| With the development of Electronic Commercial Affairs and Electronic Government Affairs, informatization changes our life day by day. Although biometrics and electronic seal has been used in many areas, seal still plays an important role in oriental countries as the symbol of the individual, enterprise, social party, government and even the whole country in the law.In the seal verification, the old manual method of seal verification is discovered with many defects. Its correction is restricted by the subject factors and many kinds of subject conditions. Also its efficiency is low. Thus, the research of the automatic seal verification has the important theory meaning and wide application. With the popularity of information technology and office automation, the traditional means of seal management has been unable to meet modern needs, especially in the public security and financial fields that need to use information technology to identify more urgently. And then, with the automatic seal verification, the development of the Electronic Government to Purchase Action Bid will go faster.Therefore, tHSI paper introduce the demand in home and the current research abroad of seal imprint, and then particularly discuss identification such as the extraction of seal color, binary, image demonizing, at the end of the paper we introduce the identification based on image algebraic operation.The correct verification rate of seals is affected by many factors, such as the technical expertise, current emotion of the operators and operational environment. So the manual seal verification has become a bottleneck of information management system, therefore an automatic method for seal verification is urgently expected. Based on several mature method in domestic and overseas, the key technology of automatic seal verification are researched systemic in tHSI thesis.The process of automatic seal verification consists Seal Extractor, Seal Recover, Seal Gray Level Transformation, Seal Finalization, Seal Geometric Parameter, Seal Registration and Seal Verification.Seal Extractor and Seal Recover The seal's extracting and fixing is the basis of the whole system. Owing to the influence of the complexity of the seal background, the uncertainty of artificial factor, and the difference of the gathering condition, it's difficult to extract the seal instances. The pretreatment improves the technology of cutting apart the seal impression picture based on color, which is transmitted from the cutting apart of the traditional colored picture based on RGB color model to the seal picture based on HSI color model. In tHSI thesis, a complete seal extracted scheme, with the combination of the RGB, HSI, HSV color model. The seal is extracted by using a pick-up red seal image method that based on HSI color model. Then the missed part can be reconstructed by associated the seal with the background.Seal Registration The precision of the seal parameter calculation determines the match degree and the seal verification rate. Because of the phenomenon of rupture and blur in the seal frame, the traditional used method, for example outer rectangle method, moment method, and curve-fitting method can bring expand error, and Hough transform checking curve method has too much calculation. Base on the two seals' defluxion angle gained in parameters calculating to rotation matching after making translation transform the two heart-shaped coincidence; THSI thesis proposes the geometric parameter calculation method based on quality is guaranteed and the calculation the seal geometry shape. Then according to the precision deflection is increased with the error only in seal geometrical parameter, the swatch seal and the model seal angle of the acquired geometrical are matched by way of heuristics transform method of image rotate.Seal Verification According to the first means and disadvantage of classical seal image registration methods, a double-level registration method, which includes a projection convolution in polar coordinates in rough registration level and a heuristic search in precise registration level, is used to complement the precise registration. After image registration, two methods of features extraction are proposed. The first method is to analyze the characteristics of cliff-image from the viewpoint of structure analysis to obtain features that can reflect difference between genuine-difference and forgery-difference. The second method is to extract frequency features by multiple Gabor filtering. Considering both the speed and precision of seal verification, tHSI thesis use the method of seal verification base on image algebraic operation. After seal registration, difference match the two images, and then analysis the point, wire and chunk in the result, gain the characteristic parameters and then verify the seal with the effectual class selector.When there is a requirement of carrying out seal to check, the image collection ware which is linked to the computer terminal input the seal into the computer with the form of graph. Computer deals with the image on the basis of the programme has been set and moves out the standard seal and encrypt information.Then the computer distinguishes the seal automaticly. Through the automatic distinguish and safe storage to the seal with the computer, it comes true that the seal management is electronicalized and intellectualized, which makes the management of seal verification fast, simple and reliable.The proposal is simple and verified. THSI proposal indicating tHSI method which is verifying seal from the new angle and have brought a new approach to automatic seal verification. |
PDF Full Text Request