Compressive Sensing (CS) shows high promise for fully distributed
compression in wireless sensor networks (WSNs). In theory, CS
allows the approximation of the readings from a sensor field with
excellent accuracy, while collecting only a small fra
ction of them at
a data gathering point. However, the conditions under which CS
performs well are not necessarily met in practice. CS requires a
suitable transformation that makes the signal sparse in its domain.
Also, the transformation of the data given by the routing protocol
and network topology and the sparse representation of the signal
have to be incoherent, which is not straightforward to achieve in
real networks. In this paper we investigated the effectiveness of
data recovery through joint Compressive Sensing (CS) and
Principal Component Analysis (PCA) in actual WSN deployments.
We proposed a novel system, called CS-PCA that embeds a
feedback control mechanism to automatically change the
compression ratio through changing the number of transmitting
sensors, while bounding the reconstruction error. The considered
recovery techniques in the proposed system are: biharmonic Spline
(Spline), Deterministic Ordinary Least Square (DOLS),
Probabilistic Ordinary Least Square (POLS) and Joint CS and PCA
(CS-PCA). We found that the later outperform all other
interpolation technique in the case of slow varying signals, while
POLS was the most effective in case of fast varying signals that(
low correlation less than 0.45)
The Automatic recognition System to vehicles through its number is an important topic, because of its important uses, such as security applications by monitoring the entrances of a important institutions, monitor the vehicles on the road, detection o
f stolen cars, and even that could be useful in statistical studies, where we can study the traffic congestion in an area. In this work we offer an overview of the Automatic Number Plate Recognition System (ANPR) through to identify the license plate number, and also recognize the color of car.
The focus of this research on the stage of converting the numbers into a picture of a car plate to actual figures, to improve the performance of all system, where many of errors that occur at this stage.
In this search was used the algorithm of Principle component
analysis (PCA) to identify the numbers plate inside the picture.
and its integration with optical character Recognition
algorithm(OCR) which usually used for recognition , to minimize
errors in recognition numbers and thus improve the performance of the automatic number plate system.and also we add color car recognize(which another important parameter of car) , this helps after return to data base detect stolen vehicles and improve the reliability of system
A new face detection system is presented. The system combines several techniques for face detection to achieve better detection rates, a skin colormodel based on RGB color space is built and used to detect skin regions. The detected skin regions are
the face candidate regions. Neural network is used and trained with training set of faces and non-faces that projected into subspace by principal component analysis technique. we have added two modifications for the classical use of neural networks in face detection. First, the neural network tests only the face candidate regions for faces, so the search space is reduced. Second, the window size used by the neural network in scanning the input image is adaptive and depends on the size of the face candidate region. This enables the face detection system to detect faces with any size.
The basic step in this algori thm is determining the number of clusters
(K) then calculating the distance between each cluster
center and the elements of images to join each element
to the closest cluster depending on threshold distance.