Gaurav Kumar

A Detailed Review of Feature Extraction in Image Processing Systems

Feature plays a very important role in the area of image processing. Before getting features, various image preprocessing techniques like binarization, thresholding, resizing, normalization etc. are applied on the sampled image. After that, feature extraction techniques are applied to get features that will be useful in classifying and recognition of images. Feature extraction techniques are helpful in various image processing applications e.g. character recognition. As features define the behavior of an image, they show its place in terms of storage taken, efficiency in classification and obviously in time consumption also. Here in this paper, we are going to discuss various types of features, feature extraction techniques and explaining in what scenario, which features extraction technique, will be better. Hereby in this paper, we are going to refer features and feature extraction methods in case of character recognition application.

Neural Network based Approach for Recognition of Text Images

Handwritten character recognition is a difficult problem due to the great variations of writing styles, different size of the characters. Multiple types of handwriting styles from different persons are considered in this work. An image with higher resolution will certainly take much longer time to compute than a lower resolution image. In the practical image acquisition systems and conditions, shape distortion is common processes because different people’s handwriting has different shape of characters. The process of recognizing character recognition in this work has been divided into 2 phases. In the first phase, Image preprocessing is done in which image is firstly converted into binary form based on some threshold value obtained through Otsu’s method. After that removal of noise is done using median filter. After that feature extraction takes place that is done here through Fourier descriptor method using Fourier transform and correlation between template made through training data and test data is obtained. A multilayer feed forward neural network is created and trained through Back Propagation algorithm. After the training, testing is done to match the pattern with test data. Results for various convergence objective of neural network are obtained and analyzed.

Artificial neural network based intelligent model for wind power assessment in India

Wind resource assessment is essential to evaluate the future wind power generation from a wind farm. As wind power generation depends directly on wind speed, therefore accurate wind speed prediction facilitates wind power generation. In this paper generalized regression neural network is employed for accurate wind speed prediction. The performance of proposed approach is evaluated using publically available dataset of different cities in India. Air temperature, earth temperature, relative humidity, daily solar radiation, elevation, latitude, heating degree days, cooling degree days, longitude and atmospheric pressure are used as input variables. Correlation coefficient of 0.99909 is obtained during training and 0.95143 during testing of GRNN model. The proposed GRNN model is then utilized to find wind speed and power potential of major wind power generating sites of Andhra Pradesh, India. A comparison between the measured and forecasted wind speed and power values validate that generalized regression neural network is an appropriate technique for long term wind speed and power prediction.

Application of waikato environment for knowledge analysis based artificial neural network models for wind speed forecasting

The installation of wind turbine in a particular location in India is based on the wind speed prediction. The wind speed can be predicted using different models. The maximum temperature, average temperature, minimum temperature, ambient temperature, dew-point temperature, atmospheric pressure, air pressure, vapor pressure, solar radiation, altitude, longitude, wind direction, mean sea level, relative humidity, time of the day, water vapor, wind power are the input variables to the artificial neural network (ANN) model which affects the accuracy of the wind speed prediction. Therefore, the selection of the most relevant input variables to the ANN model is necessary. With this objective, InfoGain Attribute Evaluator with Ranker Search Method using WEKA (a data mining implementation) is applied to find the most relevant input variables. Identified 8 relevant input variables are used as input to ANN model to predict the wind speed. The results obtained validates that the combination of input variables selected through InfoGain Attribute Evaluator gives higher prediction accuracy than any other combination of input variables. This method is used to predict the wind speed of wind turbine in Rajasthan, north-west region of India.

Automation of Software Cost Estimation using Neural Network Technique

ABSTRACT  Software cost estimation is one of the most challenging tasks in software engineering. Over the past years the estimators have used parametric cost estimation models to establish software cost, however the challenges to accurate cost estimation keep evolving with the advancing technology. A detailed review of various cost estimation methods developed so far is presented in this paper. Planned effort and actual effort has been comparison in detail through applying on NASA projects. This paper uses Back-Propagation neural networks for software cost estimation. A model based on Neural Network has been proposed that takes KLOC of the project as input, uses COCOMO model parameters and gives effort as output. Artificial Neural Network represents a complex set of relationship between the effort and the cost drivers and is a potential tool for estimation. The proposed model automates the software cost estimation task and helps project manager to provide fast and realistic estimate for the project effort and development time that in turn gives software cost.

Phoneme Transcription by a Support Vector Machine

In this paper a support vector machine program is developed that is trained to transcribe Norwegian text to phonemes. The database consists of about 50,000 Norwegian words and is developed by the Norwegian Telecom Research Centre. The transcription regime used is based on SAMPA for Norwegian. The performance of the system has been tested on about 10,000 unknown words.

Intuitionistic Fuzzy Weighted Linear Regression Model with Fuzzy Entropy under Linear Restrictions

In fuzzy set theory, it is well known that a triangular fuzzy number can be uniquely determined through its position and entropies. In the present communication, we extend this concept on triangular intuitionistic fuzzy number for its one-to-one correspondence with its position and entropies. Using the concept of fuzzy entropy the estimators of the intuitionistic fuzzy regression coefficients have been estimated in the unrestricted regression model. An intuitionistic fuzzy weighted linear regression (IFWLR) model with some restrictions in the form of prior information has been considered. Further, the estimators of regression coefficients have been obtained with the help of fuzzy entropy for the restricted/unrestricted IFWLR model by assigning some weights in the distance function.

Improved Arbitrary Size Benes Network

interconnection networks (MINs) are used to connect N inputs to N outputs. They are mainly used to connect processor to processor and for processor to memory in distributed and shared memory environment. The MINs are broadly divided into three categories Blocking Non Blocking and Rearrangeable networks. A new improved Arbitrary size Benes network has been proposed in this to improve the permutation capabilities and to reduce the cost of existing Arbitrary Size Benes Network.