A method and device for image recognition based on a user filling in a verification code

Abstract

A method and device for identifying pictures based on filling in verification codes by a user. The method comprises: sending at least one picture to be identified and a plurality of known pictures, which are used as verification code pictures, to a user (S1); receiving user identification nouns input by the user after the verification code pictures are identified by the user, and recording an identification record corresponding to the picture to be identified, the identification record comprising a picture ID of the picture to be identified and the user identification noun input by the user (S2); determining whether the user identification nouns input by the user match the known pictures or not according to the known pictures and picture nouns thereof, and setting weighted scores for the identification records according to matching times of the user identification nouns and the known pictures (S3); and finally, identifying, according to all the recorded identification records corresponding to the pictures to be identified and the weighted scores thereof, picture nouns of the pictures to be identified (S4). The device comprises a verification code picture sending module, a receiving module, a weighting module, and an identification module. By means of the method and the device, picture identification processing speed is accelerated, experience in machine learning is increased, and the identification processing capacity for mass pictures is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a method and device for identifying pictures based on verification codes filled in by users. Background technique [0002] The development of the Internet has always been moving forward in "innovation and change". From the contact platform to the browsing platform, to the interactive platform, to the work platform, the Internet is gradually penetrating people's lives. With the continuous development of the Internet and gradually entering the era of big data, city data, enterprise data, medical data, and website data have become an important part of our virtual and real life. [0003] In the process of machine learning of big data, the background server of Internet applications often encounters situations where the machine cannot accurately identify pictures, and a large amount of manpower is required for labeling and correction. For massive Internet data, manual pr...

AI Technical Summary

Problems solved by technology

For massive Internet data, manual processing of pictures that cannot be machine-learned is extremely tedious and boring work

Images