Informatics Publishing Limited

B. Karthikeyan ¹, V. Vaithiyanathan ², B. Venkatraman , M. Menaka ³

Affiliations
1 School of Computing, SASTRA University, Thanjavur, 613401, IN
2 Indira Gandhi Centre for Atomic Research, Kalpakkam, 603102
3 Indira Gandhi Centre for Atomic Research, Kalpakkam, 603102, IN

Abstract

Digital image processing is used to identify regions in an image by using various segmentation methods. This paper gives a brief account on five of the different segmentation techniques namely region growing, watershed, thresholding, split and merge, k-means clustering methods highlighting the advantages as well as disadvantages of each of these methods. A modification of traditional region growing segmentation method is presented which automatically selects the seed points and grows the regions until all the regions in the image are segmented. The results of segmentation methods presented in the paper are not dependent on the kind of image to be segmented and these methods are used in segmenting industrial radiographic weld images in which several defects like porosity, lack of fusion, slag line, incomplete penetrations, and wormholes occur. The methods are evaluated on various types of images and efficiency of these methods in the detection of several weld defects is presented along with the experimental results. The evaluation of performance of these different segmentation methods on sample images is done on the basis of subjective criteria and conclusions are achieved. These methods are used to detect the flaws in an object by identifying the flawed region in the image. Due to this ability of region detection, it finds various applications in medical imaging, optical character recognition, computer vision, remote sensing, mobile robots and industrial radiography.

Keywords

Image Segmentation, Thresholding, Region Growing, Watershed, Split and Merge, K-means Clustering

Full Text

   

B. Venkatraman ¹, M. M. Anishin Raj ², V. Vaithiyanathan ³

Affiliations
1 Radiological Safety and Environmental Group, IGCAR, Kalpakkam-603102, IN
2 Department of ICT, SASTRA University, Thanjavur-613401, IN
3 School of Computing, SASTRA University, Thanjavur-613401, IN

Abstract

Non Destructive Evaluation (NDE) is a technique to detect the defects without affecting the intended application or the structure, which is mainly used for damage assessment and quality control. NDE is basically used for automation of defect quantification. This paper presents a method for weld defect detection using iterative method for image reconstruction. Image reconstruction is a technique of reconstructing the image of object from the radon transform of the object, where radon transform is obtained by passing an energy source through the object in various angles and collecting the projected data on a detector. Weld defects such as slag inclusion, lack of penetration, and burn through can cause serious disaster if it is undetected at the time of weld process. The system of linear equation under consideration in Computed Tomography (CT) are basically very large in size, so the direct method takes too much of computational time which makes it impractical for implementation. Cimmino's method and Simultaneous Algebraic Reconstruction Technique (SART) are iterative methodologies for image reconstruction which are best suited for solving large scale linear system where direct method fails due to very large time consumption. This paper compares the experimental results of image reconstruction of weld defect radiographic images using SART and Cimmino's method for various test images with varying number of projections.

Keywords

Cimmino's Method, SART, Radon Transform, Tomography

Full Text

   

P. Subitha ¹, V. Vaithiyanathan ²

Affiliations
1 Department of Computer Science and Engineering, SASTRA University, Thanjavur, IN
2 School of Computing, SASTRA University, Thanjavur, IN

Abstract

This work is to preserve the distortion of marked image from the original image, that is, to improve the Peak Signal-to-Noise Ratio (PSNR) and to improve the Embedding Capacity (EC). Pixel-Value-Ordering (PVO) is the technique used for ensuring reversibility in Reversible Data Hiding (RDH). The difference-value is calculated from ordered pixel blocks. From the difference-value histogram, the rough bins are shifted to vacate place for concealing secret whereas the smooth bins are expanded to conceal secret. The proposed Novel Reversible Pixel-Value-Ordering Technique (RPVOT) is the containment of two schemes: Novel Difference Computation (DC) and Novel Histogram Shifting (HS). Firstly, for DC, the existing approaches compute the difference between first two (or, last two) pixel values of an ordered block whereas, the novel DC technique picks up the first two pixel values (or, last two pixel values) from an ordered block and the rounded mean of pixel values in minimum and maximum position subtracted from a pixel value in minimum position is computed. This novel DC makes eligible more number of blocks for secret concealment than other existing approaches by which more secret bits can be concealed and visual worth of the marked image is conserved as well. Secondly, novel HS is proposed which break the rule of shifting all the blocks that are not meant for embedding by shifting some blocks using naturally occurring empty bins in the histogram. This novel HS prevents many blocks from unnecessary alteration in their pixel values and hence, visual worth of the marked image is improved further. Both novel DC and novel HS are combined together to form novel RPVOT which significantly improves the Embedding Capacity (EC) along with Peak Signal-to-Noise Ratio (PSNR).

Keywords

Difference Computation, Difference-Histogram, Histogram Shifting, Reversible Data Hiding, Pixel-Value-Ordering.

Full Text

   

M. Rajasekhar Reddy ¹, V. Vaithiyanathan ¹, B. Karthikeyan ¹, Gonavaram Venkata Sai Theja ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

Background/Objectives: This paper contains the change detection between frames of a video. The main objective is to show how the sequence of frames differ from one another in a video. Methods/Statistical Analysis: The amount of change between two frames is measured using the pixel based change detection parameter’s Absolute Average Difference (AAD), Peak Signal to Noise Ratio (PSNR), Normalized Correlation (NC), Signal to Noise Ratio (SNR) and Mean Squared Error (MSE). These parameters detect the changes in each and every pixel of the frame with respect to other frame and values are calculated for each frame of a video and compared in the tables followed by analysis of the values. Findings: The results indicated the changes that are not perceived by the human eyes. They depict that if the change between two frames are visible to the human eyes then they differ more based on the parameter we have considered and if the change is not visible to the eyes then minute differences is observed between the two respective frames. Application/Improvements: The change detection plays a significant role in visual media. Based on the change detection of frames, analysis of a video can be done.

Keywords

Change Detection, Frame, Mean Squared Error, Normalized Correlation, Peak Signal to Noise Ratio, Pixel

Full Text

   

M. Lavanya ¹, R. Vijay Sai ¹, A. Festina ², J. Eshwari ², T. Manopriya ², V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur – 613401, Tamil Nadu, IN
2 Information and Communication Technology, SASTRA University, Thanjavur – 613401, Tamil Nadu, IN

Abstract

This article aims to focus on encryption based algorithm on ASCII value and Random number generator. Proposed algorithm has been developed with the view to achieve data security and prevent unauthorized persons from meddling with such secret data. An ASCII based conversion has been implemented to encrypt shorter length messages through a symmetric key. The algorithm specifically accommodates the concept of random number generation that makes it tough for the hackers to decrypt despite accidentally discovering the key. This concept also involves floating point numbers for encryption to enhance the difficulty level of cryptanalysis. Hence this algorithm will provide an efficient way to make it almost impossible for the intruders to track the message.

Keywords

ASCII, Encryption, Hackers, Random Number, Symmetric Key

Full Text

   

R. Sivagami ¹, V. Vaithiyanathan ¹, V. Sangeetha ¹, M. Ifjaz Ahmed ¹, K. Joseph Abraham Sundar ¹, K. Divya Lakshmi ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613402, Tamil Nadu, IN

Abstract

Low resolution Multispectral images obtained from earth observation satellite interpreted directly have less information which is not suitable for remote sensing applications. The advancement of sensors onboard satellites provides panchromatic images which have more image details and low-resolution MS images lead the way for the researchers to develop algorithms suitable for fusing multi-sensor images which can improve the resolution of the MS images. In this paper review on various pixel based fusion algorithms and evaluation metrics are presented. From the literature review, it is inferred that the Multi resolution techniques will give better accuracy than all other traditional algorithms.

Keywords

Evaluation Metrics, Fusion Algorithms, Fusion Transforms, Image Fusion, Remote Sensing

Full Text

   

B. Thamotharan ¹, V. Vaithiyanathan ¹, B. Venkatraman ², M. N. Mangalapurani ¹

Affiliations
1 SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 RSEG, IGCAR, Kalpakkam - 603102, Tamil Nadu, IN

Abstract

Filtering is a technique for enhancing an image. With the help of filtering Smoothing, sharpening and edge enhancement Image processing operations can be implemented. Under intense gamma field bubble detector is used to detect the amount of neutron dose. The number of nucleated bubbles yields the neutron dose. The methodologies proposed here is to apply various algorithms to those images of bubble detector and analyzing it, there by contributing an enhanced image to accurately calculate the number of bubbles in the detector.

Keywords

Median Filter, Pixel, PSNR, Spatial Domain, Square Window Size

Full Text

   

V. Sangeetha ¹, V. Vaithiyanathan ¹, R. Sivagami ¹, K. Divyalakshmi ¹, K. Joseph Abraham Sundar ¹, M. Ifjaz Ahmed ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613402, Tamil Nadu, IN

Abstract

Skeletonisation is an effective way to provide an intact representation of an object’s shape. This approach has great applications in the fields of motion planning, object representation, tracking, information retrieval, topology representation, sensor distribution and location, facility location, forestry application, building constructions etc. Skeletons naturally provide a pixel to boundary mapping through which the path between points can be found in a terrain map. Many approaches for determining the skeleton of a terrain exist. In this paper, the different methods for Skeletonisation are discussed. Initially the various categorizations of Skeletonisation is discussed which is further followed by application of those algorithms for path determining. Quantitative measures for validating the skeleton are also discussed. Finally, the applications of Skeletonisation in various domains are elaborated.

Keywords

Distance Map, Distance Transform, Skeletonisation, Thinning, Voronoi Diagram

Full Text

   

V. Vaithiyanathan ¹, K. Divya Lakshmi ¹, K. Joseph Abraham Sundar ¹, M. Ifjaz Ahmed ¹, V. Sangeetha ¹, R. Sivagami ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613402, Tamil Nadu, IN

Abstract

Local features of an image are used in many computer vision applications such as object detection and scene matching. The gradient orientation histogram is used by many local features such as Scale Invariant Feature Transform (SIFT), a widely used image local feature. This paper discusses various distance functions that can be used to measure the similarity between the local features described by the gradient orientation histogram. A distance function, based on the quadratic form is proposed for the SIFT descriptor. The state of the art distance functions - Euclidean, Chi-square, Manhattan and the proposed quadratic form based distance function are calculated between the features extracted from the images. Nearest neighborhood ratio strategy is used to find the corresponding features based on the distance measure. Correct matches are estimated using the ground truth transformation function between the images, present in the form of homograph matrix. It is experimentally found that the proposed distance function has an execution time reduced by 21% compared to the Euclidean distance for a similar accuracy performance. The proposed distance retrieves more number of correct matches compared to the modified Earth Mover distance which is fastest among the evaluated distance functions. The future work will be aimed at improving the time taken for computing the distance matrix between the feature sets and a better strategy for computing the matches.

Keywords

Distance Functions, Gradient Orientation Histogram, Image Matching, Local Features, SIFT

Full Text

   

K. S. Suresh ¹, V. Vaithiyanathan ¹, S. Venugopal ²

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401 Tamil Nadu, IN
2 Indira Gandhi Centre for Atomic Research, Kalpakkam - 603102, Tamil Nadu, IN

Abstract

Travelling Salesman Problem (TSP) is a very old problem which has been solved in so many methodologies. The solution for the Robot Path Planning (RPP) can be derived using the methodologies used for the TSP. In this paper, Genetic Algorithm (GA) principle is employed to solve the TSP and is mapped to solve the RPP with the same principle. The both problems are defined to observe similarity between these problems and enumerated the conversion phases. In these two cases how the solutions are to be derived to implement the GA technique to accomplish the optimal path in both cases and tested for different number of cities, population space and generations. The minimum cost and mean cost of the solution space proves its giving the optimal result

Keywords

ASCII, Encryption, Hackers, Random Number, Symmetric Key

Full Text

   

M. Lavanya ¹, Aarthi Ravi ², Ajay Aditya ², Rukmani Samyuktha ², V. Vaithiyanathan ¹, S. Saravanan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

This paper aims to bring enhanced load balancing scheduling on private cloud computing. As cloud computing has become a developing and emerging area, the need for a cloud becomes mandatory in working areas. The advantage of technology in their own data centers to evolve a private cloud. Due to the presence of private cloud and to fulfill its unique characteristics and special requirements, it becomes a challenging task to optimally schedule virtual machine instances requests onto nodes to compute when there are multiple tasks to satisfy. In this paper, we discuss about load balancing, which is to schedule task among various end users. The scheduling algorithm used is Round Robin algorithm. This algorithm reduces the response time and improves the processing speed. According to this algorithm the nodes are allocated to the virtual machines along with their corresponding task to a particular node in a cyclic fashion. Each node in the cloud is scheduled equally with the task until all the tasks in the global queue all allocated.

Keywords

Cloud Computing, Load Balancing, Private Cloud, Round Robin Algorithm, Scheduling

Full Text

   

M. Lavanya ¹, G. Aishwarya ², S. Keerthana ², V. Vaithiyanathan ¹, S. Saravanan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 Information and Communication Technology, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

This article aims to bring a novel method in cipher algorithm for secure aware communication. This paper proposes a unique scheme and ensures higher security during encryption and decryption process. The Key (ki) is generated for every Plain text pi. Plain text and key are converted to their equivalent ASCII values, by which the scrambled Cipher text (ci) is generated by implementing some of the concepts of the substitution techniques. During Decryption, the corresponding (ki) are used to recover the Plain text pi. It makes sure the need to send the full length key along with the cipher text for decryption process. The suggested method assures the greater security during transmission. There is a practical hindrance in guessing the Number of rounds (N) and the number of bits n shifted, by Cryptanalyst. This method will be more suitable for analyzing the discover key (ki) values from attempting Brute Force technique.

Keywords

Ciper Algorithms, Cryptanalyst, Decryption, Encryption, Secure Communication

Full Text

   

M. Lavanya ¹, T. N. Janani ², S. Sushmita ², M. Sunandha ², V. Vaithiyanathan ¹, S. Saravanan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 Information and Communication Technology, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

This article mainly focused on cloud scheduling with constraint based decentralized task routing. The job of scheduling tasks across various nodes in a hierarchical network scenario is an exigent problem. The concept of decentralized distribution scheme proposed in base paper is time-consuming since it has to compute the availability function for each and every node. In this paper we proposed a CBDA (Constraint Based Decentralized Algorithm) which offers the expediency of being quick and “Make-span minimization policy” is implemented to reduce the completion time of the currently executing nodes. In our presumption, the submission nodes are semi centralized and it can store the availability information of the nodes or routers within its area. This paper considers the allotment of the tasks to the execution nodes which are unoccupied by other tasks. The dynamic allotment of the tasks to the nodes in the tree based approach is the major criteria for selecting the desired node. This paper proposes a trade-off between fully centralized model and the decentralized model by implementing a new constraint based decentralization scheme which saves time consumption and enhances efficiency of task scheduling.

Keywords

Cloud Computing, Constraint based Method Scheduling, Decentralized Router, Dynamic Task

Full Text

   

K. S. Suresh ¹, V. Vaithiyanathan ¹, S. Venugopal ²

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 Indira Gandhi Centre for Atomic Research, Kalpakkam - 603102, Tamil Nadu, IN

Abstract

Robot Path Planning (RPP) is solved using Genetic Algorithm (GA) principle for collision-free navigation for the three dimensional static space to find the optimal path. In this paper, Layered Approach is employed where the whole three dimensional space is considered as layers of two dimensional spaces to accomplish the RPP to reach the target by avoiding obstacles and find the shortest path. The quality of the path is ensured by nearest neighbourhood approach. Implementation of the principle of GA to solve RPP is effective where the environment contains huge number of solution paths compared to the classical methods to obtain the shortest path from source to target. This approach is tested for different number of layers and the results are tabled. The path generated and optimal path obtained by the implementation of this approach has been compared with the cost of the optimal path obtained manually.

Keywords

Collision-Free, Genetic Algorithm, Robot Path Planning, Three Dimensional Spaces

Full Text

   

M. Lavanya ¹, V. Vaithiyanathan ²

Affiliations
1 School of Computing, SASTRA University, Thanjavur – 613401, Tamil Nadu
2 School of Computing, SASTRA University, Thanjavur – 613401, Tamil Nadu, IN

Abstract

This paper presents dynamic resource allocation in cloud computing using load prediction algorithm. Cloud computing is a technology that is of increasing demand these days. Cloud computing provides various kinds of services to the users. In cloud computing the provider dynamically allocate the resources. Doing so, the service provider should have some knowledge about the future resource needs. They can be calculated using the load prediction algorithms. In this paper an algorithm named Enhanced Exponentially Weighted Moving Average (EEWMA) is used to predict the load, which is efficient in terms of both overload avoidance and green computing. EEWMA algorithm predicts the future need of resources effectively and it is suitable for both increasing and decreasing need of resources. This proposed load prediction will be well suitable for overload avoidance applications.

Keywords

Cloud Computing, Dynamic Resource Allocation, Green Computing, Load Prediction, Resources

Full Text

   

K. Joseph Abraham Sundar ¹, K. Divyalakhsmi ¹, M. Ifjaz Ahmed ¹, R. Sivagami ¹, V. Sangeetha ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613 401, Tamil Nadu, IN

Abstract

Super resolution image reconstruction is defined as generating a high resolution image from a low resolution image or sequence of low resolution images captured from identical scene apparently a video. An algorithm for reconstructing a high resolution image from a low resolution image by altering the frequency components is discussed in this paper. In this method the high frequency components of the zoomed low resolution image is modified so as to increase the resolution of the low resolution image. The evaluation for the experiments is based on the performance measure matrix peak signal to noise ratio. The experimental results shown proves that the algorithm is highly advantageous and computationally fast compared to the other interpolation methods. The algorithm will be helpful in practical applications of medical imaging diagnosis, remote sensing and military applications.

Keywords

Filters, Frequency Spectrum, Interpolation, Image Reconstruction, Super Resolution

Full Text

   

M. Ifjaz Ahmed ¹, R. Sivagami ¹, K. Joseph Abraham Sundar ¹, K. Divyalakshmi ¹, V. Sangeetha ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur – 613401, Tamil Nadu, IN

Abstract

Image fusion, the process of combining multi-modal or multi-focus images to form a new informative image than input images. The fused image contains more information than their input images which helps remote sensing applications for image analysis efficiently. Many image fusion algorithms have been developed, but all of them introduced a term called as color distortion. The huge difference between the intensity of input images leads to the color distortion. The Intensity-Hue-Saturation fusion technique gives more access to the user to work on pixel by pixel. This method accessibility delivers the good fusion technique base to reduce the color distortion. We proposed an algorithm which solves the color distortion problem effectively and it can produce an output image as highly informative. The difference in intensity of input images reduced by injecting the intensity of the high resolution image. The proposed work performs better than existing algorithms and it is proved by statistical measures like a correlation coefficient, mean, standard deviation, ERGAS, UIQI and spectral angle mapper.

Keywords

Color Distortion, Enhancement, IIHS Transform, Image Fusion, Spatial Injection

Full Text

   

B. Karthikeyan ¹, M. Rajasekhar Reddy ¹, V. Vaithiyanathan ¹, D. Kannan ¹, A. C. Kosaraju ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur- 613401, IN

Abstract

Objectives: This paper proposes a new method to enhance security for data hiding in radiographic images through distortion of original data. Method: The process involves applying a Burrows-Wheeler Transform (BWT) to the original data, which groups and stores similar patterns in data, causing distortion. This distorted data is then further encoded in a safe format before hiding it in the cover image. The decoding process decoding from the safe format and applying Inverse Burrows-Wheeler Transform (IBWT) to retrieve the original data from the stego image. Findings: Thus, a 2-level security scheme is implemented. Cryptanalysis of the hidden data becomes difficult since the original data is distorted, thus enhancing the security of the hidden data. Nevertheless, the stego image obtained from this method is less deviated from the original cover image. This is shown from the satisfactory PSNR (Peak Signal to Noise Ratio) and MSE (Mean Square Error) obtained. Application/Improvements: This proposed method can be used wherever steganography or data hiding has its applications. This method can be used in commercial communication, military communication etc.

Keywords

Burrows-Wheeler Transform (BWT), Data Hiding, Inverse Burrows-Wheeler Transform (IBWT), Least Significant Bit (LSB), Radiographic Images, Steganography.

Full Text

   

Saikiran Sudhakar ¹, K. Hari Haran ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

SRAMs are important building blocks in many digital applications, such as microprocessors and cache memories. Decoders are the significant components in SRAMs. Address decoder is vital part of SRAM memory. Choice of capacity cell and read operation is relies on upon decoder. Henceforth, execution of SRAM is relies on upon these parts. This work studies the location decoder for SRAM memory, focusing on deferral streamlining and control effective circuit systems. We have focused on ideal decoder structure with slightest number of transistors to diminish range of SRAM. Usually, in Memory Chip, it consumes almost fifty percent of the total chip access time and power. Parameters which has to be considered while designing an address decoders are, first appropriate circuit technique has to be chosen and the second thing is sizing constrains of the transistors. Modified hybrid type of decoding topology is illustrated and it is compared with traditional type decoders which include both static and dynamic types using 180 nm CMOS technology in Cadence Virtuoso environment.

Keywords

Buffer Control, Cadence and Power Consumption, SRAM, Static Decoder.

Full Text

   

M. Indumathi ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Tirumalaisamudram, Thanjavur – 613401, Tamilnadu, IN

Abstract

Objectives: We proposed a Maximum Utility Growth (MUG) algorithm and Maximum Item Quantity (MIQ) Tree structure is used to decrease the number of candidates and reduce the candidate Itemset. Methods: In high utility Itemset mining profit and quantity of items are important in transaction. Several algorithms have proposed to solve the issues of large number of candidate Itemset generation. The proposed MUG algorithm and MIQ-Tree structure is used to reduce candidate Itemset and overestimated utilities in incremental mining. Moreover, the MUG with second strategy of approach calculates maximum utility of each expanded Itemset from the current prefix with supports in mining process. Finding: MUG algorithm and MIQ-Tree are proposed for mining high utility itemset to reduce the overestimated utility and it proposed two strategies for pruning candidate item sets efficiently in the process. It reduces the number of candidate and improves the performance of incremental mining. MIQ-Tree proposed to construct the tree with single-pass. The tree structure can restricted without new database and it employs decreasing the overestimated utility. MUG proposed to prune the number of candidate itemset with two strategies (I) Pruning 1-Itemset Candidates with Real Item Utilities and (II) Pruning Candidates with Estimated Maximum Itemset Utility. The experimental shows that the method developed the performance by decreasing number of candidate itemset. Performance evaluation shows that it reduces the number of candidate and its runtime with equal usage memory. Through the strategy, it can effectively eliminate the search space in the process. Applications: There is large amount of real world application such as retail marketing and stock marketing has emerged techniques high utility Itemset mining.

Keywords

Candidate Pruning, Data Mining, High Utility Itemset, Incremental Mining, Single Pass Tree Construction.

Full Text

   

A. Mathalane Mariamma ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Tirumalaisamudram, Thanjavur – 613401, Tamilnadu, IN

Abstract

Objectives: Cognition-driven activity recognition is a very challenging study domain. There are two main approaches to enhance activity modelings such as context knowledge and sensor dataset. Methods: The existing system used cognition- driven tool to annotate sensor activity dataset. It used Semantic Activity Annotation algorithm to annotate dataset. This produced perfect and wrong activity paradigm. It does not found frequent activity sequences. Findings: A novel technique is used to enhance cognition-driven activity paradigm by using the data-driven method. The methodology consists of clustering activity where basic partial activity models established through management technologies. By using this find out action cluster that denotes activities and accumulates recent actions. A learning activity is next formed to study and designing alternating methods of activities after obtain new finalize and specialized activity paradigms. This can be tested with sensor dataset and sensor dataset with noisy. Applications: It is mainly applicable for home-based rehabilitation, monitoring human activity and security-based applications.

Keywords

Activity Recognition, Activity Paradigm, Cognition-Driven, Data-Driven.

Full Text

   

K. Divya Lakshmi ¹, V. Vaithiyanathan ¹

Affiliations
1 School of Computing, SASTRA University, Thirumalaisamudram, Thanjavur - 613401, Tamil Nadu, IN

Abstract

Image registration is an important preprocessing step for computer vision tasks such as object recognition by a robot or change detection over a natural terrain from satellite images. This paper discusses the basic steps for the feature based image registration, and surveys the various methodologies from literature applicable for each step. The evolution of algorithms on image features is explained with some of their mathematical concepts, along with their limitations. Two videos captured from an unmanned aerial vehicle were used for experimentation. The performance of intensity based image registration using normalized cross correlation and Speeded Up Robust Features was observed by registering various frames of the videos. Intensity based methods perform well for all type of images when the images to be registered vary by only a translation. Feature based methods are suitable when the possible transformation between the images are unknown. Feature based methods fail when the images lack distinct features such as corner points. The study presented would enable one to choose the right methodology for each step of the image registration algorithm, for various real time computer vision applications such as navigation of unmanned aerial vehicles.

Keywords

Image Matching, Image Registration, Local Features, Registration Algorithms, UAV Navigation.

Full Text

   

V. Vaithiyanathan ¹, V. Balasubramanian ¹, S. Malarvizhi ¹, Vijay Petley ², Shweta Verma ²

Affiliations
1 Centre for Materials Joining & Research (CEMAJOR), Dept. of Mfg. Engg., Annamalai University, Annamalai Nagar, Tamilnadu, IN
2 Materials Group (MTG) Gas Turbine Research Establishment (GTRE), Bengaluru, IN

Abstract

Titanium and its alloys have been considered as one of the best engineering materials for aero-engine applications, because they possess many good characteristics such as high specific strength, superior corrosion resistance and good high temperature strength. Gas tungsten arc welding (GTAW) welding process is generally preferred because to repair aero-engine blades of its high versatility and easy applicability. Gas Tungsten Constricted Arc welding (GTCAW) is a new variant of GTAW process. It generates very high frequency (20 kHz) and alters the magnetic field of the arc, thus enabling the control of constriction of arc and leading to less heat input, narrow heat affected zone (HAZ), reduced residual stresses and distortion compared to conventional GTAW process. This paper reports the tensile properties of GTA and GTCA welded thin sheets (1.2 mm) of Ti-6Al-4V alloy used in aero-engine applications. The joints were characterized using optical microscopy, scanning electron microscopy and microhardness survey. From this investigation, it is found that GTCAW joints exhibited superior tensile properties compared to GTAW joints due to reduction of prior beta grain boundary, higher fusion zone hardness and narrow heat affected zone. Hence, it is preferred that GTCAW process can be employed to repair aero-engine components over GTAW process.

Keywords

Titanium Alloy, Gas Tungsten Arc Welding, Gas Tungsten Constricted Arc Welding, Tensile Properties, Microstructure.

Full Text