An image recognition and recommendation method based on neural network depth learning

Abstract

The invention provides an image recognition and recommendation method based on neural network depth learning. The method obtains pictures and classification from an image database, inputs to a convolution neural network, trains the neural network through repeated forward and backward propagation, improves image recognition accuracy, and extracts a 20-layer neural network model. By using this model, the object recognition and classification is carried out by collecting static pictures. Results are recognized, and by combining with the personalized characteristics of the input, the input probability of interest is analyzed. By using the machine learning model based on the effective recognition and classification of the material cloud database, and using the recommendation system algorithm, the predicted content material is pushed to the image inputter for cognitive learning. The method of the invention has the advantages of high image recognition rate, multiple recognition types and accurate content recommendation, and can be applied to the electronic products of a computer with a digital camera, a mobile phone, a tablet and an embedded system, so that people can photograph and recognize the objects seen in the eyes and actively learn the knowledge of recognizing the objects.

Description

technical field [0001] The invention relates to the technical fields of neural network, deep learning, computer image processing and data mining, and in particular to methods for image recognition, classification index and recommendation of various objects. Background technique [0002] The present invention relates to the technical field of artificial intelligence, artificial intelligence (AI), abbreviated as AI in English, one of its important tasks is to allow computers to judge input information like humans, simulating the decision-making process of human brain neuron networks. As early as 1943, logician Walter Pitts and neurophysiologist Warren McCulloch introduced the concept of neurons into the field of computing, starting the exploration of neural network theory. Afterwards, scientists from various countries deepened and expanded neural network theory, especially in the 1980s and 1990s and the beginning of this century, advancing neural network theory to the developm...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose an image recognition based on neural network deep learning and recommend recognition for the shortcomings of the current industry-trained convolutional neural network model image recognition accuracy is generally not high, the recognition object type is single, and the application range is narrow. The known method: adjust the parameters of each hidden layer of the convolutional neural network layer by layer, extract a 20-layer neural network model with high training accuracy, and effectively improve the recognition accuracy; The image data training set of various objects enables the extracted neural network model to learn and expand the range of object recognition categories; the image recognition results, combined with human personalized characteristic data, and based on the machine learning model of the educational knowledge material database, adopts the recommendation system algorithm, Push the relevant knowledge of objects of interest corresponding to what they see in their eyes and actively collect images in real time to realize the educational cognitive mode of human active learning

Images