Ingredient picture identifying and cleaning model and ingredient category identifying method

Abstract

The invention belongs to the technical field of ingredient identification, and discloses a dirty picture cleaning model and an ingredient category identifying method during an ingredient picture preprocessing process. The method comprises the steps that based on a multi-task Auto-Clean convolution neural network model, a K class lexicon and a Yes / No clean tag are given, wherein two CNN models in the model carry out convolution operation on a class tag and a clean tag; after forward propagation, the softmax layer is optimized; and specific parameters are backpropagated. A cleaned image tagged with Yes / No and class is used for iteration in the whole network to acquire the model. The automatic picture cleaning and ingredient category identifying method is realized. According to the invention,on the basis of the prior art, disadvantages are changed in a targeted manner, and optimization is carried out; and for the characteristics of complex and ever-changing background and the like of ingredient images, ingredient images are efficiently, accurately and rapidly identified.

Description

technical field [0001] The invention belongs to the technical field of material identification, and in particular relates to a model for identifying pictures of cleaned food and a method for identifying food types. Background technique [0002] The catering industry is one of the pillar industries of the national economy. How to quickly classify and accurately detect food ingredients is the core and key issue of food quality control and food safety monitoring in the catering industry. The text-based label classification method for traditional ingredients procurement cannot meet the growing business needs. How to quickly and efficiently classify ingredients images has become an urgent problem to be solved. [0003] Data cleaning is the process of re-examining and validating data to remove duplicate information, correct existing errors, and provide data consistency. In the image preprocessing process, manual cleaning requires a lot of manpower, material resources and time cos...

AI Technical Summary

Problems solved by technology

[0007] In the image preprocessing process of the prior art, manual cleaning requires a lot of manpower, material resources and time costs, and the cleaning process is prone to errors due to human factors

In practical applications, food images have the characteristics of complex and changeable background, rotation, scale, and changing light, which brings great challenges to traditional image classification methods; traditional food category recognition algorithms are inefficient. And the types of ingredients are complex, so far there is no research on meat recognition

Images