Some Fuzzy Tools for Evaluation of Computer Vision Algorithms

2018 ◽  
Vol 8 (1) ◽  
pp. 1-14
Author(s):  
Andrey Osipov
Keyword(s):  
Computer Vision ◽  
Performance Evaluation ◽  
Face Recognition ◽  
Set Theory ◽  
Fuzzy Set Theory ◽  
Evaluation Method ◽  
Similarity Measures ◽  
Ground Truth ◽  
Fuzzy Similarity ◽  
Segmentation Quality

In this article, some issues related to the performance evaluation of computer vision algorithms within the version of direct empirical supervised evaluation method developed at SRISA RAS are considered. This approach partly relies on the elements defined by using the fuzzy set theory, in particular, fuzzy similarity measures and fuzzy reference ground truth images. Some known measures of segmentation quality are considered and their extensions, representing the fuzzy similarity measures, are offered. As an example, the author considers an application of fuzzy ground truth images and fuzzy similarity measures, including some newly introduced ones, to the evaluation of face recognition algorithms.

scholarly journals PERFORMANCE EVALUATION OF COMPUTER SYSTEM WITH FAILURE BASED ON FUZZY SET THEORY

1995 ◽  
Vol 38 (4) ◽  
pp. 409-422 ◽  
Author(s):  
Jung Bok Jo ◽  
Yasuhiro Tsujimura ◽  
Mitsuo Gen ◽  
Genji Yamazaki
Keyword(s):  
Performance Evaluation ◽  
Computer System ◽  
Set Theory ◽  
Fuzzy Set ◽  
Fuzzy Set Theory

A NOVEL APPROACH TO IMAGE THRESHOLDING BASED ON 2D HOMOGENEITY HISTOGRAM AND MAXIMUM FUZZY ENTROPY

2011 ◽  
Vol 07 (01) ◽  
pp. 105-133 ◽  
Author(s):  
H. D. CHENG ◽  
YANHUI GUO ◽  
YINGTAO ZHANG
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Set Theory ◽  
Fuzzy Set ◽  
Fuzzy Set Theory ◽  
Fuzzy Entropy ◽  
Image Thresholding ◽  
Novel Approach ◽  
Entropy Principle

Image thresholding is an important topic for image processing, pattern recognition and computer vision. Fuzzy set theory has been successfully applied to many areas, and it is generally believed that image processing bears some fuzziness in nature. In this paper, we employ the newly proposed 2D homogeneity histogram (homogram) and the maximum fuzzy entropy principle to perform thresholding. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can select the thresholds automatically and effectively. Especially, it not only can process "clean" images, but also can process images with different kinds of noises and images with multiple kinds of noise well without knowing the type of the noise, which is the most difficult task for image thresholding. It will be useful for applications in computer vision and image processing.

Similarity Measures for Face Recognition

2015 ◽  
Keyword(s):  
Computer Vision ◽  
Face Recognition ◽  
Facial Recognition ◽  
Similarity Measures ◽  
Corrective Surgery ◽  
Mahalanobis Distances ◽  
Computer Scientists ◽  
Criminal Suspects ◽  
Recognition Systems ◽  
Minkowski Distances

Similarity Measures for Face Recognition Face recognition has several applications, including security, such as (authentication and identification of device users and criminal suspects), and in medicine (corrective surgery and diagnosis). Facial recognition programs rely on algorithms that can compare and compute the similarity between two sets of images. This eBook explains some of the similarity measures used in facial recognition systems in a single volume. Readers will learn about various measures including Minkowski distances, Mahalanobis distances, Hansdorff distances, cosine-based distances, among other methods. The book also summarizes errors that may occur in face recognition methods. Computer scientists "facing face" and looking to select and test different methods of computing similarities will benefit from this book. The book is also useful tool for students undertaking computer vision courses.

Evaluation of Rolling Bearing Vibration Using Fuzzy Set Theory and Chaos Theory

2012 ◽  
Vol 424-425 ◽  
pp. 338-341 ◽  
Author(s):  
Xiao Chao Sun ◽  
Xin Tao Xia ◽  
Yan Bin Liu ◽  
Lei Lei Gao
Keyword(s):  
Phase Space ◽  
Set Theory ◽  
Fuzzy Set ◽  
Chaos Theory ◽  
Fuzzy Set Theory ◽  
Rolling Bearing ◽  
Similarity Coefficient ◽  
Vibration Acceleration ◽  
Fuzzy Similarity ◽  
Bearing Vibration

The optimal fuzzy similarity coefficient based on the phase space is proposed to evaluate the rolling bearing vibration acceleration generated by wear on the surface of the ring raceway. The phase space of the time series of the rolling bearing vibration acceleration is reconstructed via the chaos theory, the fuzzy similarity relation between the phase trajectories is established by the fuzzy set theory, and then the optimal fuzzy similarity coefficient is obtained through a reasonable choice of the embedding dimension and the delay. Experimental investigation shows that with the increase of the fault diameter, the optimal fuzzy similarity coefficient decreases nonlinearly

A New Approach for Face Recognition Performance Evaluation for Robot Using LED Monitor

2014 ◽  
Vol 548-549 ◽  
pp. 939-942 ◽  
Author(s):  
Mi Young Cho ◽  
Young Sook Jeong ◽  
Byung Tae Chun
Keyword(s):  
Performance Evaluation ◽  
Face Recognition ◽  
Evaluation Method ◽  
Recognition Performance ◽  
Test Methods ◽  
Human Robot Interaction ◽  
Point Of View ◽  
Service Robots ◽  
Face Detection And Recognition ◽  
Performance Evaluation Method

With the increasing of service robots, human-robot interaction for natural communication between user and robot is becoming more and more important. Especially, face recognition is a key issue of HRI. Even though robots mainly use face detection and recognition to provide various services, it is still difficult to guarantee of performance due to insufficient test methods in point of view robot. So, we propose a new performance evaluation method for robot using LED monitor.

Sign in / Sign up

Export Citation Format

Share Document