steerable lters this search space may be scanned continouosly, though spanned by discrete feature detectors. Based on this idea, we will show a method for detecting arbitrarily oriented bars from steerable lter responses. Detection performs rather invariant to illumination colour, exploiting the properties of the CIE{Lab colour space.
منابع مشابه
Oblique Random Forests for 3-D Vessel Detection Using Steerable Filters and Orthogonal Subspace Filtering
We propose a machine learning-based framework using oblique random forests for 3-D vessel segmentation. Two different kinds of features are compared. One is based on orthogonal subspace filtering where we learn 3-D eigenspace filters from local image patches that return task optimal feature responses. The other uses a specific set of steerable filters that show, qualitatively, similarities to t...
متن کاملBiometric identification through tongue texture measurements
This paper proposes a method of personal identification based on tongue image. Tongue image have many advantage for personal identification and verification. In this paper a texture tongue features are extracted based on steerable filters and WLD (Weber Law Descriptors) transform. These features can be used in forensic applications and with other robust biometrics features can combined multi mo...
متن کاملHarnessing Preattentive Processes for Multivariate Data Visualization
A new method for designing multivariate data visualization tools is presented . These tools allow users to perform simple tasks such as estimation, target detection, and detection of data boundaries rapidly and accurately. Our design technique is based on principles arising from an area of cognitive psychology called preattentive processing. Preattentive processing involves visual features that...
متن کاملHigh Accuracy Feature Detection for Camera Calibration: A Multi-steerable Approach
We describe a technique to detect and localize features on checkerboard calibration charts with high accuracy. Our approach is based on a model representing the sought features by a multiplicative combination of two edge functions, which, to allow for perspective distortions, can be arbitrarily oriented. First, candidate regions are identified by an eigenvalue analysis of the structure tensor. ...
متن کاملVisualization of Multivariate Data Using Preattentive Processing
A new method for designing multivariate data visualization tools is presented. Multivariate data visualization involves representation of data elements with multiple dimensions in a low dimensional enviroment, such as a computer screen or printed media. Our tools are designed to allow users to perform simple tasks like estimation, target detection, and detection of data boundaries rapidly and a...
متن کامل