Flower recognition method based on convolutional neural network (CNN) with ReLU activation function

A convolutional neural network and flower recognition technology, applied in the field of image recognition, can solve the problems of slow recognition speed and low recognition rate, and achieve the effect of fast training speed, reducing the number of parameters, and good effect.

Inactive Publication Date: 2017-12-26
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, to provide a flower recognition method based on the convolutional neural network of the ReLU function, to solve the problems of low recognition rate and slow recognition speed in the prior art, so as to realize the flower recognition technology improvement

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flower recognition method based on convolutional neural network (CNN) with ReLU activation function
  • Flower recognition method based on convolutional neural network (CNN) with ReLU activation function
  • Flower recognition method based on convolutional neural network (CNN) with ReLU activation function

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0048] 1 Image preprocessing

[0049] The experiment was realized under the platform of MatlabR2014a. Preprocessing was performed by image grayscale and bilinear interpolation.

[0050] The color will cause some interference to the identification of flower species, and the color image has a large storage capacity and is inconvenient to process. Therefore, it is necessary to convert the color image into a grayscale image that contains the same amount of information and the processing process is simpler and faster. This process is called Grayscale processing is beneficial to modularize the image, eliminate image noise to obtain a better binarized image, and reduce the amount of calculation for image processing.

[0051]After the image is grayscaled, the size of the input image may vary, some images have a larger resolution, and some are smaller. And the aspect ratio is not necessarily the same. The convolutional neural network structure in this paper requires a fixed input im...

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

No PUM Login to view more

Abstract

The invention discloses a flower recognition method based on a convolutional neural network (CNN) with a ReLU activation function, which belongs to the technical field of image recognition. The method comprises steps: basic parameters of the CNN are set; the weight and the bias term are initialized, and convolutional down sampling layers are designed layer by layer; a random sequence is generated, 50 samples are selected at each time for batch training, a forward process, error conduction and a gradient calculation process are completed, and a gradient sum is updated to a weight model for next weight updating; and a well-set training function and an updating function are called for training, and the accuracy of a sample is tested. Flower recognition can be carries out effectively at a high speed under influences of lighting, rotation and occlusion conditions.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a flower recognition method based on a ReLU function convolutional neural network. Background technique [0002] With the rapid development of science and technology and the popularity of smart phones, people are more and more inclined to replace cumbersome text with more vivid and easy-to-understand pictures. However, the pictorialization of information also creates many problems. Generally, for traditional text-recorded information, we can directly search for keywords to obtain corresponding content, but when using pictures to express information, we cannot directly search or process the information expressed by pictures. Although, with the rapid development of computer technology, we have been able to process pictures and obtain important information, but there is still little work on flower identification. However, the recognition rate and calculation speed of exi...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06K9/38
CPCG06V10/28G06N3/045
Inventor 郭子琰舒心刘常燕李雷
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap