Generation of a FIR Filter by Means of a Neural Network for Improvement of the Digital Images Obtained Using the Acquisition Equipment Based on the Low Quality CCD Structurecture

The paper features the method of application of a neural network for improving the quality of the digital images generated by means of devices for backup and processing of data into a digital form which construction is based on the Charge Coupled Device (CCD) structure. In order to introduce the problem, the digital images were generated by means of two scanners (including a high class and a low class scanner) and afterwards the images were subject to an objective and a subjective evaluation. An objective evaluation was performed using two quality criteria, i.e. MSE (Mean Square Error) and Universal Image Quality Index. A FIR (Finite Impulse Response) filter applied for filtration of a low quality image was obtained as the result of the neural network learning process. The image so generated as the result of filtration features a superior quality in comparison to the original.