Picture recognition method and device based on verification code filled by user

Abstract

The invention discloses a picture recognition method and device based on a verification code filled by a user. The method comprises the following steps: sending at least one to-be-recognized picture and multiple known pictures to the user to serve as verification code pictures, receiving a user recognition noun input by the user after recognizing the verification code pictures, recording a recognition record corresponding to one to-be-recognized picture, judging whether the user recognition noun input by the user is matched with the known pictures according to the known pictures and the picture nouns thereof, setting a weighting score for the recognition record according to the matching times with the known pictures, and finally identifying the picture noun of the to-be-recognized picture according to all recorded recognition records corresponding to the to-be-recognized picture and the weighting scores thereof. The device disclosed by the invention comprises a verification code picture sending module, a receiving module, a weighting module and a recognition module. By adoption of the method and device disclosed by the invention, the picture recognition processing speed is accelerated, the machine learning experience is increased, and the recognition processing ability of massive pictures is improved effectively.

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