The invention provides an
animal identification method,
system and device based on a neural network, and a storage medium, and the method comprises the steps: carrying out the animal classification ofan image through a trained animal classification network, obtaining the animal information of the image, and carrying out the image preprocessing; building a deep
convolutional neural network, the deep
convolutional neural network comprising a
feature extraction network and a training network, and the
feature extraction network comprising a target detection part for
feature extraction and an image classification part for classified learning of
global information and features; carrying out model training, initializing a feature extraction network by using the trained weight, extracting features of all pictures, dividing the extracted features into a
training set and a
verification set, and carrying out training on a
network layer; and classifying the pictures, and outputting a
classification result to obtain a classification
label corresponding to the maximum probability. According to the invention,
animal identification of more pictures can be realized, through prediction and judgmentof the model, the operation cost can be reduced, and subsequent arrangement and sorting of the pictures are facilitated.