Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Feature Extraction and Recognition Retrieval Method for Microscopic Images of Chinese Medicinal Materials

A microscopic image and feature extraction technology, applied in the field of biomedical information processing, can solve the problems of not including available information, increasing signal processing time overhead, parameter setting and optimization increase, etc.

Inactive Publication Date: 2020-01-31
TIANSHUI NORMAL UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] (1) In terms of nonlinear modulation coupling and threshold exponential decay, the threshold decay of this model is repeatedly changed. This threshold change cannot well meet the nonlinear exponential requirements of the human eye's response to brightness, and through this threshold law A large amount of information in the processed image (or other signal) is contained in the activation period (frequency) or activation phase of neurons, but the output image does not contain all available information;
[0004] (2) The existence of a large number of leakage integrators and some feedback connections in the PCNN model improves the approximation of the model bionics and the authenticity of biological processing information, but this not only increases the complexity of the model, but also increases the accuracy of the model. Signal processing time overhead;
[0005] (3) There are too many parameters in the traditional PCNN model, and many difficulties will be added to the (automatic) setting and optimization of parameters;
[0006] (4) Due to the complexity and particularity of microscopic images of Chinese medicinal materials, the traditional PCNN model is not suitable for processing microscopic tissue images

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
  • A Feature Extraction and Recognition Retrieval Method for Microscopic Images of Chinese Medicinal Materials
  • A Feature Extraction and Recognition Retrieval Method for Microscopic Images of Chinese Medicinal Materials
  • A Feature Extraction and Recognition Retrieval Method for Microscopic Images of Chinese Medicinal Materials

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087]In order to further understand the content, features and effects of the present invention, the following examples are given, and detailed descriptions are given below with reference to the accompanying drawings.

[0088] see figure 1 :

[0089] Microscopic image acquisition preprocessing and database construction of Chinese herbal medicines:

[0090] (1) According to the pharmacopoeia, hundreds of medicinal plants such as angelica, codonopsis, licorice, rhubarb, astragalus, lily, ephedra, bupleurum, isatidis, fennel, safflower, gastrodia elata, and fritillaria, distributed in different regions of Gansu province, are to be recorded As the original object of the study, samples of authentic medicinal materials (or medicinal herb pollen samples) were collected from the growing areas in different medicinal materials growing seasons, and high-resolution digital cameras were used to obtain images of the morphology of traditional Chinese medicines.

[0091] (2) On the basis of...

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 feature extraction and identification retrieval method of microscopic images of Chinese medicinal materials. By introducing a PCNN timing matrix information processing method and combining PCNN with image Fourier transform and decimal power exponential filtering phase, the image features in the transformation domain are extracted. Information, based on the comprehensive similarity measurement of Mahalanobis distance combined with Pearson product-moment correlation method, a fast storage, identification and retrieval algorithm for microscopic image information of Chinese herbal medicines is proposed, and a holographic microstructure image of Chinese medicinal materials, pollen image feature extraction and recognition retrieval are constructed. The system further improves the objectivity, accuracy, repeatability and intelligence of the quality evaluation of Chinese herbal medicines, and provides a new way for the modernization of the detection and analysis of Chinese herbal medicines.

Description

technical field [0001] The invention belongs to the field of biomedical information processing, and in particular relates to a method for feature extraction, recognition and retrieval of microscopic images of Chinese herbal medicines. Background technique [0002] Pulse-coupled neural network (PCNN) is proposed based on the synchronous pulse emission phenomenon in the visual cortex of mammals such as cats and monkeys. It has a good biological background. The model has dynamic variable threshold, nonlinear modulation coupling, synchronous pulse The characteristics of pulse emission and space-time summation make PCNN show great advantages in signal processing applications, especially in image processing applications. However, the traditional PCNN model still has the following theoretical and technical shortcomings: [0003] (1) In terms of nonlinear modulation coupling and threshold exponential decay, the threshold decay of this model is repeatedly changed. This threshold cha...

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 Patents(China)
IPC IPC(8): G06K9/46G06K9/40G06K9/62G06N3/06
CPCG06N3/061G06V10/30G06V10/44G06V10/56G06F18/22
Inventor 刘勍施海燕杨红平马小姝张利军杨筱平
Owner TIANSHUI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products