<p>There is no doubt that car parking is a very challenging and interesting topic of surveillance. In the recent years, a lot of smart systems for parking lot access control were developed to control and register the car data. The aim of this paper is to use image processing methods to control the entrance of a smart parking. The steps of car plate recognition are: preprocessing, License plate detection, character extraction and recognition. In the step of preprocessing, image was enhanced and noise was reduced. After preprocessing stage, color filter was used to detect the plate region. In case of large image size DWT was used for feature extraction and decreased the time of the detection stage. In the stage of character segmentation, the image is converted from grayscale to binary according to a given threshold. Filtering the binary image after using the morphological operation method, the largest objects are determined as the segmented plate characters. Finally, the correlation method was used to recognize the segmented characters. In case of similarity, SVM was used as a good classifier. Experimental results using matlab software, view that the proposed method increase the plate detection and recognition rates. It achieved aver- age 97.8% detection rate, 98% segmentation rate and 97% recognition rate, So it will be a good method for smart parking entrance control.</p>

<span>Due to the increase in number of cars and slow city developments, there is a need for smart parking system. One of the main issues in smart parking systems is parking lot occupancy status classification, so this paper introduce two methods for parking lot classification. The first method uses the mean, after converting the colored image to grayscale, then to black/white. If the mean is greater than a given threshold it is classified as occupied, otherwise it is empty. This method gave 90% correct classification rate on cnrall database. It overcome the alexnet deep learning method trained and tested on the same database (the mean method has no training time). The second method, which depends on deep learning is a deep learning neural network consists of 11 layers, trained and tested on the same database. It gave 93% correct classification rate, when trained on cnrall and tested on the same database. As shown, this method overcome the alexnet deep learning and the mean methods on the same database. On the Pklot database the alexnet and our deep learning network have a close resutls, overcome <br /> the mean method (greater than 95%).</span>

The industrialization of the world, increase in population and mismanagement of the available parking space has resulted in parking problems. There is a need for an intelligent and reliable system which can be used for searching the unoccupied parking facility, to reduce the cost of leasing people and for better use of resources for car-park owners. This paper introduces an algorithm to increase the efficiency of the current smart-parking system. The main objective of this algorithm is helping users automatically to find an unoccupied parking lot with least cost based on a new performance metrics to calculate the parking cost. Considering the distance between the User and Parking, Distance between Parking and services area, Percent of free spaces in each car park and Cost of parking for a time t. Matlab software was used to compute the cost function and to save an optimal parking space upon a request by the user. The experimental results show that the proposed cost function helps improve the probability of optimal parking with least cost.