Vehiclenumber plate recognition has been an ongoing innovative research for over thelast few years. Many researches have been carried out to identify the differenttype of vehicle such as a truck, car, bus or any four wheeler vehicle. In paper14, the soble filter algorithm was used to address this issue to get theedges of the vehicle which is applied to detect and recognize the type ofvehicle. The model of 11 the vehiclefind out through in the use of SVM (Support Vector Machine) and contourletTransform.
They showed many numerical results on data set of pictures. However,they could not be applied the any technique to real-time capture of videostream 2. In the paper 16 monocular images technique are used for carrecognition. They applied canny edge detection for detect edges to detect thepresence of vehicle and their number plate and SVM classifier to recognize thevehicle number classification.
In paper 12, recognition of the type ofvehicle irrespective of scale, size and rotation variation of vehicles numberplate where 7 we applied the filter, MACH filter and Log r-theta Mappingtechniques. In paper 18, OCRtechniques was used 5, which is a commonly used technology for opticalcharacter recognition, which is used for translation of scanned images ofprinted text into format of machine encoded text. Basically an OCR technique isbased on neural network fee-forward system.
This is proposed for where two realcharacter images, which is no-overlapping to each other, sets of data uses fortraining and training using neural network technology. ANN based neural networksystem used for pattern recognition. ANN generally used feed-forward neuralnetwork based intelligent computing architecture, which can be classify the inputsinto a set of target categories.
Neural network done work well and can achievebetter performance to other even the size and color of number plate bedifferent it is also work under in the difficult environment. I. SystemapproachThe proposedsystem contains various stages as image acquisition, pre-processing, numberplate localization, character segmentation, character recognition. The systemis designed in Matlab based GUI application.
A. Car ImageCaptured By CameraArduino Unoattached with the motion sensor which detect the motion of car. Then the motorhelps to rotate the camera for capturing the car images from real time videos2. We use the high resolution picture quality camera for image acquisition,identified is captured using high resolution digital camera. B. PreprocessingFirstly, weconvert the input RGB color image to a gray-scale images. To speed up theprocess, the image is first downscaled to 50% of the original.
Here mathematical morphology 6is used to detect the plate region and the sobel operator are used forcalculation of the threshold value. After this system we will get a dilatedimage. Then we use imfill function for fill the holes, so that we can get aclear binary image. Figure 2: A GUI layoutSystem overview of Indian Number Plate Recognition System C.
IndianNumber plate LocalizationPre-processing isthe important technique to filtering and edges detection. The image ispre-processed, passing through gray scale filter and edge detection method isapplied. Which applied to the isolate of the plate region of interest.Localization 1, 4 is an algorithmic function for identifying a numberplate. By the use of localizing determines the aspect ratio of number plate ofvehicle image.
Thisalgorithm search the similar background coloursof the image unified proportion and mean contrastdifferentiate number plate objects on a vehicle. (i) Edge DetectionThere are manymethods of which performing edge detection of image. We detected the edges ofinput image 6, here we using canny edge detector which used to takes agray-scale image as its input of this system, and then returns a binary imageof same size 11 as an output image, where the edge detection function findsthe edges in the input gray image. (ii) CharacterSegmentationIn the identifiednumber plate region where character are segmented using function ofregion-props of Matlab, It is use to find the boxes bounding for eachcharacters. This function returns the smallest bounding box, which 13contains a character. So, we can use this method for obtain the bounding boxesof all character in vehicle number plate.
D. CharacterRecognition Template matchingis a technique of character recognition. It is method of finding the fixedlocation of a template (sub-image), which inside of captured image. Template matching having similarities 12between a given template image and windows with same size in an image and thatidentifying the window, that produces highest similarity measure. It works withpixel-by-pixel comparison and each possible pixel displacement of the templateimage.
E. Identify theStolen CarThe main purposeof this state that recognize and classification of binary images that havecontains character which is received by previous stage. After doing this stageeach character must have a valid label and having an error factor. If thiserror factor is greater than a predefined data value will be used for rejectthe false characters which passed from previous one.
For the time ofclassification step some features must have collected data from the characters.This is use for because image to text into characters conversion. In number plate each individualcharacter match from the completer alphanumeric database using templatematching method. The matching process is checked the template image to allpossible positions in a input larger image and computes a particular numericalindex which indicate that how the template is matches and what quality ofmatches the image in that position. After template is matched we havinga valid vehicle number which is matches from the database of excel sheetautomatically.
If the stolen vehicle is detect then the alert system will be on.We can be recognize data using the internet. We store stolen vehicle databasein online database and connect to Matlab java connecter.