On the Mathematical Morphology Based Coupler-Curve Feature Extraction for the Purpose of Synthesis of Path Generating Mechanism

2008 ◽  
Author(s):  
Jin Xie ◽  
Hui Yan ◽  
Yong Chen
Keyword(s):  
Feature Extraction ◽  
Mathematical Morphology ◽  
Fourier Transformation ◽  
Closed Curve ◽  
New Method ◽  
Structure Parameters ◽  
Translation Invariant ◽  
Tangent Circle ◽  
Key Issues ◽  
New Formula

To extract the features from a coupler curve is one of key issues in the synthesis of path generating mechanism. Fourier transformation is widely used at present. A new method of feature extraction, named mathematical morphology based method, emerges in resent years. Based on the essential operations of mathematical morphology, the shape spectrum (SS) of the coupler curve is computed. SS is rotation-scale-translation invariant. Therefore, as a means of describing coupler curve, it has possesses advantage over that based on Fourier transformation. In this paper, what kind information involved in SS of a curve is revealed. It is shown that the largest radius of internally tangent circle and the area inside of the curve can be inferred from its SS. This paper also shows that SS is without the information of the structure feature which is necessary to describe a nonsimple closed coupler curve. Eight-figure-shaped coupler curve is the simplest nonsimple closed curve. To describe such curve, three structure parameters of the curve should be involved besides that provided by SS of curve. A method using five numbers to describe and differentiate an eight-figure-shaped coupler curve is proposed in this paper. The five numbers can be obtained from its SS and the structure of the curve. A new formula to compute the similarity between two eight-figure-shaped couplers using the five numbers is presented.

A New Method of Nonlinear Feature Extraction for Multi-Fault Diagnosis of Rotor Systems

2010 ◽  
Vol 41 (10) ◽  
pp. 29-37 ◽  
Author(s):  
Zhixiong Li ◽  
Xinping Yan ◽  
Chengqing Yuan ◽  
Jiangbin Zhao ◽  
Zhongxiao Peng
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
New Method ◽  
Rotor Systems ◽  
Nonlinear Feature Extraction ◽  
Nonlinear Feature

scholarly journals Using control charts for on-line video summarisation

2019 ◽  
Vol 277 ◽  
pp. 01012 ◽  
Author(s):  
Clare E. Matthews ◽  
Paria Yousefi ◽  
Ludmila I. Kuncheva
Keyword(s):  
Feature Extraction ◽  
Control Chart ◽  
Control Charts ◽  
State Of The Art ◽  
Synthetic Data ◽  
New Method ◽  
Data Sets ◽  
On Line ◽  
Memory Constraints ◽  
Video Summarisation

Many existing methods for video summarisation are not suitable for on-line applications, where computational and memory constraints mean that feature extraction and frame selection must be simple and efficient. Our proposed method uses RGB moments to represent frames, and a control-chart procedure to identify shots from which keyframes are then selected. The new method produces summaries of higher quality than two state-of-the-art on-line video summarisation methods identified as the best among nine such methods in our previous study. The summary quality is measured against an objective ideal for synthetic data sets, and compared to user-generated summaries of real videos.

scholarly journals Feature Extraction Based on Non-Subsampled Shearlet Transform (NSST) with Application to SAR Image Data

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Huijie Ding ◽  
Arthur K. L. Lin
Keyword(s):  
Feature Extraction ◽  
Sparse Representation ◽  
Target Recognition ◽  
Image Feature ◽  
Sar Image ◽  
Translation Invariant ◽  
Shearlet Transform ◽  
Machine Learning Classification ◽  
Joint Sparse Representation ◽  
Multilevel Representations

Considering the defaults in synthetic aperture radar (SAR) image feature extraction, an SAR target recognition method based on non-subsampled Shearlet transform (NSST) was proposed with application to target recognition. NSST was used to decompose an SAR image into multilevel representations. These representations were translation-invariant, and they could well reflect the dominant and detailed properties of the target. During the machine learning classification stage, the joint sparse representation was employed to jointly represent the multilevel representations. The joint sparse representation could represent individual components independently while considering the inner correlations between different components. Therefore, the precision of joint representation could be enhanced. Finally, the target label of the test sample was determined according to the overall reconstruction error. Experiments were conducted on the MSTAR dataset to examine the proposed method, and the results confirmed its validity and robustness under the standard operating condition, configuration variance, depression angle variance, and noise corruption.

scholarly journals Instruction2vec: Efficient Preprocessor of Assembly Code to Detect Software Weakness with CNN

2019 ◽  
Vol 9 (19) ◽  
pp. 4086 ◽  
Author(s):  
Yongjun Lee ◽  
Hyun Kwon ◽  
Sang-Hoon Choi ◽  
Seung-Ho Lim ◽  
Sung Hoon Baek ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Experimental Results ◽  
New Method ◽  
Binary Analysis ◽  
Vulnerability Detection ◽  
Security Vulnerabilities ◽  
Assembly Code ◽  
Detection Techniques ◽  
Software Vulnerabilities ◽  
Analysis Technique

Potential software weakness, which can lead to exploitable security vulnerabilities, continues to pose a risk to computer systems. According to Common Vulnerability and Exposures, 14,714 vulnerabilities were reported in 2017, more than twice the number reported in 2016. Automated vulnerability detection was recommended to efficiently detect vulnerabilities. Among detection techniques, static binary analysis detects software weakness based on existing patterns. In addition, it is based on existing patterns or rules, making it difficult to add and patch new rules whenever an unknown vulnerability is encountered. To overcome this limitation, we propose a new method—Instruction2vec—an improved static binary analysis technique using machine. Our framework consists of two steps: (1) it models assembly code efficiently using Instruction2vec, based on Word2vec; and (2) it learns the features of software weakness code using the feature extraction of Text-CNN without creating patterns or rules and detects new software weakness. We compared the preprocessing performance of three frameworks—Instruction2vec, Word2vec, and Binary2img—to assess the efficiency of Instruction2vec. We used the Juliet Test Suite, particularly the part related to Common Weakness Enumeration(CWE)-121, for training and Securely Taking On New Executable Software of Uncertain Provenance (STONESOUP) for testing. Experimental results show that the proposed scheme can detect software vulnerabilities with an accuracy of 91% of the assembly code.

Sign in / Sign up

Export Citation Format

Share Document