Search

In “Multidimensional Bernstein polynomials and Bezier curves: Analysis of machine learning algorithm for facial ex- ´ pression recognition based on curvature, Appl. Math. Comput. 344–345 (2019) 150–162”, some statistical evaluations on feature vectors were given in order to analyse their meaningfulness while classifying human facial expressions. In this paper, by using some results arising from SPSS program, we provide some further statistical evaluations and observations which are related to features based on the calculated Hausdorff distances between Bezier curves belonging to the regions that shape human facial expressions. [ABSTRACT FROM AUTHOR]

The main purpose of interest points detection (IPD) for 3D objects based on Harris operator is to find the fast computation of weighted average of the derivative data for different points. In this paper, we analyze the extension of Harris operator using Hausdorff distance (EHOHD) and propose the extension of Harris operator using Hilbert scanning distance (EHOHSD) as a new proposed method to IPD on 3D manifold triangular meshes data. Proposed EHOHSD method is 6–16 times faster than EHOHD method. The quality of this IPD with EHOHSD was measured using the repeatability criterion. [ABSTRACT FROM PUBLISHER]

In this paper, a novel license plate recognition algorithm is presented based on Hausdorff distance direct to community vehicle monitoring. This method utilizes colour and edge characters, meanwhile, combines some conventional image preprocessing methods to get several region of interest. In order to recognize the license plate, a well-organized digital models is prepared in initialization, and the Hausdorff distance is computed to recognize the vehicle characters according the threshold be defined before. The resulting of algorithm, which shows some tolerant of small location errors occurring in edge detection and has good robustness and efficiency. [ABSTRACT FROM PUBLISHER]

In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases. [ABSTRACT FROM PUBLISHER]

This paper presents a particle filter for object tracking using the combination of shape and texture features. Local descriptors contribute to estimation by filtering out some irrelevant observations, making it more reliable. We introduces an online feature adaptation mechanism that enables to automatically select the best set of features in presence of time varying and complex background, occlusions, etc. Experimental results on real-would videos demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM PUBLISHER]

Biometric authentication provides a high security and reliable approach to be used in security access system. However, this authentication method has not been widely implemented in a resource-constrained embedded system. In this project, we investigate a method of personal authentication based on infrared vein pattern in the back of the hand. A biometric feature is extracted from the vein pattern image and create database. The current image matched with the database and identify that personal is authenticate or not. In this project the algorithm consists of four modules: image capturing, image pre-processing, feature extraction, and the authentication module. Attach the IR web camera to the door, automatically when any person open the door camera will capture the back hand vein of images, using hough threshold method draw the circle on the vein and attaching all the center of the circle and get thinning images, which is use to reduce the error segmentation problem. Then Minutiae feature extraction include different point. Housdroff Distance is technique measuring of two images. If that image is match then only the door is open otherwise it not. This system directly recognizes the shapes of the vein pattern by ensuring their Line-Segment Hausdorff Distance. [ABSTRACT FROM PUBLISHER]

Development of sensors and systems for detection of chemical compounds is an important challenge with applications in areas such as anti-terrorism, demining, and environmental monitoring. A newly developed colorimetric sensor array is able to detect explosives and volatile organic compounds; however, each sensor reading consists of hundreds of pixel values, and methods for combining these readings from multiple sensors must be developed to make a classification system. In this work we examine two distance based classification methods, K-Nearest Neighbor (KNN) and Gaussian process (GP) classification, which both rely on a suitable distance metric. We evaluate a range of different distance measures and propose a method for sensor fusion in the GP classifier. Our results indicate that the best choice of distance measure depends on the sensor and the chemical of interest. [ABSTRACT FROM PUBLISHER]

In this present work, we propose two approximation methods of a novel curved surface representation which is relatively invariant under 3D motion group, introduced in our recent work [11]. It is constructed from the superposition of two geodesic potentials of two fixed surface points. From this representation, finite invariant points could be extracted locally in the neighborhood of such two reference points. By comparing each approximation method with a reference representation computed on an analytical surface, the best method is retained by the way of the Hausdorff distance in the shape space. Subsequently, this approximation algorithm is applied to analyze the shape of 3D human faces. Its discrimination power has been identified by experimentations performed on the database Bosphorus. [ABSTRACT FROM AUTHOR]

Mutual information is a widely-used metric in medical image registration, which achieves many good results; however, it may lead to misregistration because of the absence of spatial information. In order to solve this problem, this paper proposes an improved hybrid metric combining mutual information and spatial information. The spatial information is obtained through calculating Hausdorff fraction. In experiments, mutual information is used as a comparative method. Experiments show that the proposed method performs well in multiphase contrast-enhanced abdomen CT image non-rigid registration problems. [ABSTRACT FROM PUBLISHER]

Large numbers of image databases now exist that contain multiple modified versions of the same image. An extreme example of this is the large number of modified versions of images on the internet (web site). There is a need to develop tools that will enable the identification of all of the original and modified versions of the same images. Thus, in this paper proposes a robust method for image identification with variant illumination, compression, flip, scaling, rotation and gray scale conversion. Techniques introduced in this work are composed of two stages. First, the signature of image is to be detected by the Trace Transform. Then, in the second stage, the Hausdorff distance and Modified Shape Context are employed to measure and determine of similarity between models and test images. Finally, our method is evaluated with experiments on a set of over 60,000 unique images and one billion image pairs. The extensive experimental results show detection rate of over 83% at false-positive rate below 1 per million. [ABSTRACT FROM AUTHOR]