Automobile damage part recognition method and system

Abstract

The invention discloses an automobile damage part recognition method and system. The method comprises the following steps of: if an automobile insurance claim photo uploaded by a first terminal, recognizing a pixel area of an automobile damage part in the automobile insurance claim photo by utilizing a pre-trained recognition model, wherein the predetermined recognition model is obtained through labelling and training pixel areas in a preset quantity of automobile damage part sample pictures; and if the pixel area of the automobile damage part in the insurance claim photo is recognized, labeling the recognized pixel area, and sending the insurance claim photo with the pixel area label to the first terminal and / or a predetermined second terminal, or intercepting the recognized pixel area and then sending the pixel area to the first terminal and / or the predetermined second terminal. According to the method and system disclosed by the invention, the automobile damage parts with different area sizes in the insurance claim photos can be recognized more accurately.

Description

technical field [0001] The invention relates to the technical field of computers, and in particular, to a method and system for identifying vehicle damaged parts. Background technique [0002] At present, in the field of auto insurance claims, in order to improve the efficiency of claims, many auto insurance companies use image classification and recognition technology in the auto insurance claims system to automatically identify vehicles and damaged parts in the uploaded claim photos. However, the existing image classification and recognition technology can only identify the rough outline of the damaged part of the vehicle, but cannot accurately identify the damaged part of the vehicle. When one damaged part involves two vehicle parts at the same time, the prior art The identified outline of a roughly damaged vehicle part may only point to one vehicle part. For example, if most of the vehicle scratches are on one vehicle part X1 and only a small part is on the edge of anot...

AI Technical Summary

Problems solved by technology

However, the existing image classification and recognition technology can only recognize the rough outline of the damaged part of the vehicle, and cannot accurately identify the damaged part of the car. When a damaged part involves two parts of the vehicle at the same time, the existing technology The roughly identified outline of the damaged vehicle part may point to only one vehicle part

For example, if most of the vehicle scratches are on one vehicle part X1, and only a small part is on the edge of another vehicle part X2, the damaged vehicle part identified by the existing technology may only be X1

Images