Search

An image may suffer from some degradation such as blurriness. This degradation affects the image contrast. There are various approaches to improve the contrast of the images. Among these approaches, un-sharp masking is a popular method due to its simplicity in implementation and computation. In the un-sharp masking method, the details of the input image are boosted to improve the image quality. In this method, the quality of the enhanced image directly depends on the parameter named gain factor. Since the quality of an image may not be the same throughout the image, in this paper we propose an adaptive un-sharp masking method to locally improve the quality of the images. In this method, at first, the input image is divided into a number of overlapping blocks. Then the appropriate gain factor is estimated for the pixels of each block using the gradient information of the block. Subjective and objective image quality assessments are used to compare the performance of the proposed method with both the classic and the recently developed un-sharp masking methods. The experimental results show that the proposed method has a better performance in comparison to the other existing methods.

Background/Objectives: The sunlight heats up closed area which is free of air and in close contact with sun much faster and significantly. This project is used to reduce the very high temperatures present inside the vehicles to feel very comfortable. Methods/Statistical Analysis: This paper proposes a CAN based module for self-regulated inside ventilation of vehicles to reduce the high temperatures presented inside the vehicles in summer. Two microcontrollers and a group of sensors which facilitate efficient, reliable, safe ventilation and sufficient data to ensure functional are used by this project. The communication using CAN bus is established between two ARM controllers. By changing the windows of the vehicle to open position, the ventilation process is performed. The position of the windows is controlled by the controller itself and without presence of driver using an algorithm that gives the details of sensors. Findings: The movements observed near the vehicle, precipitation and others have importance besides temperature for the ventilation. The results of the tests give usefulness and the modules utilization, the windows of the vehicle is closed when the temperature inside the vehicle achieves more than comfortable temperature and if any fire accidents, thefting of vehicle occurs then the location of the vehicle is sent to the user. Application/Improvements: The system provides comfortability to the users with a low cost. It saves the fuel by reducing the usage of AC. This system can be used in home and own vehicles, cabs, and transport business.

value of its individual pixels. Most of existing gamma correction methods apply a uniform gamma value across the image. Considering the fact that gamma variation for a single image is actually nonlinear, the proposed method locally estimates the gamma values in an image database of training images are constructed from various standard images under different gamma conditions. Then by windowing each of the training images, a number of features that characterize images content are computed from its pixel intensity histogram, gray level co-occurrence matrix, and discrete cosine transform domain. To improve the gamma values of an image the aforementioned features are initially computed in sliding windows, then SVM is employed to estimate the gamma value in each window. In this study, it is shown that the proposed method has performed well in improving the quality of images. Subjective and objective image quality assessments used in this study attest superiority of the proposed method compared to the existing methods in image quality enhancement using image gamma value.

The main objective of the study is to evaluate the physical characteristics and the natural resources in the study area and to develop methods for its efficient utilization and sustainable management using tools such as remote sensing and GIS. The thematic layers are derived from IRS-ID PAN + LISS-III merged satellite imagery and survey of India (SOI) topo maps using visual interpretation technique. These maps are converted to digital format using AutoCAD software and further integrated using Arc/Info and Arc view GIS software for the generation of final outputs. Physical characterization helps for quality of environment and natural resources development, which are optimally suitable to the terrain and to the development of water resources. The physical characterization of an area is also useful to plan the basic minimum needs of farmers, thereby improving their socio-economic conditions and helps in evolving a broad national policy which can be applied by decision makers for sustainable development of any given study area. This case study would help in developing municipalities with details at micro level for further planning.

In this paper we used Independent Component Analysis (ICA) model of EEG signals for preprocessing and then Discrete Wavelet Transform (DWT) analysis for feature extraction from EEG signal which this features are useful in BCI application. Then we used Fuzzy C-means (FCM) algorithm for recognition of some diseases like epileptic seizure, Cerebral Palsy (CP), etc. This project can be divided in three parts. The first part is EEG signal preprocessing using ICA. The second part is the feature extraction of normal and abnormal EEG using feature vectors derived from the wavelet analysis. The third part is the classification of normal and abnormal signals using FCM algorithm. In section II we explain EEG signal preprocessing, in section III we describe feature extraction and in section IV we explain the classification

The advantages of magnetic resonance imaging (MRI) over other diagnostic image modalities are its high spatial resolution and excellent discrimination of soft tissues. Many neurological conditions alter the shape, volume, and distribution of brain tissue; MRI is the preferred imaging modality for examining these conditions which requires segmentation into different intensity classes which are regarded as the best available representations for biological tissues. There is a need for computer analysis of MRI such as precise delineation of tumors and reliable, reproducible segmentation of images. The aim of this work is to propose a FCM clustering algorithm basis neural network for MRI segmentation.

With development of information and communication technology, data transmission becomes more critical day by day. Higher security for transmitting data is especially required. Therefore; we designed a new method to transmit data on the phone line where there is no speech signal on it. Statistic investigations in one communication center in Iran show that there is about 57% non-speech signal on the phone line. Because a person on one side of the phone line speaks and then waits to hear the voice of the other person on the other side and, therefore; this non-speech signal has a good capacity for transmitting data. This project can be divided in four parts. The first part is the automatic classification of speech signal from non-speech using feature vectors derived from the wavelet analysis. The second part is the classification of speech and nonspeech signals using neural network. For recognizing this two cluster (speech signal and non-speech signal), we used NN. The third part is encrypting data and forth part is transmitting encrypted data on non-speech signal on the phone line.

With development of Information and Communication Technology, Data transmission becomes more critical day by day. Higher security for transmitting data is especially required. Therefore; we designed a new method to transmit data on the phone line where there is no speech signal on it. Statistic investigations in one communication center in Iran, show that there is about 57% non-speech signal on the phone line. Because a person on one side of the phone line speaks and then waits to hear the voice of the other person on the other side and, therefore; this non-speech signal has a good capacity for transmitting data. This project can be divided in three parts. The first part is to recognize speech signal from non-speech signal and canceling non-speech signal. The second part is encrypting data and third part is transmitting encrypted data on non-speech signal on the phone line.