An object appearance detection method and depth neural network model

Abstract

The invention relates to a method for detecting the appearance of an object and a depth neural network model. The method for detecting the appearance of an object comprises the following steps: building a depth neural network model; deep neural network model has the ability to distinguish the appearance through the cycle of training and learning; according to the large number of cyclic training and learning, the depth neural network model gradually converges to obtain the optimal weight of each eigenvalue; convolution operation is carried out on the appearance picture of the object to be detected, and the classification result is obtained according to the set probability interval value. The depth neural network model comprises a training module, an evaluation module and a prediction module. The invention solves many problems existing in manually formulating judgment rules of object appearance classification, and overcomes the problems of low manual operation efficiency or low accuracyof traditional automatic judgment. At the same time, because of its sustainable self-iterative upgrading, its recognition efficiency will be improved in theory. The module of the invention is simple,the hardware cost is low, and the application range is wide.

Description

【Technical Field】 [0001] The invention relates to the technical field of intelligent image recognition, and relates to automatic detection of the appearance of an object, in particular to a method and a deep neural network model for detecting the appearance of an object. 【Background technique】 [0002] With the continuous development of industrial production and the continuous increase of people's material demand, the annual output of some consumer electronic products has exceeded 100 million units. At present, the mainstream object appearance inspection method still relies on the manual visual inspection of the production line operators, and the inspection is carried out according to the defined judgment standards. The manual inspection program requires a lot of manpower, and has a high error rate and low efficiency, which is likely to cause a bottleneck in production capacity and a high return to the factory. In order to improve efficiency, save manpower, and reduce customer c...

AI Technical Summary

Problems solved by technology

Although this method can improve work efficiency, because the formulation of the rules mainly depends on the operator's past experience and previous test data, and it is difficult for humans to find the mutual mapping relationship of various data among a large amount of data, which leads to rule definition. The rules themselves have serious flaws, and this method cannot completely solve this problem in principle.

Images