Analysing the Quality of Food on Convolution Neural Network for Fuzzy Classifier in Hyperspectral Imagery

Abstract

Abstract Introduction: This paper is introducing a new architecture which associates convolutional neural network (CNN) formed on fuzzy neural network (FNN). The fuzzy neural network with some few connected layers which gives to add some feature information for using fuzzy neural network. Mapping of membership values, feature maps also called as outputs are produced by CNN that is given in to fuzzy layers by using training phase. The classification accuracy is increased in this proposed architecture instead we are using fuzzy neural networks that can generate not only crisp values but also fuzzy values because of more information is produced in the fuzzy set. Methods: Cross-validation tests are evaluated in our proposed model. More data is needed for executing training the sequences, we contain only less data and testing the data which contains more amount of information that will express the object classified in its ability where important information is not available. Results: The convolution neural network consists of tuned convolution layer, Heuristic Activation Operation and Parallel Element Merge Layer which is manipulated by the fuzzy classifier output based on food image context extractor. Conclusion: Finally, Quality of Food is analysed by means of Visual IDE. Based on that Hyperspectral Output Image is extracted with good accuracy