Multi-Sensor Image Fusion for Visible and Infrared Thermal Images

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.

Face Recognition Using Principal Component Analysis, K-Means Clustering, and Convolutional Neural Network

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.

A Communication Signal Recognition Algorithm Based on Holder Coefficient Characteristics

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%.

Automated Heart Sound Classification from Unsegmented Phonocardiogram Signals Using Time Frequency Features

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%.

Wavelet-Based ECG Signal Analysis and Classification

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.

Terrain Classification for Ground Robots Based on Acoustic Features

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.

Contrast Enhancement of Color Images with Color Morphing Approach

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.

Reduction of False Positives in Head-Shoulder Detection Based on Multi-Part Color Segmentation

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.

A Spatial Hypergraph Based Semi-Supervised Band Selection Method for Hyperspectral Imagery Semantic Interpretation

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.

A Supervised Learning Data Mining Approach for Object Recognition and Classification in High Resolution Satellite Data

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.

Fuzzy Inference System Based Unhealthy Region Classification in Plant Leaf Image

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).

Analysis of Electrocardiograph (ECG) Signal for the Detection of Abnormalities Using MATLAB

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.

Road Extraction Using Stationary Wavelet Transform

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.

Topographic Arrangement of 3D Design Components on 2D Maps by Unsupervised Feature Extraction

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.

Texture Feature Extraction using Slant-Hadamard Transform

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.

Javanese Character Recognition Using Hidden Markov Model

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.

Learning User Keystroke Patterns for Authentication

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.

Interoperable CNC System for Turning Operations

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.

A Novel Approach for Protein Classification Using Fourier Transform

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.

A New Approach to Face Recognition Using Dual Dimension Reduction

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.