Yusuf Perwej

Yusuf Perwej

The recognition of unconstrained handwriting continues to be a difficult task for computers despite active research for several decades. This is because handwritten text offers great challenges such as character and word segmentation, character recognition, variation between handwriting styles, different character size and no font constraints as well as the background clarity. In this paper primarily discussed Online Handwriting Recognition methods for Arabic words which being often used among then across the Middle East and North Africa people. Because of the characteristic of the whole body of the Arabic words, namely connectivity between the characters, thereby the segmentation of An Arabic word is very difficult. We introduced a recurrent neural network to online handwriting Arabic word recognition. The key innovation is a recently produce recurrent neural networks objective function known as connectionist temporal classification. The system consists of an advanced recurrent neural network with an output layer designed for sequence labeling, partially combined with a probabilistic language model. Experimental results show that unconstrained Arabic words achieve recognition rates about 79%, which is significantly higher than the about 70% using a previously developed hidden markov model based recognition system.

Yusuf Perwej, Ashish Chaturvedi

This paper demonstrates the use of neural networks for developing a system that can recognize hand-written English alphabets. In this system, each English alphabet is represented by binary values that are used as input to a simple feature extraction system, whose output is fed to our neural network system.

Yusuf Perwej, Ashish Chaturvedi

Even today in Twenty First Century Handwritten communication has its own stand and most of the times, in daily life it is globally using as means of communication and recording the information like to be shared with others. Challenges in handwritten characters recognition wholly lie in the variation and distortion of handwritten characters, since different people may use different style of handwriting, and direction to draw the same shape of the characters of their known script. This paper demonstrates the nature of handwritten characters, conversion of handwritten data into electronic data, and the neural network approach to make machine capable of recognizing hand written characters.

Yusuf Perwej, Firoj Parwej, Asif Perwej

The Internet as a whole does not use secure links, thus information in transit may be vulnerable to interruption as well. The important of reducing a chance of the information being detected during the transmission is being an issue in the real world now days. The Digital watermarking method provides for the quick and inexpensive distribution of digital information over the Internet. This method provides new ways of ensuring the sufficient protection of copyright holders in the intellectual property dispersion process. The property of digital watermarking images allows insertion of additional data in the image without altering the value of the image.In this paper investigate the following relevant concepts and terminology, history of watermarks and the properties of a watermarking system and applications. We are proposing edge detection using Gabor Filters. In this paper we are proposed least significant bit (LSB) substitution method to encrypt the message in the watermark image file. The benefits of the LSB are its simplicity to embed the bits of the message directly into the LSB plane of cover-image and many techniques using these methods. The LSB does not result in a human perceptible difference because the amplitude of the change is little therefore the human eye the resulting stego image will look identical to the cover image and this allows high perceptual transparency of the LSB. The spatial domain technique LSB substitution it would be able to use a pseudo-random number generator to determine the pixels to be used for embedding based on a given key. We are using DCT transform watermark algorithms based on robustness. The watermarking robustness have been calculated by the Peak Signal to Noise Ratio (PSNR) and Normalized cross correlation (NC) is used to quantify by the similarity between the real watermark and after extracting watermark.

Yusuf Perwej, Asif Perwej

A large part of the workforce, and growing every day, is originally from India. India one of the second largest populations in the world, they have a lot to offer in terms of jobs. The sheer number of IT workers makes them a formidable travelling force as well, easily picking up employment in English speaking countries. The beginning of the economic crises since 2008 September, many Indians have return homeland, and this has had a substantial impression on the Indian Rupee (INR) as liken to the US Dollar (USD). We are using numerational knowledge based techniques for forecasting has been proved highly successful in present time. The purpose of this paper is to examine the effects of several important neural network factors on model fitting and forecasting the behaviours. In this paper, Artificial Neural Network has successfully been used for exchange rate forecasting. This paper examines the effects of the number of inputs and hidden nodes and the size of the training sample on the in-sample and out-of-sample performance. The Indian Rupee (INR) / US Dollar (USD) is used for detailed examinations. The number of input nodes has a greater impact on performance than the number of hidden nodes, while a large number of observations do reduce forecast errors.