Vehicle Parking Inventory System Utilizing Image Recognition through Artificial Neural Networks Leo S. Bartolome, Argel A. Bandala, Cesar Llorente, Elmer P. Dadios Electronics Engineering Department De La Salle University Abstract – An automated vehicle logging system is introduced in this paper. The system utilizes character recognition through images captured from the entrance of a parking area. These images are processed to extract the licensed plates of any vehicle entering the parking area. Extracted plates images are then converted into numerical forms devised by researchers to fit the requirements of the artificial neural network. From the numbered plate, each character is then extracted to produce their distinct features. Character recognition engine is primarily implemented using feed forward neural networks. There are 50 input neurons which are defined by resizing each character into 25x25 pixel image and summing all the pixel values in each row and each columns resulting to 50 sums. After which a numerical value will be produce and will signify a character equivalent. Characters are recognized separately. This process is done until all of the characters are recognized. Afterwards, these characters are then concatenated to produce the plate number identity. The system is trained using 5860 sets of training data yielding a system with 0.0001645724% error. Keywords-Artificial Neural Networks, Plate Number Recognition, Image Processing I. Introduction Many of the parking space establishments are using a manual inventory of different vehicles looking for a place where they can park. Apparently, doing it manually is cumbersome for small and big establishments that commonly leading to human errors affecting customers. Some of the common mistakes committed are typographical errors due to clarity of handwriting, customers not listed on the record, inaccurate time and date of customers, and indefinite list of vehicle legal owners. Having an automatic Vehicle Parking Inventory will lead the current system into a more organize, accurate and secured parking establishments that will both benefit the owner and the customer. Digital Image Processing (DIP) and Artificial Neural Network (ANN) has been studied for more than 200 applications [1] where there have been discussions of the present and possible future role of neural networks, especially feed- forward neural networks[2]. A method used in character recognition both for printed [3] and plate number [4] resulted into good detection rate but poor recognition. In this regard, the author proposed a new system of detecting and recognizing licensed plates of vehicles in the Philippines parking establishments with an improve performance of recognition rate. Utilizing Digital Image Processing and Artificial Neural Network a system for automatic vehicle inventory is proposed to address common mistakes committed from parking establishments. II. System Architecture Plate Number Extraction Image Processing Neural Networks Interpretation Figure 1. General Block Diagram of the System