Digital Image Watermarking Based On Gradient Direction Quantization And Denoising Using Different Techiniques

Vol. 3  Issue 1
Year: 2016
Issue:Mar-May
Title:Digital Image Watermarking Based On Gradient Direction Quantization And Denoising Using Different Techiniques
Author Name:I. Kullayamma and Sathyanarayana
Synopsis:
Digital watermarking is the act of hiding a message related to a digital signal (i.e. an image, song, video) within the signal itself. In recent years, the phenomenal growth of the internet has highlighted the need for a mechanism to protect ownership of digital media. Digital watermarking is a solution to the problem of copyright protection and authentication of multimedia data while working in a networked environment. The authors propose a robust quantization-based image watermarking method, called the Gradient Direction Water Marking (GDWM), and based on the uniform quantization of the direction of gradient vectors. In GDWM, the watermark bits are embedded by quantizing the angles of significant gradient vectors at multiple wavelet scales. The proposed method has the following advantages: 1) Increased invisibility of the embedded watermark, 2) Robustness to amplitude scaling attacks, and 3) Increased watermarking capacity. To quantize the gradient direction, the DWT coefficients are modified based on the derived relationship between the changes in coefficients and the change in the gradient direction. In this paper, they propose fourdifferent denoising techniques for checking of the watermarking efficiency [15]. In various noise scenarios, the performance of the proposed denoised methods are compared in terms of PSNR and Correlation Coefficient. The Contourlet transform provides better PSNR when compared to other filter methods. The Correlation Coefficient observed that the Contourlet transform provides almost near to 1 which is ideal.

Image Steganalysis: Segmenting Stego Image using Watershed Method and Feature Extraction by MRF Method

Vol. 3  Issue 1
Year: 2016
Issue:Mar-May
Title:Image Steganalysis: Segmenting Stego Image using Watershed Method and Feature Extraction by MRF Method
Author Name:B. Yamini and R. Sabitha 
Synopsis:
Transmitting the secret information by Steganography plays a vital role in Human Visual System (HVS). The carrier media such as image or audio or video can be used to hide the information. Steganalysis is a technique used to get rid of cheating, by identifying the hidden information from the carrier media. The identification of embedded information or message from the carrier media produces higher success rate to steganography methods. Image Steganography is the art of hiding the message or a file or an image by taking the image as carrier media. Based on the adaptable regions, the content is hidden and this method is termed as Adaptive image steganography. Dealing with retrieval of embedded content from the adaptable region of cover image is known to be Adaptive Image Steganalysis. The Blind Steganalysis is the ability to attack the stego image without the knowledge about steganography. Its Counter method, attacks the stego image by significant method used for steganography. In existing method, Enhanced canny edge detector is used to extract the features of the image better than other edge detectors, but smoothens the boundaries including noise and fails to identify the false edges. In the proposed method, Watershed method is used to segment the Adaptive regions from the stego image. The Markov Random Fields (MRF) extracts the features from the segmented adaptive region. The precision and recall is calculated after identifying the adaptive region with its payload location and hidden content using SVM (Support Vector Machine) classifier. An SVM is a binary classifier, classifies data by finding the best hyperplane which separates all data points of one class from the other class. After the classification and identification of payload location, the message is extracted from the hidden region by reversible two LSB (Least Significant Bit) bits.

Cost Control Model of Power Grid Maintenance using Fuzzy Pattern Recognition Theory

Vol. 3  Issue 1
Year: 2016
Issue:Mar-May
Title:Cost Control Model of Power Grid Maintenance using Fuzzy Pattern Recognition Theory
Author Name:M. Bhargavi and S. Vijayalakshmi 
Synopsis:
In power enterprises, the construction process is complicated using lines and equipment maintenance, the cost is affected by meteorological and geographical factors, which influence mode in uncertain. In this paper, the authors use a predictive control model to control the project cost using fuzzy clustering method and the threshold intervals of the objective function in clusters. This model uses relative fuzzy operator to build fuzzy matrix, construct correlation between factors, and describe the factors' effect. Extract the cluster's Eigen function, define the boundaries of various clusters, and determine the type of the predicted points and the range of the objective function. When the actual cost of the maintenance project is within the range calculated by the cost model, then it is normal. If the actual cost exceeds this range, then further analysis of all the aspects of the cost is needed to find out the reason.

Feature Diminish Based Nonlinear Support Vector Machine For Micro Classification Of Digital Mammogram Images

Vol. 3  Issue 1
Year: 2016
Issue:Mar-May
Title:Feature Diminish Based Nonlinear Support Vector Machine For Micro Classification Of Digital Mammogram Images
Author Name:Manoharan .R and Kalaimagal .R
Synopsis:

The interpretation and analysis of medical images represent an important and exciting part of computer vision and pattern recognition. Developing a computer-aided diagnosis system for cancer diseases, such as breast cancer, to assist physicians in hospitals is becoming of high importance and priority for many researchers and clinical centers. It is a complex process to develop a computer vision system to perform such tasks. Breast cancer is the cause of the most common cancer death in women. X-ray mammography is widely used to screen women with an increased risk of breast cancer. Computer Aided Detection (CAD) systems have been developed to boost efficiency and accuracy in diagnosing cancer. This research presents the design of CAD for cancerous micro calcification classification in digital mammogram images based on Discrete Shearlet Transform (DST) and Kernel Principal Component Analysis (KPCA). The purpose of the Kernel Principle Component Analysis improved the classification accuracy by reducing the number of features. The implementation of Mammogram breast cancer detection is done using MIAS Database and MATLAB Tool. Results are shown in DST based NLSVM superior to the other conventional classifier techniques.

Multilingual Speech Processing through MFCCs feature extraction for multilingual speaker identification system

Vol. 3  Issue 1
Year: 2016
Issue:Mar-May
Title:Vinay Kumar Jain and Neeta Tripathi 
Author Name:Navneet Kr. Kashyap, B. K. Pandey, H. L. Mandoria, and Ashok Kumar
Synopsis:

The speaker identification systems work only in a single language environment using sufficient data. Many countries including India are multilingual and hence the effect of multiple languages on a speaker identification system needs to be investigated. Speaker identification system shows poor performance when training is done in one language and the testing in another language. This is a major problem in multilingual speaker identification system. The main objective of this research work is to observe the impact of the languages on multilingual speaker identification system and identifying the variation of MFCC feature vector values in multilingual environments, which will help to design multilingual speaker identification system. The present paper explores the experimental result carried out on collected database of multilingual speakers of three Indian languages. The speech database consists of speech data recorded from 100 speakers including male and female. The Mel Frequency Cepstral Coefficients (MFCC) as a front end feature vectors are extracted from the speech signals. The minimum, maximum and mean values of the feature vectors have been calculated for the analysis. It is observed that Rajasthani language has the larger values as compared to Hindi language and Marathi Language in minimum values of the feature vectors, where as Marathi Language has the larger values as compared to Hindi language and Rajasthani language in maximum values of feature vectors. The impact of the languages on multilingual speaker identification system has been evaluated.

A Comprehensive Study on Different Pattern Recognition Techniques

Vol. 2  Issue 4
Year: 2016
Issue:Dec-Feb
Title:A Comprehensive Study on Different Pattern Recognition Techniques
Author Name:Navneet Kr. Kashyap, B. K. Pandey, H. L. Mandoria, and Ashok Kumar
Synopsis:

Pattern Acceptance has been admired because of its advancement in the appliance areas. The applying breadth includes medicine, communications, automation, aggressive intelligence, abstracts mining, bioinformatics, certificate classification, accent recognition, business and abounding others. In this analysis, cardboard assorted approaches of Arrangement Acceptance has been presented with their pros-cons, and the appliance specific archetype has been confirmed. From the base of the survey, arrangement acceptance techniques could be categorized into six parts. Such awning techniques include Neural Network scheme, Statistics Techniques, Template Matching, Hybrid versions and Fuzzy Model.

An Analytical Study of Handwritten Character Recognition

Vol. 2  Issue 4
Year: 2016
Issue:Dec-Feb
Title:An Analytical Study of Handwritten Character Recognition
Author Name:Ujwal Singh Vohra, Shri Prakash Dwivedi and H.L.Mandoria
Synopsis:

Handwritten Character Recognition is a crucial part of Optical Character Recognition (OCR) through which the computer understands the handwriting of individuals automatically from the image of a handwritten script. From a decade, OCR becomes the most important application of Pattern Recognition, Machine Vision and Signal Processing for the rapid growth of technology, which can be described as the Electronic or Mechanical conversion of the captured or scanned image. The image is converted into the machine encoded form that can be further used in machine translation, text to speech conversion, text mining and the storage of data. Selections of appropriate feature extraction and classification methods are the crucial factors for achieving a higher rate of recognition with greater level of accuracy for handwritten characters to accurately achieve recognition of each and every letter. Here, in this paper the authors attempt to give a more elaborative image for a comprehensive review that has been proposed to achieve a deep study of the handwritten characters recognition, and this data will be useful for the readers working in the field of handwritten character recognition.

Improved Tree Leaves Segmentation Using Hybrid GAC Approach

Vol. 2  Issue 4
Year: 2016
Issue:Dec-Feb
Title:Improved Tree Leaves Segmentation Using Hybrid GAC Approach
Author Name:Nivasini. R.P and Thilagamani.S
Synopsis:

Leaves are one of the important parts in a tree. Extracting accurately the shape of a leaf is a crucial step in image-based systems. The partial or total absence of textures on leaf surface and the high color variability of leaves belonging to the same species make shape as the main recognition element. For such reasons, leaf segmentation plays a decisive role in the leaf extraction process. Even though many general segmentation methods have been proposed in the last decades, leaf segmentation presents specific challenges. In particular, a pixel-level precision is required in order to highlight fine scale boundary structures and discriminate similar global shapes. The authors propose a robust and accurate method for segmenting objects acquired under various controlled conditions. Then, they have improved the performance of the segmentation methods using preprocessing tools such as, color distance map and input strokes. Based on these methods, we can eliminate unwanted boundaries and localize the leaf object efficiently. They have implemented a Hybrid Guided Active Contour (GAC) method to measure geometric properties of leaf images, and have provided with a comparative study for various segmentation algorithms based on performance metrics. Based on experimental results, GAC provides improved performance in leaf datasets.

An Automated Fabric Fault Detection Using a Microcontroller

Vol. 2  Issue 4
Year: 2016
Issue:Dec-Feb
Title:An Automated Fabric Fault Detection Using a Microcontroller
Author Name:A. Selvarasi
Synopsis:

Textile industries are one of the major revenue generating industries in Tamil Nadu, India. Greater efforts are taken in manufacturing the good quality fabrics. Defects in a fabric are a major issue to the textile industry. Textile industries in Tamil Nadu initially had only manual inspection strategy for the detection of faults. Later, automation has been made through image processing techniques. Traditional inspection process for fabric defects is by human visual inspection, which is inefficient, costly and time consuming. To enhance the accuracy of fabric defects detection, and help people out from this tedious and stressful work, an automated fabric inspection system has been proposed. To automate this process, the fault present on the fabrics can be identified using MATLAB with Image processing techniques and the implementation of this idea is done in Arduino kit for real time applications.

Local Orientation Gradient XOR Patterns: A New Feature Descriptor for Image Indexing and Retrieval

Vol. 2  Issue 4
Year: 2016
Issue:Dec-Feb
Title:Local Orientation Gradient XOR Patterns: A New Feature Descriptor for Image Indexing and Retrieval
Author Name:A. Hariprasad Reddy and N. Subhash Chandra
Synopsis:

This paper presents a novel feature extraction method, Local Orientation Gradient XoR Patterns (LOGXoRP) for image indexing and retrieval. The LOGXoRP encodes the exclusive OR (XOR) operation between the center pixel and its surrounding neighbors of quantized orientation and gradient values, whereas the Local Binary Patterns (LBP) and the Local Gradient Patterns (LGP) encode the relationship between the gray values of center pixel and its neighbors. The authors shows that the LOGXoRP can extract effective texture (edge) features as compared to LBP and LGP. The performance of the proposed method is tested by conducting two experiments on Corel-5K and Corel-10K databases. The results of the proposed method after being investigated shows a significant improvement in terms of their evaluation measures as compared to LBP, LGP and other existing state-of-art techniques on respective databases.

DWT based SVD and Morphological Gradient For Satellite Color Image Enhancement

Vol. 2  Issue 3
Year: 2015
Issue:Sep-Nov
Title:DWT based SVD and Morphological Gradient For Satellite Color Image Enhancement
Author Name:R. Thriveni and Ramashri Tirumala
Synopsis:

Digital image processing plays an important role in the analysis and interpretation of satellite image data. One of the most common degradations in satellite images is their poor contrast quality. Image enhancement technique help in improving the visibility of the image. This suggests the use of contrast enhancement methods as an attempt to modify the intensity distribution of the image. The main aim of this paper is to contrast and edge enhancements for digital satellite images using Discrete Wavelet Transform based Singular Value Decomposition and Morphological Gradient. The objective of the proposed method is that the input image is decomposed into different sub bands through DWT, estimating the singular value matrix of the low–low sub band image, and then, reconstructing the enhanced image by applying inverse DWT. To achieve a sharper color image, an intermediate stage for estimating the high-frequency sub bands is required. This is done by the success of threshold decomposition, gradient based operators are used to detect the locations of the edges, sharpen these detected edges. The results show the efficiency of proposed satellite image enhancement with color balances and not introducing unnecessarily artifacts. The proposed technique has been tested on satellite benchmark images. The quantitative (PSRN, MSE, RMSE, EME) and visual results show the efficiency of the proposed enhancement technique.

Trademark Image Retrieval Using 3-D Color Histogram Approach

Vol. 2  Issue 3
Year: 2015
Issue:Sep-Nov
Title:Trademark Image Retrieval Using 3-D Color Histogram Approach
Author Name:Latika Pinjarkar, Manisha Sharma and Smita Selot
Synopsis:

Products and services available in the market in the form of brands that make trade practices are very important. Nowadays in the market, brand name is becoming very important. Every organization must have it's unique trademark or logo for uniqueness. Therefore designing an efficient trademark retrieval system and its evaluation for distinctiveness is thus becoming a very tedious job nowadays. Trademark Image Registration is one of the important application area of Content Based Image Retrieval (CBIR). Trademark image registration, where a new candidate mark is compared with the existing marks to ensure that there is no risk of confusion, has long been recognized as a prime application area of CBIR [1]. In the proposed work, a CBIR system is designed for trademark image retrieval based on 3D color histogram (HSV values) technique. The color histogram has the advantages of rotation and translation invariance and it has the disadvantages of lack of spatial information. The experiments were conducted on a database of few trademark images. The performance of the system was evaluated using standard evaluation parameters precision and recall.

Robot Localization and Object Detection with Fish-Eye Vision System And Sensors

Vol. 2  Issue 3
Year: 2015
Issue:Sep-Nov
Title:Robot Localization and Object Detection with Fish-Eye Vision System And Sensors
Author Name:G. Vara Prasad and C. Shoba Bindu
Synopsis:

This paper addresses the problem of designing an autonomous robot for the purpose of navigating in the sensitive areas, keeping focus on localization of the robot. If a robot doesn't know its current location, it is very difficult to determine its further activities. Thus, localization plays a vital role in building an efficient mobile robot. This paper mainly focuses on design and implementation of OI-ROBOT (Object Identification Robot) which mainly comprises of fish eye lens camera to obtain Omni-directional vision, Sensors, to identify the position of the robot and an embedded micro controller that takes charge in target recognition and distortion rectification. The experimental results demonstrate the navigation and selflocalization of the mobile robot. This Robot also helps in fire detection and can be easily available through an Andriod phone or Internet.

An Application of GMM Algorithm in Signature Skew Detection

Vol. 2  Issue 3
Year: 2015
Issue:Sep-Nov
Title:An Application of GMM Algorithm in Signature Skew Detection
Author Name:T. M. Rajesh and V. N. Manjunath Aradhya 
Synopsis:

Signature Identification and Verification (SIV) system is one of the oldest behavioral biometrics, which is being more widely used for the identification and verification applications by a person. Handwritten signature written with a skew is a hurdle to any SIV system. If one has to achieve the accurate results in identification and verification process using signature as a biometric trait, we need to remove the skew of the signatures which are scanned from the documents, and in order to estimate the skew angle and correct the skewness of the signature, skew detection stage is the most important step to be taken care off. In this paper the authors present a Gaussian Mixture Model to estimate the skew angle of a signature. Experimentation is carried out on the Kannada signature database of 30 users.

Drought Pattern Investigation through processing Normalized Vegetation Index-based Satellite Images

Vol. 2  Issue 3
Year: 2015
Issue:Sep-Nov
Title:Drought Pattern Investigation through processing Normalized Vegetation Index-based Satellite Images
Author Name:Taye Tolu Mekonnen and Kumudha Raimond
Synopsis:

The emergence of satellite remote sensing technology has provided people with various appropriate, more accurate and easy to use tools for monitoring environmental conditions like the health of vegetation. Using the red and infrared band reflectances, for instance, enables the derivation of a vegetation index called Normalized Difference Vegetation Index (NDVI) in spatial and temporal domains. This index is vital to assess the evolution of drought as well as predict crop yield.

The aim of this study is to analyze a series of deviation of NDVI images, extract virtual drought objects from the series, and investigate for drought patterns from historical images for the growing season after appropriate preprocessing and segmentation of the images.

In this study, the virtual drought objects extracted from images over the growing season (June -September) were found to exhibit a given (similar) pattern for the historical drought years, taken in Ethiopia. The graphical pattern exhibited by historical occurrences of drought for specific areas on the ground, demonstrated nearly a similar time series except the fact that the intensities vary. This variance is an indicative of the difference in the severity level of the droughts at each specific area. Hence, given the implementation of the appropriate prediction tool, this similarity in the time series analysis of the historical data over a drought will give new views for ways in drought prediction for early warning and crop condition monitoring at near real-time.

A Comprehensive study of Enhancement and Segmentation Techniques on Microarray Images

Vol. 2  Issue 2
Year: 2015
Issue:Jun-Aug
Title:A Comprehensive study of Enhancement and Segmentation Techniques on Microarray Images
Author Name:Elavaar Kuzhali S and Suresh D.S
Synopsis:
Microarray image enhancement and segmentation procedure are the rudimentary processing steps to obtain high quality image data that would truly reflect the underlying biology in the samples. Robust enhancement and segmentation has been the subject of research for many years, and it is important to understand these crucial steps. Reducing noise from the original image is still a challenging problem. It is important to preserve features like edges and sharp structures for better visualization and further analysis. After denoising, segmentation process is a vital step in microarray image. Selection of suitable algorithm for image segmentation is a very difficult task for a particular type of image although extensive work has been proposed. In this paper, the authors outline fundamental concepts of various existing algorithms, its advantages and limitations for microarray images. These algorithms are classified into various categories and a brief description and analysis of these algorithms is presented. This is an initiative to study, analyze and to provide future direction for research in the areas of microarray enhancement and segmentation techniques.

User Authentication and Identification Using Neural Network

Vol. 2  Issue 2
Year: 2015
Issue:Jun-Aug
Title:User Authentication and Identification Using Neural Network
Author Name:Md Liakat Ali, Kutub Thakur and Charles C. Tappert 
Synopsis:
Now-a-days people are heavily dependent on computers to store and process important information. User authentication and identification has become one of the most important and challenging issue in order to secure them from intruders. As traditional user ID and password scheme have failed to provide information security, keystroke dynamics authentication systems can be used to strengthen the existing security techniques. Keystroke dynamic authentication systems are transparent, low cost, and non-invasive for the user, but it has lower accuracy and lower performance compared to other biometric authentication systems. The aim of this paper is to depict a detailed survey of the researches on keystroke dynamic authentication that have used neural networks for classification described in the last two decades. The summary, accuracy of each experiment, and shortcomings of those researches have been presented in this study. Finally, the paper addresses some challenges in keystroke dynamic authentication systems using neural networks that need to be resolve in order to get better performance.

Efficient Face Recognition Using Expert Search Techniques Under Difficult Lighting Conditions

Vol. 2  Issue 2
Year: 2015
Issue:Jun-Aug
Title:Efficient Face Recognition Using Expert Search Techniques Under Difficult Lighting Conditions
Author Name:Basava Raju. K, Y. Rama Devi and P. V. Kumar
Synopsis:
Making face recognition more reliable under uncontrolled lighting conditions is one of the most important challenges for practical face recognition systems. Data preprocessing thus becomes an important and emerging topic in many data-driven applications such as image processing and bioinformatics. Dimensionality reduction provides an efficient way for data abstraction and representation as well as feature extraction. It aims to detect intrinsic structures of data and to extract a reduced number of variables (dimensions) that capture and retain the main features of the high-dimensional data. For instance, images contain a large number of pixel values and are presented as high-dimensional arrays. The computationally efficient combination of the most successful local appearance descriptors, like Local Binary Pattern (LBP) with its extension Local Ternary Patterns (LTP) for facial appearance and Gabor filter to encode facial shape over a range of coarser scales are implemented. Here, a data mining approach for dimensionality reduction provides an efficient way for data abstraction and representation as well as feature extraction. It aims to detect intrinsic structures of data and to extract a reduced number of variables (dimensions) that capture and retain the main features of the highdimensional data. The resulting method provides state-of-the-art performance on different data sets that are widely used for testing recognition under difficult illumination conditions: Ex-tended Yale-B, CAS-PEAL-R1. Further experiments show that our preprocessing method outperforms several existing preprocessors for a range of feature sets, data sets and lighting conditions by comparing with previously published methods, achieving a face verification rate of 89.1% at 0.2% false accept rate.

FPGA Implementation Of Shearlet Transform Based Invisible Image Watermarking Algorithm

Vol. 2  Issue 2
Year: 2015
Issue:Jun-Aug
Title:FPGA Implementation Of Shearlet Transform Based Invisible Image Watermarking Algorithm
Author Name:Sabarinathan. E and Manoj.E 
Synopsis:
In today’s internet era, fortification of digital gratified during communication is penurious. Watermarking affords the security for digital content. Robustness of such watermarking procedure is quite low. For increasing the robustness an approach is introduced which is Neuro fuzzy based watermarking embedding process. Conventional methods have information loss during recovery as, it will be easily hacked, due to lower embedding capacity and, requires more memory and power consumption. The proposed scheme binary image is embedded over color image which uses Shearlet and Inverse Shearlet algorithm for preprocessing of an image and Neuro fuzzy algorithm to embed the bits in green plane of an image. Requirement of Lower Memory and, speed of encryption are improved by Neuro fuzzy algorithm.

Fourier-Cosine Transform Coefficients Fusion for Face Recognition

Vol. 2  Issue 2
Year: 2015
Issue:Jun-Aug
Title:Fourier-Cosine Transform Coefficients Fusion for Face Recognition
Author Name:Priyadharshini. S and Maheswaran U
Synopsis:
3D Face recognition has been an area of interest among researchers for the past few decades especially in pattern recognition. The main advantage of 3D Face recognition is the availability of geometrical information of the face structure which is more or less unique for a subject. This paper focuses on the problems of person recognition using 3D Face data. Use of unregistered 3D Face data drastically increases the operational speed of the system with huge database enrolment. In this effort, unregistered 3D Face data is fed to a classifier in multiple spectral representations of the same data. Discrete Fourier Transform (DFT) and Discrete Cosine Transform (DCT) are used for the spectral representations. The face recognition accuracy obtained when the feature extractors are used individually is evaluated. Fusion of the matching scores proves that the recognition accuracy can be improved significantly by fusion of scores of multiple representations. FRAV 3D database is used for testing the algorithm.

Mixing Fingerprints : A Survey

Vol. 2  Issue 1
Year: 2015
Issue:Mar-May
Title:Mixing Fingerprints : A Survey
Author Name:Ria Mathews and Bino Thomas 
Synopsis:
Biometrics has an important role in privacy protection, when compared to traditional privacy protection methods like tokens, PIN, passwords etc. With the widespread use of fingerprint techniques in authentication systems, privacy protection of the fingerprint becomes an important issue. Traditional encryption is not sufficient for fingerprint privacy protection because decryption is required before the fingerprint matching, which exposes the fingerprint to the attacker. In recent years, significant efforts have been put into developing specific protection techniques for fingerprint. The main objective of this paper is to make a study on mixing fingerprints and how they are used in privacy protection of fingerprints. In this paper various methods of biometric template protection of fingerprint by mixing the fingerprints or multi-biometrics has been surveyed.

Language Identification Using MFCC Features Derived During Oration

Vol. 2  Issue 1
Year: 2015
Issue:Mar-May
Title:Language Identification Using MFCC Features Derived During Oration
Author Name:Manogna Maddali and C. Shoba Bindu 
Synopsis:
Automatic Language Identification is the task of identifying the Spoken Language, given utterance of speech. Many Communication Systems make use of this LID. Acoustic properties are used in many experiments, as it is easy to differentiate. Instead of using these features, prosodic properties can be used to identify the Language. The main idea is to explore the duration of neighboring syllable like units as a language discriminative feature. This paper proposes a LID which uses the rhythmic properties of Spoken Speech. Prosodic Features are extracted using Mel Frequency Cepstral Coefficients (MFCC). Based on the energy levels in the Signal, Phoneme Recognition is done to identify the syllable, like units. ANN is used to train the system and results are generated. The main focus of this paper is to improve the Recognition Accuracy. The error rate is reduced when compared with other systems.

Comparison of Spatial Domain Features for Writer Recognition Under Different Ink Width Conditions

Vol. 2  Issue 1
Year: 2015
Issue:Mar-May
Title:Comparison of Spatial Domain Features for Writer Recognition Under Different Ink Width Conditions
Author Name:Sharada Laxman Kore and Shaila Apte
Synopsis:
In this paper, the authors tested the usefulness of most commonly used existing methods of writer recognition under different ink width conditions. A comparative study of Spatial Domain Features is presented in this paper. The existing methods give low error rate when they compare two handwritten images with different pen type. To improve the accuracy to a higher level histogram, variance in histogram bins and normalized histogram are used as features to recognize the handwriting. The system is tested for 981 writers with 2 samples, each with different writing instruments. The system is tested using Chain Code and Differential Chain Codes. Experimental result shows that the histogram of chain code outperform the other methods with 90.46 % as the recognition accuracy on this newly created dataset.

An Intelligent System Approach for Handwritten Kannada Word Recognition

Vol. 2  Issue 1
Year: 2015
Issue:Mar-May
Title:An Intelligent System Approach for Handwritten Kannada Word Recognition
Author Name:M. S. Patel and S. C. Linga Reddy
Synopsis:
The challenges in OCR system are many in the area of Handwritten Character and Word Recognition. From its very nature, Handwritten Character Word is a mixture of cursive and non-cursive segments. This leads to the problem of Recognition being significantly difficult. In this paper, the authors propose an intelligent system for recognition of handwritten Kannada words for recognition of the names of Districts and Taluks written on boards, land marks, etc. The proposed system applies an idea of subspace approach with popular Neural Network Architectures such as Generalized Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) for classification. This method is experimented on handwritten words comprising 189 (District & Taluk names of Karnataka State) classes.

Face Detection and Recognition Based on Facial Features and Key Points Matching

Vol. 2  Issue 1
Year: 2015
Issue:Mar-May
Title:Face Detection and Recognition Based on Facial Features and Key Points Matching
Author Name:Basava Raju .K, Y. Ramadevi and P. V. Kumar
Synopsis:
Face Recognition has benefitted greatly from the many databases that have been produced to study it. Most of these databases have been created under controlled conditions to facilitate the study of specific parameters on the Face Recognition problem. These parameters include such variables as Position, Pose, Lighting, Expression, Background, Camera Quality, Occlusion, Age, and Gender. While there are many applications for Face Recognition Technology in which one can control the parameters of Image Acquisition, there are also many applications in which the practitioner has little or no control over such parameters. This paper is provided as an aid in studying the latter, unconstrained, face recognition problem. The database represents an initial attempt to provide a set of labeled face photographs spanning the range of conditions typically encountered by people in their everyday lives. This paper describes a face detection system which goes beyond traditional face detection approaches normally designed for single faced images. The system described in this paper has been designed taking into account spatial coherence contained in multiple face detection. The resulting system builds a feature based model for each detected face, and searches them using various model information in the database. It provides a feasible way to locate the positions of two eyeballs, near and far corners of eyes, midpoint of nostrils and mouth corners from face image. This approach would help to extract useful features on human face automatically and improve the accuracy of face recognition.

FPGA based parallel hardware architecture for real time object classification

Vol. 1  Issue 4
Year: 2015
Issue:Dec-Feb
Title:FPGA based parallel hardware architecture for real time object classification
Author Name:Sabarinathan. E and Manoj. E
Synopsis:
Efficacious Recognition and consistent identification of visual features is an important problem in applications, such as Object Recognition, Structure from Motion, Image Indexing and Visual Localization. The input data takes, many forms such as Video Sequences, views from Multiple Cameras or Multi-dimensional data from a scanner. Concurrent performance is a perilous demand to utmost of these applications, which necessitate the finding and corresponding of the visual features in real time. Although Feature Recognition and Identification Methods have been studied in the Literature, due to their Computational Intricacy, pure software execution by Unique Hardware is far from suitable in their performance for Real Time Applications. The existing system consists of Scale Invariant Feature Transform (SIFT) for Feature Detection and Binary Robust Independent Elementary Features (BRIEF) for Feature Description and Matching. This system fails to detect the features which are invariant to scale, change in viewpoint and illumination, and the addition of noise. The proposed system consists of Wavelet Feature Extraction Method, and for classification process, Subtractive Clustering is used. This system reduces time consumption and overall system complexity. This paper focuses on a different hardware design to enable real-time performance of founding correspondences between idealistic sequential frames of high-resolution 720 p (1280 x 720) video. Due to these assistances, the proposed system attains feature detection and matching at 60 frame/s for 720-p video. Its processing speed can encounter and even overdo the demand of most realistic concurrent video analytics applications.

Single Instruction Multiple Data (SIMD) approach for Efficient Fractal Image Encoding using Distributed Architecture

Vol. 1  Issue 4
Year: 2015
Issue:Dec-Feb
Title:Single Instruction Multiple Data (SIMD) approach for Efficient Fractal Image Encoding using Distributed Architecture
Author Name:Akhilesh Kumar, G. R. Sinha and Vikas Dilliwar
Synopsis:
There are several application areas where tremendous computational resources are required including image processing, big data and genetic mapping which are computationally intensive areas. Huge computing resources are required to solve such complex problems and powerful computing environment is needed. An emphasis is made on fractal image compression, which requires higher computing needs to solve. Single Instruction Multiple Data approach is followed using distributed architecture. The research compares the performance on the basis of speed up and encoding time. It was found that image compression requires more computing power to solve in lesser time. In this paper, the parallel algorithms are developed using Distributed Fractal Image Encoding Architecture (DFIE) as Single Instruction Multiple Data (SIMD) approach

Pattern Analysis Based CRF Segmentation and MRF Classification for Skin Lesions in Dermoscopic Images

Vol. 1  Issue 4
Year: 2015
Issue:Dec-Feb
Title:Pattern Analysis Based CRF Segmentation and MRF Classification for Skin Lesions in Dermoscopic Images
Author Name:Delfin Ruby. S, Subbulakshmi. N and S. Allwin Devaraj 
Synopsis:
In this paper, Conditional Random Field Based Segmentation and different model-based Markov Random Field(MRF) classification for skin lesions in dermoscopic images are proposed. This method is used in the pattern analysis framework for diagnosis of melanoma by dermatologists. A Dermoscopic image is smoothened by Wiener Filer Method and converted into Grayscale Image. Then the image is diluted which gives the contour of an image. The input image is segmented by Conditional Random Field Technique. The Estimated CPU time is calculated which gives less Processing Time. Then classification is carried out by an image retrieval approach with different distance metrics. These features are supposed to follow Gaussian Model, Gaussian Mixture Model, and Bag-of-features Histogram Model. The main aim of this paper is the classification of an entire pigmented lesion and analysis of the texture of an image. The image database is extracted from a public Atlas of Dermoscopy. Receiver Operating Characteristics (ROC) Curve is used to evaluate the performance of Segmentation Process which gives more accuracy. Finally, the skin lesions with their levels were analysed.