Image Recognition Method of Globe Country Based on Convolutional Neural Network
A convolutional neural network and image recognition technology, applied in the field of deep learning and image recognition, can solve problems such as unsatisfactory recognition effect, difficulty in extracting advanced features, cumbersome manual feature extraction process, etc., to solve the problem of gradient disappearance, efficient The effect of using features and reducing the number of training parameters
Inactive Publication Date: 2021-09-24
DALIAN UNIV OF TECH
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In this method, the process of manually extracting features is cumbersome, and it is difficult to extract more advanced features, so the recognition effect is not ideal
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0015] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0016] figure 1 As shown, the globe country image recognition method based on the convolutional neural network proposed by the present invention mainly includes:
[0017] Step 101, constructing an image data set for training a convolutional neural network model. Various types of images of various countries on the commonly used educational globes...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for recognizing country images of globes based on a convolutional neural network. First of all, through data collection and data enhancement, various types of images of various countries on commonly used teaching globes are collected to construct a globe country image dataset. Multiple images taken at different spatial positions and angles. Second, compression and preprocessing operations are performed on each image in the dataset. Then, a new convolutional neural network model is designed by combining the characteristics of the classic convolutional neural network models MobileNet and DenseNet, and the new model is trained on the collected data set, so that the model can learn the information of each country on the globe. image features to classify them. The recognition model designed by the method of the invention combines the characteristics of the two models of MobileNet and DenseNet, and has higher recognition accuracy and lower model complexity.
Description
technical field [0001] The invention relates to the fields of deep learning and image recognition, in particular to a convolutional neural network-based image recognition method for globe countries. Background technique [0002] At present, most of the research on the country recognition of the globe adopts the traditional image recognition method. First, it needs to manually extract features, such as using sift, hog, lbp, haar and other image feature operators to extract image features, and then use such as svm, adaboost and other classifiers. Classification. In this method, the process of manually extracting features is cumbersome, and it is difficult to extract more advanced features, so the recognition effect is not ideal. [0003] The convolutional neural network does not require tedious manual feature extraction of images, but directly inputs the original image into the network, uses convolution operations to extract low-level features at lower layers, and then combin...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06T9/00
CPCG06T9/005G06N3/045G06F18/214
Inventor 王飞龙冯林王蕾
Owner DALIAN UNIV OF TECH