Firoj Parwej

Firoj Parwej

Handwriting is one of the most important means of daily communication. Although the problem of handwriting recognition has been considered for more than 60 years there are still many open issues, especially in the task of unconstrained handwritten sentence recognition. This paper focuses on the automatic system that recognizes continuous English sentence through a mouse-based gestures in real-time based on Artificial Neural Network. The proposed Artificial Neural Network is trained using the traditional backpropagation algorithm for self supervised neural network which provides the system with great learning ability and thus has proven highly successful in training for feed-forward Artificial Neural Network. The designed algorithm is not only capable of translating discrete gesture moves, but also continuous gestures through the mouse. In this paper we are using the efficient neural network approach for recognizing English sentence drawn by mouse. This approach shows an efficient way of extracting the boundary of the English Sentence and specifies the area of the recognition English sentence where it has been drawn in an image and then used Artificial Neural Network to recognize the English sentence. The proposed approach English sentence recognition (ESR) system is designed and tested successfully. Experimental results show that the higher speed and accuracy were examined.

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.