scholarly journals Colour Texture Analysis of Face Spoof Detection using CNN Classifier

2019 ◽  
Vol 9 (1) ◽  
pp. 5037-5046
Keyword(s):  
Neural Network ◽  
Texture Analysis ◽  
Video Processing ◽  
Data Bases ◽  
Face Images ◽  
Image And Video Processing ◽  
Stable Performance ◽  
And Training ◽  
Face Spoofing

The emphasis on analysis of various research schemes of non – intrusive software based face spoofing detection is now a days gaining reputation in image and video processing tools. The analysis on luminance(Y)data of the various face images which provides the discrimination of forged faces from genuine faces by removing the chroma component. Here the work provides an innovative approach that perceives spoofed face using texture analysis (colour)by exploiting combined colour texture information from various channels such as luminance and chrominance. This helps to exploit joint information by removing degraded feature metaphors from dissimilar colour models.Precisely the featured histograms are figured over all images that obtained from the YCrCb colour model band distinctly.The concatenation of testing and training by using Neural Network for classification of spoofed images by the concept of blending of images gives the best possible outcomes. Wide-ranging researches on face data bases is most interesting target datasets paves the way for best processing face spoofing results than state of art. The proposed method gives stable performance when compared with the most unlike methods that conferred in the literature survey. The promising outcomes of evaluation suggests that facial colour texture depiction is added steady strange conditions associated to gray-scale complements.The favourableoutcomeswereattained using these CNN(Convolution Neural Network)designs for face antispoofing in diversesituations.

A Similarity-Based Object Classification Using Deep Neural Networks

2019 ◽  
pp. 197-219
Author(s):  
Parvathi R. ◽  
Pattabiraman V.
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Search Algorithm ◽  
Random Projection ◽  
Learning Networks ◽  
Learning Models ◽  
External Conditions ◽  
And Training

This chapter proposes a hybrid method for classification of the objects based on deep neural network and a similarity-based search algorithm. The objects are pre-processed with external conditions. After pre-processing and training different deep learning networks with the object dataset, the authors compare the results to find the best model to improve the accuracy of the results based on the features of object images extracted from the feature vector layer of a neural network. RPFOREST (random projection forest) model is used to predict the approximate nearest images. ResNet50, InceptionV3, InceptionV4, and DenseNet169 models are trained with this dataset. A proposal for adaptive finetuning of the deep learning models by determining the number of layers required for finetuning with the help of the RPForest model is given, and this experiment is conducted using the Xception model.

scholarly journals NEURAL NETWORK CLASSIFICATION METHOD FOR AIRCRAFT IN ISAR IMAGES

2019 ◽  
Vol 2 ◽  
pp. 141
Author(s):  
Krasimir Ognyanov Slavyanov
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Synthetic Aperture ◽  
Neural Network Architecture ◽  
The Neural Network ◽  
Full Explanation ◽  
Network Method ◽  
High Level ◽  
And Training

This article offers a neural network method for automatic classification of Inverse Synthetic Aperture Radar objects represented in images with high level of post-receive optimization. A full explanation of the procedures of two-layer neural network architecture creating and training is described. The classification in the recognition stage is proposed, based on several main classes or sets of flying objects. The classification sets are designed according to distinctive specifications in the structural models of the aircrafts. The neural network is experimentally simulated in MATLAB environment. Numerical results of the experiments carried, prove the correct classification of the objects in ISAR optimized images.

scholarly journals Classification of surface water objects in visible spectrum images

2020 ◽  
pp. 87-95
Author(s):  
A. A. Artemyev ◽  
E. A. Kazachkov ◽  
S. N. Matyugin ◽  
V. V. Sharonov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Surface Water ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Visible Spectrum ◽  
Training Dataset ◽  
And Training ◽  
Selection Of

This paper considers the problem of classifying surface water objects, e.g. ships of different classes, in visible spectrum images using convolutional neural networks. A technique for forming a database of images of surface water objects and a special training dataset for creating a classification are presented. A method for forming and training of a convolutional neural network is described. The dependence of the probability of correct recognition on the number and variants of the selection of specific classes of surface water objects is analysed. The results of recognizing different sets of classes are presented.

METHOD FOR CONTROL OF TECHNICAL STATE OF ONBOARD RADIOELECTRONIC EQUIPMENT OF SPACECRAFTS BASED ON INTERACTION OF ELEMENTS OF DISTRIBUTED TECHNICAL DIAGNOSIS SYSTEM

2021 ◽  
pp. 44-50
Author(s):  
A. I. Loskutov ◽  
A. V. Stolyarov ◽  
E. A. Ryahova
Keyword(s):  
Neural Network ◽  
Mathematical Formulation ◽  
Technical State ◽  
Technical Diagnostics ◽  
Neural Network Classification ◽  
Interesting Approach ◽  
Diagnostics System ◽  
And Training ◽  
Practical Recommendations

The article deals with the issues of technical diagnostics of on-board radioelectronic equipment of spacecrafts. A mathematical formulation of the problem is carried out in order to minimize the time of technical diagnostics. A method has been developed for monitoring the technical state of onboard radioelectronic equipment based on the interaction of elements of a distributed technical diagnostics system, which includes identification of onboard radioelectronic equipment and training a neural network, searching for the location and causes of a malfunction using a mathematical model and making decisions by controlling the onboard radioelectronic equipment of spacecrafts. When searching for the location and causes of a malfunction, an interesting approach is based on a neural network classification of malfunctions. Practical recommendations for technical diagnostics of onboard radioelectronic equipment of spacecrafts are presented, in particular, a scheme for constructing a promising onboard distributed system of technical diagnostics when interacting with onboard systems of a typical spacecraft.

scholarly journals Audio, Image, Video, and Weather Datasets for Continuous Electronic Beehive Monitoring

2021 ◽  
Vol 11 (10) ◽  
pp. 4632
Author(s):  
Vladimir Kulyukin
Keyword(s):  
Video Processing ◽  
Data Science ◽  
State Of The Art ◽  
Image And Video Processing ◽  
Performance Benchmarks ◽  
Northern Utah ◽  
Stable Performance ◽  
Processing Algorithms ◽  
Forager Traffic ◽  
Point Of Reference

In 2014, we designed and implemented BeePi, a multi-sensor electronic beehive monitoring system. Since then we have been using BeePi monitors deployed at different apiaries in northern Utah to design audio, image, and video processing algorithms to analyze forager traffic in the vicinity of Langstroth beehives. Since our first publication on BeePi in 2016, we have received multiple requests from researchers and practitioners for the datasets we have used in our research. The main objective of this article is to provide a comprehensive point of reference to the datasets that we have so far curated for our research. We hope that our datasets will provide stable performance benchmarks for continuous electronic beehive monitoring, help interested parties verify our findings and correct errors, and advance the state of the art in continuous electronic beehive monitoring and related areas of AI, machine learning, and data science.

An Intelligent Recognition Algorithm on Traffic Safety States

2013 ◽  
Vol 433-435 ◽  
pp. 1388-1391 ◽  
Author(s):  
Wei Zhi Wang ◽  
Bing Han Liu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Traffic Safety ◽  
Video Processing ◽  
High Accuracy ◽  
Recognition Algorithm ◽  
Video Images ◽  
Network Methods ◽  
Intelligent Recognition

Traffic safety states can be divided into safe and dangerous according to the attributes of video images of traffic safety states. We propose a synergic neural network recognition model based on prototype pattern by analyzing various methods on intelligent video processing. Our proposed method realizes real time classification of traffic safety states with high accuracy of traffic safety states recognition. The experimental results validate that the accuracy of classification of proposed method arrives at 87.5%, increased by 16.2% compared to traditional neural network methods.

scholarly journals Skin Disease Recognition using Texture Analysis

2021 ◽  
Vol 9 (VI) ◽  
pp. 1560-1562
Author(s):  
Prof. M. G. Panjwani
Keyword(s):  
Neural Network ◽  
Side Effects ◽  
Texture Analysis ◽  
Recognition System ◽  
Image Feature ◽  
Skin Infections ◽  
Image Feature Extraction ◽  
Long Time ◽  
Illness Recognition

Skin is the primary part of our body, One of the major issues we are facing presently days that's skin illness due to high air pollution. In this research, we are trying to skin illness recognition by using Neural Network which is based on texture analysis. There are many skin infections like Eczema, Acne, Hives, rosacea, psoriasis, etc. In common, these diseases have similarities in the design of contamination and side effects such as redness and rash. Diagnosis and recognition of skin illness take a really long time to handle. The infection determination and recognition gets to be troublesome as the complexity and number of highlights of the infection increases. Thus, a computer helped diagnosis and recognition system is presented. Computer algorithm which contains few steps that are image processing, image feature extraction, segmentation, and classification .of information has been executed with the assistance of a Convolutional neural network (CNN). The CNN can learn designs of side effects of specific infections and makes it speedier.

Sign in / Sign up

Export Citation Format

Share Document