scholarly journals Interrelationship identification between humans from images using two class classifier

2018 ◽  
Vol 7 (2.21) ◽  
pp. 5 ◽  
Author(s):  
Amit Verma ◽  
T Meenpal ◽  
B Acharya
Keyword(s):  
Feature Extraction ◽  
Feature Detection ◽  
Confusion Matrix ◽  
Image Database ◽  
Identification Algorithm ◽  
Bag Of Words ◽  
Human Beings ◽  
Feature Detectors ◽  
Surf Features

The paper proposes an automatic interrelationship identification algorithm between human beings. The image database contains two interrelationship classes i.e. two people hugging and handshaking each other. The feature detection and feature extraction has been done using bag of words algorithm. SURF features and FAST features are used as feature detectors. Finally, the extracted features have been applied to SVM for classification. We have tested the classifier against a set of test images for both feature detectors.  Finally, the accuracy of the classifier has been calculated and confusion matrix has been plotted.  

scholarly journals Nowhere to Hide: A Novel Private Protocol Identification Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jiantao Shi ◽  
Xiangzhan Yu ◽  
Zechao Liu
Keyword(s):  
Feature Extraction ◽  
Rapid Development ◽  
Recognition Algorithm ◽  
Mobile Internet ◽  
Point Of View ◽  
Biological Information ◽  
Identification Algorithm ◽  
Human Beings ◽  
Private Data ◽  
Extraction Algorithm

In recent years, with the rapid development of mobile Internet and 5G technology, great changes have been brought to our lives, and human beings have stepped into the era of big data. These new features and techniques in 5G support many different types of mobile applications for users, which makes network security extremely challenging. Among them, more and more applications involve users’ private data, such as location information, financial information, and biological information. In order to prevent users’ privacy disclosure, most applications choose to use private protocols. However, such private protocols also provide a means for malware and malicious applications to steal users’ privacy and confidential data. From a more secure point of view, we need to provide a way for users to know how many private protocols are running on their mobile phones and distinguish which are authorized applications and which are not. Therefore, the analysis and identification of private protocols have become a hot topic in current research. How to extract the characteristics of network protocol effectively and identify the private protocol accurately becomes the most important part of this research. In this paper, we combine genetic algorithm and association rule algorithm and then propose a set of feature extraction algorithm and protocol recognition algorithm for unknown protocols. The experimental analysis based on the actual data shows that these methods can effectively solve the problems of feature extraction and recognition for unknown protocols and can greatly improve the accuracy of private protocol recognition.

Perception

2018 ◽  
Author(s):  
Joel Z. Leibo ◽  
Tomaso Poggio
Keyword(s):  
Computational Neuroscience ◽  
Feature Detection ◽  
Pedestrian Detection ◽  
Detection Systems ◽  
Catching Up ◽  
Feature Detectors ◽  
Recognition Systems ◽  
Engineered Systems ◽  
Perceptual Systems ◽  
The Brain

This chapter provides an overview of biological perceptual systems and their underlying computational principles focusing on the sensory sheets of the retina and cochlea and exploring how complex feature detection emerges by combining simple feature detectors in a hierarchical fashion. We also explore how the microcircuits of the neocortex implement such schemes pointing out similarities to progress in the field of machine vision driven deep learning algorithms. We see signs that engineered systems are catching up with the brain. For example, vision-based pedestrian detection systems are now accurate enough to be installed as safety devices in (for now) human-driven vehicles and the speech recognition systems embedded in smartphones have become increasingly impressive. While not being entirely biologically based, we note that computational neuroscience, as described in this chapter, makes up a considerable portion of such systems’ intellectual pedigree.

A hybrid feature extraction approach for brain MRI classification based on Bag-of-words

2019 ◽  
Vol 48 ◽  
pp. 144-152 ◽  
Author(s):  
Wadhah Ayadi ◽  
Wajdi Elhamzi ◽  
Imen Charfi ◽  
Mohamed Atri
Keyword(s):  
Feature Extraction ◽  
Brain Mri ◽  
Bag Of Words ◽  
Hybrid Feature Extraction

scholarly journals An Image Copy-Move Forgery Detection Scheme Based on A-KAZE and SURF Features

Symmetry ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 706 ◽  
Author(s):  
Chengyou Wang ◽  
Zhi Zhang ◽  
Xiao Zhou
Keyword(s):  
Feature Detection ◽  
Joint Photographic Expert Group ◽  
Social Stability ◽  
Forgery Detection ◽  
Detection Scheme ◽  
Speeded Up Robust Features ◽  
Image Blurring ◽  
Surf Features ◽  
Copy Move Forgery Detection ◽  
Processing Techniques

The popularity of image editing software has made it increasingly easy to alter the content of images. These alterations threaten the authenticity and integrity of images, causing misjudgments and possibly even affecting social stability. The copy-move technique is one of the most commonly used approaches for manipulating images. As a defense, the image forensics technique has become popular for judging whether a picture has been tampered with via copy-move, splicing, or other forgery techniques. In this paper, a scheme based on accelerated-KAZE (A-KAZE) and speeded-up robust features (SURF) is proposed for image copy-move forgery detection (CMFD). It is difficult for most keypoint-based CMFD methods to obtain sufficient points in smooth regions. To remedy this defect, the response thresholds for the A-KAZE and SURF feature detection stages are set to small values in the proposed method. In addition, a new correlation coefficient map is presented, in which the duplicated regions are demarcated, combining filtering and mathematical morphology operations. Numerous experiments are conducted to demonstrate the effectiveness of the proposed method in searching for duplicated regions and its robustness against distortions and post-processing techniques, such as noise addition, rotation, scaling, image blurring, joint photographic expert group (JPEG) compression, and hybrid image manipulation. The experimental results demonstrate that the performance of the proposed scheme is superior to that of other tested CMFD methods.

scholarly journals Detection of Fracture Bones in X-ray Images Categorization

2020 ◽  
pp. 1-11
Author(s):  
Adigun Oyeranmi ◽  
Babatunde Ronke ◽  
Rufai Mohammed ◽  
Aigbokhan Edwin
Keyword(s):  
Feature Extraction ◽  
Performance Metrics ◽  
Confusion Matrix ◽  
False Negative ◽  
Support Vector ◽  
Kappa Statistics ◽  
Fracture Detection ◽  
True Negative ◽  
Research Attention ◽  
X Ray

Fractured bone detection and categorization is currently receiving research attention in computer aided diagnosis system because of the ease it has brought to doctors in classification and interpretation of X-ray images.  The choice of an efficient algorithm or combination of algorithms is paramount to accurately detect and categorize fractures in X-ray images, which is the first stage of diagnosis in treatment and correction of damaged bones for patients. This is what this research seeks to address. The research design involves data collection, preprocessing, segmentation, feature extraction, classification and evaluation of the proposed method. The sample dataset were x-ray images collected from the Department of Radiology, National Orthopedic Hospital, Igbobi-Lagos, Nigeria as well as Open Access Medical Image Repositories. The image preprocessing involves the conversion of images in RGB format to grayscale, sharpening and smoothing using Unsharp Masking Tool.  The segmentation of the preprocessed image was carried out by adopting the Entropy method in the first stage and Canny edge method in the second stage while feature extraction was performed using Hough Transformation. Detection and classification of fracture image employed a combination of two algorithms;  K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) for detecting fracture locations based on four classification types: (normal, comminute, oblique and transverse).Two performance assessment methods were employed to evaluate the developed system. The first evaluation was based on confusion matrix which evaluates fracture and non-fracture on the basis of TP (True Positive), TN (True negative), FP (False Positive) and FN (False Negative). The second appraisal was based on Kappa Statistics which evaluates the type of fracture by determining the accuracy of the categorized fracture bone type. The result of first assessment for fracture detection shows that 26 out of 40 preprocessed images were fractured, resulting to the following three values of performance metrics: accuracy value of 90%, sensitivity of 87% and specificity of 100%. The Kappa coefficient error assessment produced accuracy of 83% during classification. The proposed method can find suitable use in categorization of fracture types on different bone images based on the results obtained from the experiment.

scholarly journals Prediction of Solid Garbage Waste Generation in Smart Cities using Naive Bayes Algorithm

2019 ◽  
Vol 9 (2S) ◽  
pp. 53-56
Keyword(s):  
Naive Bayes ◽  
Learning Algorithm ◽  
Smart Cities ◽  
Confusion Matrix ◽  
Daily Basis ◽  
Naïve Bayes ◽  
Human Beings ◽  
Waste Generation ◽  
Future Prediction ◽  
Bayes Algorithm

Smart cities which are becoming overcrowded today are making human beings life miserable and prone to more challenges on daily basis. Overcrowded is leading to vast generation of wastes contributing to air pollution and in turn is affecting health causing various diseases. Even though various measures are taken to recycle wastes, the rate at which it is being produced is becoming higher and higher. This paper deals with prediction of waste generation using Naïve Bayes machine learning algorithm(Classifier) based on the statistics of previous waste datasets. The datasets used for the future prediction are obtained from reliable sources. The implementation of the algorithm is done in Pyspark using Anaconda Jupyter. The performance of the classifier on the datasets is analyzed with confusion matrix and accuracy metric is used to rate the efficiency of the classifier. The accuracy obtained indicates that algorithm can be effectively used for real time prediction and it gives more accurate results for huge input datasets based on independence assumption.

scholarly journals An End-to-End Identification Algorithm for Smearing Star Image

2021 ◽  
Vol 13 (22) ◽  
pp. 4541
Author(s):  
Jinliang Han ◽  
Xiubin Yang ◽  
Tingting Xu ◽  
Zongqiang Fu ◽  
Lin Chang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Semantic Information ◽  
The Self ◽  
Identification Algorithm ◽  
Identification Rate ◽  
Star Image ◽  
Star Identification ◽  
Angular Velocities ◽  
End To End

In the previous study, there were a few direct star identification (star-ID) algorithms for smearing star image. An end-to-end star-ID algorithm is proposed in this article, to directly identify the smearing image from star sensors with fast attitude maneuvering. Combined with convolutional neural networks and the self-attention mechanism of transformer encoder, the algorithm can effectively classify the smearing image and identify the star. Through feature extraction and position encoding, neural networks learn the position of stars to generate semantic information and realize the end-to-end identification for the smearing star image. The algorithm can also solve the problem of low identification rate due to smearing of long exposure time for images. A dataset of dynamic stars is analyzed and constructed based on multiple angular velocities. Experiment results show that, compared with representative algorithms, the identification rate of the proposed algorithm is improved at high angular velocities. When the three-axis angular velocity is 10°/s, the rate is still 60.4%. At the same time, the proposed algorithm has good robustness to position noise and magnitude noise.

Explaining feature detection Mechanisms: A Survey

2021 ◽  
pp. 51-64
Author(s):  
Ahmed A. Elngar ◽  
◽  
◽  
◽  
◽  
...  
Keyword(s):  
Feature Detection ◽  
Feature Matching ◽  
Image Features ◽  
Mathematical Concepts ◽  
Detection Algorithms ◽  
Feature Detectors ◽  
Essential Components ◽  
Basic Notation ◽  
Computer Vision Applications ◽  
Detection Mechanisms

Feature detection, description and matching are essential components of various computer vision applications; thus, they have received a considerable attention in the last decades. Several feature detectors and descriptors have been proposed in the literature with a variety of definitions for what kind of points in an image is potentially interesting (i.e., a distinctive attribute). This chapter introduces basic notation and mathematical concepts for detecting and describing image features. Then, it discusses properties of perfect features and gives an overview of various existing detection and description methods. Furthermore, it explains some approaches to feature matching. Finally, the chapter discusses the most used techniques for performance evaluation of detection algorithms.

Identification of Multiple Fault Parameters in a Rigid-Rotor and Flexible-Bearing-Coupling System: An Experimental Investigation

2013 ◽  
Author(s):  
Mohit Lal ◽  
Rajiv Tiwari
Keyword(s):  
Economic Losses ◽  
Identification Algorithm ◽  
Rigid Rotor ◽  
Human Beings ◽  
Multiple Fault ◽  
Rotating Machine ◽  
Estimated Parameters ◽  
Coupling System ◽  
Fault Parameters ◽  
Coupling Dynamic

Rotating machineries are very common and widely used in the modern industrial world. A breakdown of the rotating machine may result in economic losses and even worse, in the damage of human beings. So it needs accurate and reliable prediction of its dynamic characteristic. The multiple fault identification algorithm developed in [1] identifies the bearing and coupling dynamic parameters along with residual unbalances in a rigid-rotor and flexible-bearing-coupling system has been validated experimentally in the present article. An indigenously developed test rig was used for the experimentation. After estimating multiple fault parameters the accuracy of estimated parameters has been checked by checking the consistency of the estimated parameters and by performing the standard impact test. It has been observed that with more number of measurements consistencies of the estimated parameters are very good.

Sign in / Sign up

Export Citation Format

Share Document