Download Project Document/Synopsis
Here we come up with an innovative system where characters are extracted from input number plate image. We used many image preprocessing steps in order to extract only text from number plate image. Since images are more susceptible to noise and with many other unwanted objects. Noise is removed from image using effective noise removal method. Before image preprocessing steps, RGB image is converted to gray scale image and image is resized keeping aspect ratio same. Morphological processing is used which helps to detect text more accurately. Image is converted to double. Edge detection method is used to detect edges and image intensity level is increased. Objects which have gaps are filled. After Edge detection , image might contain many horizontal and vertical lines. These lines should be removed from image which helps to extract only text from image. After applying these image preprocessing steps , image is left with few smaller unwanted objects. These unwanted objects are removed. Bounding boxes is applied to text extracted. These text are in image format. These images are converted to characters. System uses optical character recognition to extract characters from image. Character and number images are stored in directory. The extracted text image are separated by bounding box. Each bounding box will contain each character or number. Each character or number is resized to image stored in directory. Extracted image and existing character image feature is compared. After comparison characters are detected. Finally detected characters are shown in text format.
- OCR method detects text more accurately.
- Used many image pre-processing steps to remove noise and unwanted objects.
- Problem while detecting characters with similar features