Abstract: This paper is motivated by the importance of multi-sensor image fusion with specific focus on Infrared (IR) and Visible image (VI) fusion for various applications including military reconnaissance. Image fusion can be defined as the process of combining two or more source images into a single composite image with extended information content that improves visual perception or feature extraction. These images can be from different modalities like Visible camera & IR Thermal Imager. While visible images are captured by reflected radiations in the visible spectrum, the thermal images are formed from thermal radiation (IR) that may be reflected or self-emitted. A digital color camera captures the visible source image and a thermal IR camera acquires the thermal source image. In this paper, some image fusion algorithms based upon Multi-Scale Transform (MST) and region-based selection rule with consistency verification have been proposed and presented. This research includes implementation of the proposed image fusion algorithm in MATLAB along with a comparative analysis to decide the optimum number of levels for MST and the coefficient fusion rule. The results are presented, and several commonly used evaluation metrics are used to assess the suggested method's validity. Experiments show that the proposed approach is capable of producing good fusion results. While deploying our image fusion algorithm approaches, we observe several challenges from the popular image fusion methods. While high computational cost and complex processing steps of image fusion algorithms provide accurate fused results, but they also make it hard to become deployed in system and applications that require real-time operation, high flexibility and low computation ability. So, the methods presented in this paper offer good results with minimum time complexity.
Abstract: Face recognition is the problem of identifying or recognizing individuals in an image. This paper investigates a possible method to bring a solution to this problem. The method proposes an amalgamation of Principal Component Analysis (PCA), K-Means clustering, and Convolutional Neural Network (CNN) for a face recognition system. It is trained and evaluated using the ORL dataset. This dataset consists of 400 different faces with 40 classes of 10 face images per class. Firstly, PCA enabled the usage of a smaller network. This reduces the training time of the CNN. Thus, we get rid of the redundancy and preserve the variance with a smaller number of coefficients. Secondly, the K-Means clustering model is trained using the compressed PCA obtained data which select the K-Means clustering centers with better characteristics. Lastly, the K-Means characteristics or features are an initial value of the CNN and act as input data. The accuracy and the performance of the proposed method were tested in comparison to other Face Recognition (FR) techniques namely PCA, Support Vector Machine (SVM), as well as K-Nearest Neighbour (kNN). During experimentation, the accuracy and the performance of our suggested method after 90 epochs achieved the highest performance: 99% accuracy F1-Score, 99% precision, and 99% recall in 463.934 seconds. It outperformed the PCA that obtained 97% and KNN with 84% during the conducted experiments. Therefore, this method proved to be efficient in identifying faces in the images.
Abstract: Communication signal modulation recognition
technology is one of the key technologies in the field of modern
information warfare. At present, communication signal automatic
modulation recognition methods are mainly divided into two major
categories. One is the maximum likelihood hypothesis testing method
based on decision theory, the other is a statistical pattern recognition
method based on feature extraction. Now, the most commonly used
is a statistical pattern recognition method, which includes feature
extraction and classifier design. With the increasingly complex
electromagnetic environment of communications, how to effectively
extract the features of various signals at low signal-to-noise ratio
(SNR) is a hot topic for scholars in various countries. To solve this
problem, this paper proposes a feature extraction algorithm for the
communication signal based on the improved Holder cloud feature.
And the extreme learning machine (ELM) is used which aims at
the problem of the real-time in the modern warfare to classify
the extracted features. The algorithm extracts the digital features
of the improved cloud model without deterministic information in
a low SNR environment, and uses the improved cloud model to
obtain more stable Holder cloud features and the performance of the
algorithm is improved. This algorithm addresses the problem that
a simple feature extraction algorithm based on Holder coefficient
feature is difficult to recognize at low SNR, and it also has a
better recognition accuracy. The results of simulations show that the
approach in this paper still has a good classification result at low
SNR, even when the SNR is -15dB, the recognition accuracy still
reaches 76%.
Abstract: Cardiologists perform cardiac auscultation to detect
abnormalities in heart sounds. Since accurate auscultation is
a crucial first step in screening patients with heart diseases,
there is a need to develop computer-aided detection/diagnosis
(CAD) systems to assist cardiologists in interpreting heart sounds
and provide second opinions. In this paper different algorithms
are implemented for automated heart sound classification using
unsegmented phonocardiogram (PCG) signals. Support vector
machine (SVM), artificial neural network (ANN) and cartesian
genetic programming evolved artificial neural network (CGPANN)
without the application of any segmentation algorithm has been
explored in this study. The signals are first pre-processed to remove
any unwanted frequencies. Both time and frequency domain features
are then extracted for training the different models. The different
algorithms are tested in multiple scenarios and their strengths and
weaknesses are discussed. Results indicate that SVM outperforms
the rest with an accuracy of 73.64%.
Abstract: This paper presents the processing and analysis of ECG signals. The study is based on wavelet transform and uses exclusively the MATLAB environment. This study includes removing Baseline wander and further de-noising through wavelet transform and metrics such as signal-to noise ratio (SNR), Peak signal-to-noise ratio (PSNR) and the mean squared error (MSE) are used to assess the efficiency of the de-noising techniques. Feature extraction is subsequently performed whereby signal features such as heart rate, rise and fall levels are extracted and the QRS complex was detected which helped in classifying the ECG signal. The classification is the last step in the analysis of the ECG signals and it is shown that these are successfully classified as Normal rhythm or Abnormal rhythm. The final result proved the adequacy of using wavelet transform for the analysis of ECG signals.
Abstract: The motivation of our work is to detect different
terrain types traversed by a robot based on acoustic data from the
robot-terrain interaction. Different acoustic features and classifiers
were investigated, such as Mel-frequency cepstral coefficient and
Gamma-tone frequency cepstral coefficient for the feature extraction,
and Gaussian mixture model and Feed forward neural network for the
classification. We analyze the system’s performance by comparing
our proposed techniques with some other features surveyed from
distinct related works. We achieve precision and recall values between
87% and 100% per class, and an average accuracy at 95.2%. We also
study the effect of varying audio chunk size in the application phase
of the models and find only a mild impact on performance.
Abstract: Low contrast images can result from the wrong setting of image acquisition or poor illumination conditions. Such images may not be visually appealing and can be difficult for feature extraction. Contrast enhancement of color images can be useful in medical area for visual inspection. In this paper, a new technique is proposed to improve the contrast of color images. The RGB (red, green, blue) color image is transformed into normalized RGB color space. Adaptive histogram equalization technique is applied to each of the three channels of normalized RGB color space. The corresponding channels in the original image (low contrast) and that of contrast enhanced image with adaptive histogram equalization (AHE) are morphed together in proper proportions. The proposed technique is tested on seventy color images of acne patients. The results of the proposed technique are analyzed using cumulative variance and contrast improvement factor measures. The results are also compared with decorrelation stretch. Both subjective and quantitative analysis demonstrates that the proposed techniques outperform the other techniques.
Abstract: The paper presents a method that utilizes figure-ground color segmentation to extract effective global feature in terms of false positive reduction in the head-shoulder detection. Conventional detectors that rely on local features such as HOG due to real-time operation suffer from false positives. Color cue in an input image provides salient information on a global characteristic which is necessary to alleviate the false positives of the local feature based detectors. An effective approach that uses figure-ground color segmentation has been presented in an effort to reduce the false positives in object detection. In this paper, an extended version of the approach is presented that adopts separate multipart foregrounds instead of a single prior foreground and performs the figure-ground color segmentation with each of the foregrounds. The multipart foregrounds include the parts of the head-shoulder shape and additional auxiliary foregrounds being optimized by a search algorithm. A classifier is constructed with the feature that consists of a set of the multiple resulting segmentations. Experimental results show that the presented method can discriminate more false positive than the single prior shape-based classifier as well as detectors with the local features. The improvement is possible because the presented approach can reduce the false positives that have the same colors in the head and shoulder foregrounds.
Abstract: Hyperspectral imagery (HSI) typically provides a
wealth of information captured in a wide range of the
electromagnetic spectrum for each pixel in the image. Hence, a
pixel in HSI is a high-dimensional vector of intensities with a
large spectral range and a high spectral resolution. Therefore, the
semantic interpretation is a challenging task of HSI analysis. We
focused in this paper on object classification as HSI semantic
interpretation. However, HSI classification still faces some issues,
among which are the following: The spatial variability of spectral
signatures, the high number of spectral bands, and the high cost
of true sample labeling. Therefore, the high number of spectral
bands and the low number of training samples pose the problem of
the curse of dimensionality. In order to resolve this problem, we
propose to introduce the process of dimensionality reduction trying
to improve the classification of HSI. The presented approach is a
semi-supervised band selection method based on spatial hypergraph
embedding model to represent higher order relationships with
different weights of the spatial neighbors corresponding to the
centroid of pixel. This semi-supervised band selection has been
developed to select useful bands for object classification. The
presented approach is evaluated on AVIRIS and ROSIS HSIs
and compared to other dimensionality reduction methods. The
experimental results demonstrate the efficacy of our approach
compared to many existing dimensionality reduction methods for
HSI classification.
Abstract: Advances in spatial and spectral resolution of satellite
images have led to tremendous growth in large image databases. The
data we acquire through satellites, radars, and sensors consists of
important geographical information that can be used for remote
sensing applications such as region planning, disaster management.
Spatial data classification and object recognition are important tasks
for many applications. However, classifying objects and identifying
them manually from images is a difficult task. Object recognition is
often considered as a classification problem, this task can be
performed using machine-learning techniques. Despite of many
machine-learning algorithms, the classification is done using
supervised classifiers such as Support Vector Machines (SVM) as the
area of interest is known. We proposed a classification method,
which considers neighboring pixels in a region for feature extraction
and it evaluates classifications precisely according to neighboring
classes for semantic interpretation of region of interest (ROI). A
dataset has been created for training and testing purpose; we
generated the attributes by considering pixel intensity values and
mean values of reflectance. We demonstrated the benefits of using
knowledge discovery and data-mining techniques, which can be on
image data for accurate information extraction and classification from
high spatial resolution remote sensing imagery.
Abstract: In addition to environmental parameters like rain,
temperature diseases on crop is a major factor which affects
production quality & quantity of crop yield. Hence disease
management is a key issue in agriculture. For the management of
disease, it needs to be detected at early stage. So, treat it properly &
control spread of the disease. Now a day, it is possible to use the
images of diseased leaf to detect the type of disease by using image
processing techniques. This can be achieved by extracting features
from the images which can be further used with classification
algorithms or content based image retrieval systems. In this paper,
color image is used to extract the features such as mean and standard
deviation after the process of region cropping. The selected features
are taken from the cropped image with different image size samples.
Then, the extracted features are taken in to the account for
classification using Fuzzy Inference System (FIS).
Abstract: The proposed method is to study and analyze Electrocardiograph (ECG) waveform to detect abnormalities present with reference to P, Q, R and S peaks. The first phase includes the acquisition of real time ECG data. In the next phase, generation of signals followed by pre-processing. Thirdly, the procured ECG signal is subjected to feature extraction. The extracted features detect abnormal peaks present in the waveform Thus the normal and abnormal ECG signal could be differentiated based on the features extracted. The work is implemented in the most familiar multipurpose tool, MATLAB. This software efficiently uses algorithms and techniques for detection of any abnormalities present in the ECG signal. Proper utilization of MATLAB functions (both built-in and user defined) can lead us to work with ECG signals for processing and analysis in real time applications. The simulation would help in improving the accuracy and the hardware could be built conveniently.
Abstract: In this paper, a novel road extraction method using Stationary Wavelet Transform is proposed. To detect road features from color aerial satellite imagery, Mexican hat Wavelet filters are used by applying the Stationary Wavelet Transform in a multiresolution, multi-scale, sense and forming the products of Wavelet coefficients at a different scales to locate and identify road features at a few scales. In addition, the shifting of road features locations is considered through multiple scales for robust road extraction in the asymmetry road feature profiles. From the experimental results, the proposed method leads to a useful technique to form the basis of road feature extraction. Also, the method is general and can be applied to other features in imagery.
Abstract: As a result of the daily workflow in the design
development departments of companies, databases containing huge
numbers of 3D geometric models are generated. According to the
given problem engineers create CAD drawings based on their design
ideas and evaluate the performance of the resulting design, e.g. by
computational simulations. Usually, new geometries are built either
by utilizing and modifying sets of existing components or by adding
single newly designed parts to a more complex design.
The present paper addresses the two facets of acquiring
components from large design databases automatically and providing
a reasonable overview of the parts to the engineer. A unified
framework based on the topographic non-negative matrix
factorization (TNMF) is proposed which solves both aspects
simultaneously. First, on a given database meaningful components
are extracted into a parts-based representation in an unsupervised
manner. Second, the extracted components are organized and
visualized on square-lattice 2D maps. It is shown on the example of
turbine-like geometries that these maps efficiently provide a wellstructured
overview on the database content and, at the same time,
define a measure for spatial similarity allowing an easy access and
reuse of components in the process of design development.
Abstract: Random and natural textures classification is still
one of the biggest challenges in the field of image processing and
pattern recognition. In this paper, texture feature extraction using
Slant Hadamard Transform was studied and compared to other
signal processing-based texture classification schemes. A
parametric SHT was also introduced and employed for natural
textures feature extraction. We showed that a subtly modified
parametric SHT can outperform ordinary Walsh-Hadamard
transform and discrete cosine transform. Experiments were carried
out on a subset of Vistex random natural texture images using a
kNN classifier.
Abstract: Hidden Markov Model (HMM) is a stochastic method
which has been used in various signal processing and character
recognition. This study proposes to use HMM to recognize Javanese
characters from a number of different handwritings, whereby HMM
is used to optimize the number of state and feature extraction. An
85.7 % accuracy is obtained as the best result in 16-stated vertical
model using pure HMM. This initial result is satisfactory for
prompting further research.
Abstract: Keystroke authentication is a new access control system
to identify legitimate users via their typing behavior. In this paper,
machine learning techniques are adapted for keystroke authentication.
Seven learning methods are used to build models to differentiate user
keystroke patterns. The selected classification methods are Decision
Tree, Naive Bayesian, Instance Based Learning, Decision Table, One
Rule, Random Tree and K-star. Among these methods, three of them
are studied in more details. The results show that machine learning
is a feasible alternative for keystroke authentication. Compared to
the conventional Nearest Neighbour method in the recent research,
learning methods especially Decision Tree can be more accurate. In
addition, the experiment results reveal that 3-Grams is more accurate
than 2-Grams and 4-Grams for feature extraction. Also, combination
of attributes tend to result higher accuracy.
Abstract: The changing economic climate has made global
manufacturing a growing reality over the last decade, forcing
companies from east and west and all over the world to
collaborate beyond geographic boundaries in the design,
manufacture and assemble of products. The ISO10303 and
ISO14649 Standards (STEP and STEP-NC) have been
developed to introduce interoperability into manufacturing
enterprises so as to meet the challenge of responding to
production on demand. This paper describes and illustrates a
STEP compliant CAD/CAPP/CAM System for the manufacture
of rotational parts on CNC turning centers. The information
models to support the proposed system together with the data
models defined in the ISO14649 standard used to create the NC
programs are also described. A structured view of a STEP
compliant CAD/CAPP/CAM system framework supporting the
next generation of intelligent CNC controllers for turn/mill
component manufacture is provided. Finally a proposed
computational environment for a STEP-NC compliant system
for turning operations (SCSTO) is described. SCSTO is the
experimental part of the research supported by the specification
of information models and constructed using a structured
methodology and object-oriented methods. SCSTO was
developed to generate a Part 21 file based on machining
features to support the interactive generation of process plans
utilizing feature extraction. A case study component has been
developed to prove the concept for using the milling and turning
parts of ISO14649 to provide a turn-mill CAD/CAPP/CAM
environment.
Abstract: Discovering new biological knowledge from the highthroughput biological data is a major challenge to bioinformatics today. To address this challenge, we developed a new approach for protein classification. Proteins that are evolutionarily- and thereby functionally- related are said to belong to the same classification. Identifying protein classification is of fundamental importance to document the diversity of the known protein universe. It also provides a means to determine the functional roles of newly discovered protein sequences. Our goal is to predict the functional classification of novel protein sequences based on a set of features extracted from each protein sequence. The proposed technique used datasets extracted from the Structural Classification of Proteins (SCOP) database. A set of spectral domain features based on Fast Fourier Transform (FFT) is used. The proposed classifier uses multilayer back propagation (MLBP) neural network for protein classification. The maximum classification accuracy is about 91% when applying the classifier to the full four levels of the SCOP database. However, it reaches a maximum of 96% when limiting the classification to the family level. The classification results reveal that spectral domain contains information that can be used for classification with high accuracy. In addition, the results emphasize that sequence similarity measures are of great importance especially at the family level.
Abstract: In this paper a new approach to face recognition is
presented that achieves double dimension reduction, making the
system computationally efficient with better recognition results and
out perform common DCT technique of face recognition. In pattern
recognition techniques, discriminative information of image
increases with increase in resolution to a certain extent, consequently
face recognition results change with change in face image resolution
and provide optimal results when arriving at a certain resolution
level. In the proposed model of face recognition, initially image
decimation algorithm is applied on face image for dimension
reduction to a certain resolution level which provides best
recognition results. Due to increased computational speed and feature
extraction potential of Discrete Cosine Transform (DCT), it is
applied on face image. A subset of coefficients of DCT from low to
mid frequencies that represent the face adequately and provides best
recognition results is retained. A tradeoff between decimation factor,
number of DCT coefficients retained and recognition rate with
minimum computation is obtained. Preprocessing of the image is
carried out to increase its robustness against variations in poses and
illumination level. This new model has been tested on different
databases which include ORL , Yale and EME color database.