Accepted Papers

  • Thermal Imaging Using Cnn And Knn Classifiers With Fwt, Pca And Lda Algorithms.
    Chigozie Orji1 , Evan Hurwitz2 and Ali Hasan3, 1University of Johannesburg, South Africa2University of Johannesburg, South Africa and 3University of Johannesburg, South Africa
    ABSTRACT
    This paper deals with the problem of errors in a biometric system that may arise from poor lighting and spoofing. To tackle this, images from the Terravic Facial Infrared Database have been used with Fast Wavelet Transform (FWT), an ensemble of classifiers and feature extractors, to reduce errors encountered in thermal facial recognition. By dividing the image set into a training set, comprising 1000 thermal images of 10 persons wearing glasses (X) and a test set comprising 100 image samples (y), of the same persons in glasses. A mean percentage error of 0.84% was achieved, when a Convolutional Neural Network (CNN) was used to classify the image set (y), after training with (X). However, when the images where pre-processed with Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and k-Nearest Neighbors (KNN) classifier, a mean percentage error of 0.68% was achieved with the CNN classifier.
  • Fingerprint Recognition Algorithm
    Farah Dhib Tatar, National school of the studies of engineer of Tunis, Tunisia
    ABSTRACT
    Biometrics is an emerging field where technology improves our ability to identify a person. The advantage of biometric identification is that each individual has its own physical characteristics that cannot be changed, lost or stolen. The use of fingerprinting is today one of the most reliable technologies on the market to authenticate an individual. This technology is simple to use and easy to implement. The techniques of fingerprint recognition are numerous and diversified, they are generally based on generic algorithms and tools for filtering images.This article proposes a fingerprint recognition chain based on filtering algorithms. The results are retrieved and validated using Matlab.
  • Identifying Patterns in Thought-Forms Using Histograms of the Second Derivative of Intensity Outline
    Rai Sachindra Prasad1, Shishir Prasad2 and Vikas Prasad3, 1Graphic Era University, Dehradun, India, 2Uttarakhand Ayurvedic University, Dehradun, India and 3Universitatsmedizin, Germany
    ABSTRACT
    Existence of human biofield is now universally accepted. Scientific experiments have conclusively proved that the state of mind, i.e. the thought process, is responsible for generating different characteristics of biofield. Vigorous research efforts on detection, measurement, and even two dimensional imaging of ultraweak biophotons emission from biological objects have been reported. With the rapid progress in biphotonic research world over, prospects of development of a biophotonic camera for capturing thoughts in image form appear to be a possibility. The physiological structure of human beings from the view point of Biophysicists and Theosophists has a great deal in common since both talk of cloud of biophotons emission with spectrum of several colors. A literature survey resulted in finding a large number of hand-drawn, hand-painted thought forms images in Theosophical texts published nearly hundred years ago. This provided the motivation for an investigation of the true color thought form images from theosophical literature. All images were qualified with comments of ‘Good, Bad, or both’ while discussing the nature/ behavior of individuals involved. These comments are stated to be based on three principles related to (i) color, (ii) form (shape), and (iii) outline of the images, but without furnishing scientific proof. Of these three, the aspect of color using the HSV space, and form using Radon Transform and Histograms, have been recently investigated by the authors. This paper investigates the third aspect of outline using Histograms of the second derivative of the intensity values in intensity image on MATLAB platform. Results prove that the procedure adopted identifies the patterns correctly in nearly ninety percent of a sample of thirty four images when compared with the comments. The procedure can be relied upon in identifying patterns in biofield images with similar attributes.