Variable-length universal numeric alphabet verification code identification system and method

Abstract

The invention discloses a variable-length universal numeric alphabet verification code identification system and method, and belongs to the technical field of computers. The method comprises the following steps of: 1, randomly generating numeric alphabet verification code pictures with various lengths, fonts and noises by utilizing a captcha third-party library; 2, constructing a deep convolutional neural network model based on the numeric alphabetic verification code picture generated in the step 1; 3, training the deep convolutional neural network model constructed in the step 2 until a training model with relatively high precision is obtained; and step 4, identifying the uploaded verification code picture by using the deep convolutional neural network model obtained by training in the step 3. A character is added in the constructed deep convolutional neural network to prevent the unfixed-length verification code from generating the situation that the character is empty, so that the method is suitable for identifying multiple types of verification codes, and the identification efficiency is improved. And the use effect of the identification system is further improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a system and method for identifying a variable-length universal alphanumeric verification code. Background technique [0002] The verification code is a public automatic program that distinguishes whether the user is a computer or a human. It can prevent: malicious cracking of passwords, swiping tickets, flooding forums, and effectively prevents a hacker from continuously logging in to a specific registered user with a specific program brute force cracking method Try, therefore, to accurately identify the verification code, which can avoid the situation that the user cannot use the program normally due to unclear identification in daily life. [0003] The existing digital and alphanumeric verification code recognition systems are all solutions for fixed length, fixed font, and fixed noise pattern when identifying verification codes, resulting in a narrow range of application fo...

AI Technical Summary

Problems solved by technology

[0003] The existing digital and alphanumeric verification code recognition systems are all solutions for fixed length, fixed font, and fixed noise pattern when identifying verification codes, resulting in a narrow range of application for the recognition system, poor use effect, and problems in building volumes. When the convolutional neural network model recognizes the verification code, it cannot split the characters with high edge adhesion, resulting in a slow model processing rate, and when training the constructed convolutional neural network, the accuracy of the verification code cannot be guaranteed. The degree reaches the maximum value, further reducing the recognition accuracy of the recognition system

Images