Study of the automatic reading of watt meter based on image processing technology

At present, the electromagnetic waft meter is still widely used in china, the workers from the electricity board have to collect electric data from door to door through manual reading, so that there is a great shortage of real-time, accurate, and evidence demonstrative reading. This practice is also manpower consuming and energy consuming, with high cost and low efficiency. Automatic meter reading has effectively overcome the low efficiency and inaccuracy in manual reading. In the present automatic meter reading system, electric impulse counting is adopted for automatic electric computation, that is, the electric impulse put out by the watt meter is counted and accumulated to obtain digital information about electricity. This method, however, can easily lead to the loss of the counting impulses, or lead to multi-counting impulses, which may lead to wrong counting. In this paper, an automatic watt meter reading system has been described. A video camera fixed in front of the watt meter will take real time pictures of the reading on the watt meter. The digits shown on the waft meter will be recognized by means of image segmentation and character recognition so that the reading will be real time, with high efficiency, and small errors.