Archive Browsing VOLUME 7 ISSUE 09 APRIL 2019

Automatic Number Plate Recognition System using Template Matching and Euclidian Distance
Abstract: In the present world, the increase in the use of vehicles and automobiles are very useful for our day to day life. For the identification and classification of different vehicles according to the owner, vehicle type and region where the vehicle is used, we use the number plate. By the increase in the number of vehicles, the law enforcement and classification of vehicles are a great challenge to the authority. So the use of automatic number plate recognition system has a very important role in the current scenario. There are several types of research and methods are used to implement the recognition of numbers from the images such as optical character recognition (OCR) etc. But by using those methods there are several limitations for the identification of numbers and also classification of numbers with the characters which are in the same shape. Here we use a new method for the number plate recognition which done by the template matching by calculating the Euclidian distance between the current input and the template. We are also done some morphological operations on the input number plate image. By using this method, we got an 85% accuracy in the local images that we took in number plates having different dimensions and different background colors.

Authors: Ali Askar K M, Unnikrishnan S Kumar

File Name: Ali_70700-19-104.pdf
 Download Abstract | Download Full Paper

Optimal Cluster Head Election using Cuckoo Search Algorithm
Abstract: This paper is based on indoor wireless sensor networks, in conjunction with an appropriate management methodology that allows us to analyse and verify the behaviour of these wireless networks in an internal way. To make WSN energy efficient and to increase the lifetime of the network, this paper presents an energy-efficient clustering algorithm optimized by Cuckoo Search Algorithm (CSA). Performance of this approach is evaluated using certain evaluation parameters; Throughput and Network Lifetime.

Authors: Pratik Gupta, Mrs. Madhvi Singh Bhanwar

File Name: Pratik_70500-18-101.pdf
 Download Abstract | Download Full Paper

Phishing URL Detection using PSO Optimized Support Vector Machine
Abstract: This paper aims to collect, map and model elements that will lead to the finding of phishing URL automatically, for this purpose data mining is used as basic tools, in this sense, it is considered that the existing patterns in a URL make it possible to distinguish the legitimate link for pages, the identification of these patterns will serve to model a successful classification method, for this purpose, the attributes found in the database "phishing web" that correspond to patterns of phishing pages will be validated, at the same time will be evaluated algorithms extracted from the literature that allow a better classification of records, finally, a model with the highest precision results is delivered which consists of particle swarm optimized support vector machine classifier.

Authors: Ankit Shrivastava, Dr. Sudhir Agrawal

File Name: Ankit_70900-19-101.pdf
 Download Abstract | Download Full Paper

Double Threshold Based Energy Detection for Spectrum Sensing in Cognitive Radio Networks
Abstract: Spectrum sensing plays an influential role in detecting white spaces present in the spectrum. So, the spectrum sensing algorithm will help the secondary user (SU) to detect spectrum holes precisely. Here energy detection (ED) spectrum sensing technique is used. Energy detection spectrum sensing with single threshold has been widely researched in the past. The interference between the primary user (PU) and secondary user (SU) was more in energy detection with a single threshold, therefore, the collision rate was much high. So, to minimize the collision rate and improve the probability of detection (P_d), this paper proposes a double threshold based energy detection spectrum sensing algorithm to increase the performance of cognitive radio networks. Simulation results validate the importance of research on the basis of the probability of detection (P_d), probability of miss detection (P_m), collision rate and signal-to-noise ratio.

Authors: Naveen Solanki, Mrs. Madhvi Singh Bhanwar

File Name: Naveen_70900-19-103.pdf
 Download Abstract | Download Full Paper

Fuzzy Logic based Clustering Approach in Heterogeneous and Homogeneous Wireless Sensor Networks

Authors: Satyaprakash Shikari, Pallavi Pahadiya

File Name: Satyaprakash_70900-19-104.pdf
 Download Abstract | Download Full Paper

Multimodal Biometric Recognition using Gabor Wavelet, Harris Corner and Random Forest Classifier
Abstract: Biometric recognition systems use certain human characteristics such as voice, facial features, fingerprint, iris or hand geometry to identify an individual or verify their identity. These systems have been developed individually for each of these biometric modalities until they achieve remarkable levels of performance. Multimodal biometric systems combine different modalities in a unique recognition system. The multimodal fusion allows to improve the results obtained by a single biometric characteristic and make the system more robust to noise and interference and more resistant to possible attacks. The fusion can be carried out at the level of the signals acquired by the different sensors, of the parameters obtained for each modality, of the scores provided by unimodal experts or of the decision taken by said experts. In the fusion at the level of parameters or scores it is necessary to homogenize the characteristics coming from the different biometric modalities prior to the fusion process. This paper presents the development of a multimodal biometric identification system based on two biometrics namely, the iris and the fingerprint. Feature extraction is done using Gabor Wavelet and Harris Corner Method and classification is accomplished using Random forest classifier

Authors: Prachi Agarwal, Pankaj Rathi

File Name: Prachi_70900-19-106.pdf
 Download Abstract | Download Full Paper

Improved Denoising using Local Adaptive Real Oriented Dual-Tree Wavelet
Abstract: Image Denoising is a subject of digital image processing, used to eliminate the noise in image that is corrupted in the process of acquisition, transmission, reception and storage. Denoising filters out noise from distorted image , while retaining the edges and other detailed features as fine as possible. AWGN is the most common noise which corrupts images in our daily life. In this research work, Local Adaptive Real Oriented Dual-Tree Wavelet Method and improved Denoising method are used to find out the denoised image. An improved denoising approach is based on Local Adaptive Wavelet Image Denoising in both spatial and transform domain. In this paper, we have estimated and compared performances of improved denoising method and the local adaptive real oriented dual-tree wavelet image denoising method. Performance evaluation of these methods are compared using peak signal to noise ratio (PSNR) and mean squared error (MSE) between the original image and noisy image and PSNR between the original image and denoised image. The result shows an improvement of 18.15% (avg.) in PSNR and MSE is decreased by 45.84% (avg.).

Authors: Ayush Kumar, Rupesh Dubey

File Name: Ayush_70900-19-105.pdf
 Download Abstract | Download Full Paper

© 2016 IJDACR Journal. All rights reserved.