Abstract: In this paper, Fuzzy C-Means clustering with
Expectation Maximization-Gaussian Mixture Model based hybrid
modeling algorithm is proposed for Continuous Tamil Speech
Recognition. The speech sentences from various speakers are used
for training and testing phase and objective measures are between the
proposed and existing Continuous Speech Recognition algorithms.
From the simulated results, it is observed that the proposed algorithm
improves the recognition accuracy and F-measure up to 3% as
compared to that of the existing algorithms for the speech signal from
various speakers. In addition, it reduces the Word Error Rate, Error
Rate and Error up to 4% as compared to that of the existing
algorithms. In all aspects, the proposed hybrid modeling for Tamil
speech recognition provides the significant improvements for speechto-
text conversion in various applications.
Abstract: Mammography has been one of the most reliable
methods for early detection of breast cancer. There are different
lesions which are breast cancer characteristic such as
microcalcifications, masses, architectural distortions and bilateral
asymmetry. One of the major challenges of analysing digital
mammogram is how to extract efficient features from it for accurate
cancer classification. In this paper we proposed a hybrid feature
extraction method to detect and classify all four signs of breast
cancer. The proposed method is based on multiscale surrounding
region dependence method, Gabor filters, multi fractal analysis,
directional and morphological analysis. The extracted features are
input to self adaptive resource allocation network (SRAN) classifier
for classification. The validity of our approach is extensively
demonstrated using the two benchmark data sets Mammographic
Image Analysis Society (MIAS) and Digital Database for Screening
Mammograph (DDSM) and the results have been proved to be
progressive.
Abstract: In this paper the issue of dimensionality reduction is
investigated in finger vein recognition systems using kernel Principal
Component Analysis (KPCA). One aspect of KPCA is to find the
most appropriate kernel function on finger vein recognition as there
are several kernel functions which can be used within PCA-based
algorithms. In this paper, however, another side of PCA-based
algorithms -particularly KPCA- is investigated. The aspect of
dimension of feature vector in PCA-based algorithms is of
importance especially when it comes to the real-world applications
and usage of such algorithms. It means that a fixed dimension of
feature vector has to be set to reduce the dimension of the input and
output data and extract the features from them. Then a classifier is
performed to classify the data and make the final decision. We
analyze KPCA (Polynomial, Gaussian, and Laplacian) in details in
this paper and investigate the optimal feature extraction dimension in
finger vein recognition using KPCA.
Abstract: Advances in the field of image processing envision a
new era of evaluation techniques and application of procedures in
various different fields. One such field being considered is the
biomedical field for prognosis as well as diagnosis of diseases. This
plethora of methods though provides a wide range of options to select
from, it also proves confusion in selecting the apt process and also in
finding which one is more suitable. Our objective is to use a series of
techniques on bone scans, so as to detect the occurrence of
rheumatoid arthritis (RA) as accurately as possible. Amongst other
techniques existing in the field our proposed system tends to be more
effective as it depends on new methodologies that have been proved
to be better and more consistent than others. Computer aided
diagnosis will provide more accurate and infallible rate of
consistency that will help to improve the efficiency of the system.
The image first undergoes histogram smoothing and specification,
morphing operation, boundary detection by edge following algorithm
and finally image subtraction to determine the presence of
rheumatoid arthritis in a more efficient and effective way. Using preprocessing
noises are removed from images and using segmentation,
region of interest is found and Histogram smoothing is applied for a
specific portion of the images. Gray level co-occurrence matrix
(GLCM) features like Mean, Median, Energy, Correlation, Bone
Mineral Density (BMD) and etc. After finding all the features it
stores in the database. This dataset is trained with inflamed and noninflamed
values and with the help of neural network all the new
images are checked properly for their status and Rough set is
implemented for further reduction.
Abstract: Analysis of vocal fold vibration is essential for understanding the mechanism of voice production and for improving clinical assessment of voice disorders. This paper presents a Dynamic Time Warping (DTW) based approach to analyze and objectively classify vocal fold vibration patterns. The proposed technique was designed and implemented on a Glottal Area Waveform (GAW) extracted from high-speed laryngeal images by delineating the glottal edges for each image frame. Feature extraction from the GAW was performed using Linear Predictive Coding (LPC). Several types of voice reference templates from simulations of clear, breathy, fry, pressed and hyperfunctional voice productions were used. The patterns of the reference templates were first verified using the analytical signal generated through Hilbert transformation of the GAW. Samples from normal speakers’ voice recordings were then used to evaluate and test the effectiveness of this approach. The classification of the voice patterns using the technique of LPC and DTW gave the accuracy of 81%.
Abstract: Two multisensor system architectures for navigation
and guidance of small Unmanned Aircraft (UA) are presented and
compared. The main objective of our research is to design a compact,
light and relatively inexpensive system capable of providing the
required navigation performance in all phases of flight of small UA,
with a special focus on precision approach and landing, where Vision
Based Navigation (VBN) techniques can be fully exploited in a
multisensor integrated architecture. Various existing techniques for
VBN are compared and the Appearance-Based Navigation (ABN)
approach is selected for implementation. Feature extraction and
optical flow techniques are employed to estimate flight parameters
such as roll angle, pitch angle, deviation from the runway centreline
and body rates. Additionally, we address the possible synergies of
VBN, Global Navigation Satellite System (GNSS) and MEMS-IMU
(Micro-Electromechanical System Inertial Measurement Unit)
sensors, and the use of Aircraft Dynamics Model (ADM) to provide
additional information suitable to compensate for the shortcomings of
VBN and MEMS-IMU sensors in high-dynamics attitude
determination tasks. An Extended Kalman Filter (EKF) is developed
to fuse the information provided by the different sensors and to
provide estimates of position, velocity and attitude of the UA
platform in real-time. The key mathematical models describing the
two architectures i.e., VBN-IMU-GNSS (VIG) system and VIGADM
(VIGA) system are introduced. The first architecture uses VBN
and GNSS to augment the MEMS-IMU. The second mode also
includes the ADM to provide augmentation of the attitude channel.
Simulation of these two modes is carried out and the performances of
the two schemes are compared in a small UA integration scheme (i.e.,
AEROSONDE UA platform) exploring a representative cross-section
of this UA operational flight envelope, including high dynamics
manoeuvres and CAT-I to CAT-III precision approach tasks.
Simulation of the first system architecture (i.e., VIG system) shows
that the integrated system can reach position, velocity and attitude
accuracies compatible with the Required Navigation Performance
(RNP) requirements. Simulation of the VIGA system also shows
promising results since the achieved attitude accuracy is higher using
the VBN-IMU-ADM than using VBN-IMU only. A comparison of
VIG and VIGA system is also performed and it shows that the
position and attitude accuracy of the proposed VIG and VIGA
systems are both compatible with the RNP specified in the various
UA flight phases, including precision approach down to CAT-II.
Abstract: Mosaic refers to a technique that makes image by gathering lots of small materials in various colors. This paper presents an automatic algorithm that makes the photo-mosaic image using photos. The algorithm is composed of 4 steps: partition and feature extraction, block matching, redundancy removal and color adjustment. The input image is partitioned in the small block to extract feature. Each block is matched to find similar photo in database by comparing similarity with Euclidean difference between blocks. The intensity of the block is adjusted to enhance the similarity of image by replacing the value of light and darkness with that of relevant block. Further, the quality of image is improved by minimizing the redundancy of tiles in the adjacent blocks. Experimental results support that the proposed algorithm is excellent in quantitative analysis and qualitative analysis.
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: The yield management system is very important to produce high-quality semiconductor chips in the semiconductor manufacturing process. In order to improve quality of semiconductors, various tests are conducted in the post fabrication (FAB) process. During the test process, large amount of data are collected and the data includes a lot of information about defect. In general, the defect on the wafer is the main causes of yield loss. Therefore, analyzing the defect data is necessary to improve performance of yield prediction. The wafer bin map (WBM) is one of the data collected in the test process and includes defect information such as the fail bit patterns. The fail bit has characteristics of spatial point patterns. Therefore, this paper proposes the feature extraction method using the spatial point pattern analysis. Actual data obtained from the semiconductor process is used for experiments and the experimental result shows that the proposed method is more accurately recognize the fail bit patterns.
Abstract: Depending on the big data analysis becomes important, yield prediction using data from the semiconductor process is essential. In general, yield prediction and analysis of the causes of the failure are closely related. The purpose of this study is to analyze pattern affects the final test results using a die map based clustering. Many researches have been conducted using die data from the semiconductor test process. However, analysis has limitation as the test data is less directly related to the final test results. Therefore, this study proposes a framework for analysis through clustering using more detailed data than existing die data. This study consists of three phases. In the first phase, die map is created through fail bit data in each sub-area of die. In the second phase, clustering using map data is performed. And the third stage is to find patterns that affect final test result. Finally, the proposed three steps are applied to actual industrial data and experimental results showed the potential field application.
Abstract: BCI (Brain Computer Interface) is a communication machine that translates brain massages to computer commands. These machines with the help of computer programs can recognize the tasks that are imagined. Feature extraction is an important stage of the process in EEG classification that can effect in accuracy and the computation time of processing the signals. In this study we process the signal in three steps of active segment selection, fractal feature extraction, and classification. One of the great challenges in BCI applications is to improve classification accuracy and computation time together. In this paper, we have used student’s 2D sample t-statistics on continuous wavelet transforms for active segment selection to reduce the computation time. In the next level, the features are extracted from some famous fractal dimension estimation of the signal. These fractal features are Katz and Higuchi. In the classification stage we used ANFIS (Adaptive Neuro-Fuzzy Inference System) classifier, FKNN (Fuzzy K-Nearest Neighbors), LDA (Linear Discriminate Analysis), and SVM (Support Vector Machines). We resulted that active segment selection method would reduce the computation time and Fractal dimension features with ANFIS analysis on selected active segments is the best among investigated methods in EEG classification.
Abstract: An automatic moment-based texture segmentation approach is proposed in this paper. First, we describe the related work in this computer vision domain. Our texture feature extraction, the first part of the texture recognition process, produces a set of moment-based feature vectors. For each image pixel, a texture feature vector is computed as a sequence of area moments. Then, an automatic pixel classification approach is proposed. The feature vectors are clustered using an unsupervised classification algorithm, the optimal number of clusters being determined using a measure based on validation indexes. From the resulted pixel classes one determines easily the desired texture regions of the image.
Abstract: Feature extraction plays an important role in many remote sensing applications. Automatic extraction of water bodies is of great significance in many remote sensing applications like change detection, image retrieval etc. This paper presents a procedure for automatic extraction of water information from remote sensing images. The algorithm uses the relative location of R color component of the chromaticity diagram. This method is then integrated with the effectiveness of the spatial scale transformation of whole method. The whole method is based on water index fitted from spectral library. Experimental results demonstrate the improved accuracy and effectiveness of the integrated method for automatic extraction of water bodies.
Abstract: The exponential increase in the volume of medical image database has imposed new challenges to clinical routine in maintaining patient history, diagnosis, treatment and monitoring. With the advent of data mining and machine learning techniques it is possible to automate and/or assist physicians in clinical diagnosis. In this research a medical image classification framework using data mining techniques is proposed. It involves feature extraction, feature selection, feature discretization and classification. In the classification phase, the performance of the traditional kNN k nearest neighbor classifier is improved using a feature weighting scheme and a distance weighted voting instead of simple majority voting. Feature weights are calculated using the interestingness measures used in association rule mining. Experiments on the retinal fundus images show that the proposed framework improves the classification accuracy of traditional kNN from 78.57 % to 92.85 %.
Abstract: Image registration is the process of establishing point
by point correspondence between images obtained from a same
scene. This process is very useful in remote sensing, medicine,
cartography, computer vision, etc. Then, the task of registration is to
place the data into a common reference frame by estimating the
transformations between the data sets. In this work, we develop a
rigid point registration method based on the application of genetic
algorithms and Hausdorff distance. First, we extract the feature points
from both images based on the algorithm of global and local
curvature corner. After refining the feature points, we use Hausdorff
distance as similarity measure between the two data sets and for
optimizing the search space we use genetic algorithms to achieve
high computation speed for its inertial parallel. The results show the
efficiency of this method for registration of satellite images.
Abstract: This paper presents an algorithm based on the
wavelet decomposition, for feature extraction from the ECG signal
and recognition of three types of Ventricular Arrhythmias using
neural networks. A set of Discrete Wavelet Transform (DWT)
coefficients, which contain the maximum information about the
arrhythmias, is selected from the wavelet decomposition. After that a
novel clustering algorithm based on nature inspired algorithm (Ant
Colony Optimization) is developed for classifying arrhythmia types.
The algorithm is applied on the ECG registrations from the MIT-BIH
arrhythmia and malignant ventricular arrhythmia databases. We
applied Daubechies 4 wavelet in our algorithm. The wavelet
decomposition enabled us to perform the task efficiently and
produced reliable results.
Abstract: Recognition of Indian languages scripts is challenging problems. In Optical Character Recognition [OCR], a character or symbol to be recognized can be machine printed or handwritten characters/numerals. There are several approaches that deal with problem of recognition of numerals/character depending on the type of feature extracted and different way of extracting them. This paper proposes a recognition scheme for handwritten Hindi (devnagiri) numerals; most admired one in Indian subcontinent. Our work focused on a technique in feature extraction i.e. global based approach using end-points information, which is extracted from images of isolated numerals. These feature vectors are fed to neuro-memetic model [18] that has been trained to recognize a Hindi numeral. The archetype of system has been tested on varieties of image of numerals. . In proposed scheme data sets are fed to neuro-memetic algorithm, which identifies the rule with highest fitness value of nearly 100 % & template associates with this rule is nothing but identified numerals. Experimentation result shows that recognition rate is 92-97 % compared to other models.
Abstract: An early and accurate detection of Alzheimer's disease (AD) is an important stage in the treatment of individuals suffering from AD. We present an approach based on the use of structural magnetic resonance imaging (sMRI) phase images to distinguish between normal controls (NC), mild cognitive impairment (MCI) and AD patients with clinical dementia rating (CDR) of 1. Independent component analysis (ICA) technique is used for extracting useful features which form the inputs to the support vector machines (SVM), K nearest neighbour (kNN) and multilayer artificial neural network (ANN) classifiers to discriminate between the three classes. The obtained results are encouraging in terms of classification accuracy and effectively ascertain the usefulness of phase images for the classification of different stages of Alzheimer-s disease.
Abstract: In this paper a Pattern Recognition algorithm based on
a constrained version of the k-means clustering algorithm will be
presented. The proposed algorithm is a non parametric supervised
statistical pattern recognition algorithm, i.e. it works under very mild
assumptions on the dataset. The performance of the algorithm will
be tested, togheter with a feature extraction technique that captures
the information on the closed two-dimensional contour of an image,
on images of industrial mineral ores.
Abstract: A new approach is adopted in this paper based
on Turk and Pentland-s eigenface method. It was found that the
probability density function of the distance between the projection
vector of the input face image and the average projection vector of
the subject in the face database, follows Rayleigh distribution. In
order to decrease the false acceptance rate and increase the
recognition rate, the input face image has been recognized using two
thresholds including the acceptance threshold and the rejection
threshold. We also find out that the value of two thresholds will be
close to each other as number of trials increases. During the training,
in order to reduce the number of trials, the projection vectors for each
subject has been averaged. The recognition experiments using the
proposed algorithm show that the recognition rate achieves to
92.875% whilst the average number of judgment is only 2.56 times.