Seal identification and controlling method

Abstract

The invention discloses a seal identification control method, which comprises the following steps: collecting template seals: collecting images of seals to be identified into a database through a CCD or a scanner, storing them in a picture format as template seals; Text extraction: use the four operation steps of binarization, skeleton extraction, frame extraction and seal extraction to extract the seal to be recognized; seal registration: the seal registration operation is divided into two steps, rough registration and fine registration , the rough registration first adjusts the print to be recognized and the template to approximately the same position and orientation, and the fine registration further adjusts the two prints to almost the same position and orientation; seal identification: multi-level recognition is adopted The strategy and the multi-feature classification fusion decision-making method are used to identify the printed text to be recognized and the printed text of the template. The control method overcomes the shortcomings in the prior art, and can greatly improve the seal recognition reliability and recognition efficiency.

Description

technical field [0001] The invention relates to the technical field of seal identification, in particular to a seal identification system and a control method thereof. Background technique [0002] With the development of my country's market economy, almost everything is inseparable from the seal, and every item needs a seal. The seal participates in my country's political, economic and cultural life with its irreplaceable identity and credit function. However, in real life, due to the poor anti-counterfeiting performance of various seals in our country and the backward identification and supervision methods, we have been infested by counterfeit seals for a long time. It is these counterfeit seals that breed one after another fake contracts, fake bills, fake documents, and fake products, and breed one after another large and small cases of violations of regulations, disciplines, and even laws. According to data, among the tens of millions of cases of dishonesty, violation o...

AI Technical Summary

Problems solved by technology

However, the current computer recognition system has some difficulties that have not been effectively overcome: 1) the recognition accuracy is not high

Because the similarity between true and false seals is usually relatively high, and the existing systems usually use traditional pattern recognition and image processing methods, although some effects have been obtained, a wide and effective method has not been found. The basis for identifying true and false seals, or the characteristics of distinguishing between true and false seals, to accurately distinguish between counterfeit and legitimate seals with very subtle differences

2) There are many restrictions and poor adaptability

Due to the uneven force of people when stamping the seal, the incompleteness of the seal to be recognized due to the diversity and complexity of the background pattern, the inconsistency of the texture thickness and the background noise, the distortion of the seal extraction is caused by the recognition operation. It brings a lot of interference, and there is currently no method that can reduce these interferences to the lowest level in general, usually only under the conditions required by the identification method adopted by a certain system, can a relatively relatively good result

Therefore, the existing systems usually have more restrictions on the quality of the target image

3) Not easy to use

Many existing systems require users to manually register the stamps, and the problem with manual registration is that the stamp images cannot be aligned accurately, which will cause large errors in the final recognition results and reduce the number of workers. work efficiency

Chinese patent CN00104581.4 discloses a method for identifying the authenticity of a seal, including the following steps: a. setting a verification code composed of several characters on the seal; b. establishing a seal management database related to the seal with the verification code, and The database is connected to the Internet (or connected to the telephone system); c, the seal verification code corresponding to the verification code is set by the seal holder according to certain rules, and the verification code is input into the seal management database; d, by telephone (or computer) connects described seal management database, after inputting the verification code that wants to distinguish seal, input seal verification password to seal management database by the holder, and make judgment whether password matches verification code by seal management database; If the password matches the verification code, it can be judged that the seal is authentic and the holder is legal; otherwise, there may be problems with the authenticity of the seal and the legitimacy of the holder, which needs further verification

Therefore, the use of manual recognition will result in low efficiency and low recognition rate.

And the existing computer identification system is also more and more unsuitable for the needs of current seal identification because of the existence of various difficult problems that are difficult to overcome.

Images