A method of image recognition and recommendation cognition based on neural network deep learning

Abstract

The present invention proposes a method of image recognition and recommendation cognition based on neural network deep learning, which acquires pictures and classifications from the image database, inputs them into the convolutional neural network, and trains the neural network through repeated forward and backward propagation. network, improve the accuracy of image recognition, and extract a 20-layer neural network model. Using this model, object recognition and classification are carried out through statically collected pictures. The recognition result, combined with the personalized characteristics of the inputter, analyzes the interest probability of the inputter. Using the constructed machine learning model based on the material cloud database for effective identification and classification, and using the recommendation system algorithm, the predicted content material is pushed to the image input person for cognitive learning. The invention has the advantages of high image recognition rate, many types of recognition, and accurate content recommendation, and can be applied to electronic products such as computers with digital cameras, mobile phones, tablets, and embedded systems, allowing people to recognize objects in their eyes. Shooting recognition, active learning to recognize 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