Majlesi Journal of Multimedia Processing
Volume:2 Issue: 4, Dec 2013

The kinematic specification of hand movement has effective properties in diagnosis of neural-motional diseases such as schizophrenia, Parkinson, or emotional states. In this paper a device is presented which have the ability to extract such properties. It includes a resistance touch panel that is mounted on a color LCD. By drawing on the panel, information of hand movement could be extracted by ARM microprocessor and transferred to a computer for exact examination such as diseases recognition, through USB port with acceptable sampling rate. Then, accumulated data is recorded by the device microcontroller, and it displays hand movement at the same time on the LCD as an appropriate feedback for user and software. Using information processing modules and comparing them with normal situation, it could help treatment of special diseases or motional disabilities or training assistance objects for children.

Ventricular fibrillation is one of the most dangerous arrhythmia of the heart. Heart rate increases up to 450 times per minute in this disease, however, due to the fact that all the heart muscles are fluttering, and all the cells cannot contract an specific time, they cannot pump the blood from the heart to the arteries and veins. All the frequency and time signal factors are out of their normal conditions. I comparison to the previous method, this algorithm can improve recognizing the ventricular fibrillation using artificial neural networks that has been achieved by applying image forming process based on signals and time delayed signals intelligently.

This paper presents a novel image zooming technique using Partial Differential Equations (PDEs). The proposed method combines a denoising algorithm with the Locally Adaptive Zooming (LAZ) algorithm. The proposed method uses high-resolution image obtained from LAZ algorithm to construct zoomed image by diffusion coefficient. This proposed method preserves edges and minimizes blurring and staircase effects in the zoomed image. In order to evaluate image quality obtained from the proposed method, this paper focuses on both subjective and objective assessments. The results of these measures on a variety of images show that the proposed method is superior over the other image zooming methods.

In this paper an estimator for speech enhancement based on Laplacian Mixture Model has been proposed. The proposed method, estimates the complex DFT coefficients of clean speech from noisy speech using the MMSE estimator, when the clean speech DFT coefficients are supposed mixture of Laplacians and the DFT coefficients of noise are assumed zero-mean Gaussian distribution. For estimating the Laplacian Mixture model parameters, Expectation-Maximization algorithm is used.The segmental Signal to Noise Ratio, Log-Likelihood Ratio and Perceptual Evaluation of Speech Quality measures are used for objective evaluation of the proposed method. It is shown that the proposed estimator, in term of these objective measures, has better performance than two estimators based on single Gaussian and another estimator based on single Laplacian model.

With the advancement of technology and availability of imaging tools, it’s not difficult now to manipulate digital images, to hide or create misleading images. Image forgery detection is currently one of the hot research fields of image processing. Copy-Move tampering is a common type of image synthesizing, where a part of an image is copied and pasted to another place to add or remove an object. In this paper, we present an improved algorithm based on Discrete Wavelet Transform (DWT) and Discrete Cosine Transform Quantization Coefficients Decomposition (DCT-QCD) to detect such cloning forgery. Our technique works by first applying DWT to the input image to yield a reduced dimensional representation. Then the compressed image is divided into n×n overlapping blocks. Using Singular Value Decomposition (SVD) on cosine coefficients, the size of blocks is reduced from n×n to 1×n. Hence instead of compare the n×n blocks only compare of 1×n vectors is need. Since complexity of related algorithms is concerned to number of blocks, this approach drastically reduces the time needed for the detection process. Experimental results show that the proposed scheme accurately detects such specific image manipulations as long as the copied region is not rotated or scaled.

User verification systems, which use a biometric method, are most often forced to face with noisy data and unlimited error rates. In order to improve the implementation of specific adaptations and matches in such situations, combinatory or hybrid biometric systems are used. In this paper, we propose a hybrid biometric system by combining face and eye iris features that can considerably improve the identification systems’ performance by reducing the present problems and errors in the biometric systems using a single method. We combined the Cohn - Kanade facial database and the FVC fingerprint database to perform the required experiments. Then, we identified the specific individuals, and evaluated the performance of the proposed system. The results showed that the proposed hybrid biometric system is highly more reliable and more accurate than the systems using a single biometric method, and are very appropriate to be used in immediate detection systems due to its high speed in detection.