Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Cell classifying method based on EMD feature extraction and sparse representation

A feature extraction and sparse representation technology, applied in the field of medical hyperspectral classification and recognition, can solve the problems of low accuracy and time-consuming

Active Publication Date: 2016-11-09
BEIJING UNIV OF CHEM TECH
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In traditional medical treatment, doctors use the naked eye to observe the shape of lesion areas on medical images, and many medical images are generated every day, which is time-consuming and has low accuracy.

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
  • Cell classifying method based on EMD feature extraction and sparse representation
  • Cell classifying method based on EMD feature extraction and sparse representation
  • Cell classifying method based on EMD feature extraction and sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The basic flow of the method for cell classification based on EMD feature extraction and sparse representation of the present invention is as follows: figure 1 As shown, it specifically includes the following steps:

[0058] 1) First normalize the blood cell data, and then store the data and corresponding labels.

[0059] 2) Due to the large number of spectral bands of blood cells and the spatial correlation between each band, if all the bands are used, redundant information will be generated, which will increase the computational time overhead. In order to reduce the data volume of EMD feature extraction and improve the operation time, band selection is performed on the blood cell data first. The size of blood cell data selected in the experiment is 462×451×33. So choose 5 bands out of 33 bands, which are the 25th, 33rd, 20th, 30th and 32nd bands. The selected bands have the advantages of high information content, low correlation, large spectral difference, and good...

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 cell classifying method based on EMD feature extraction and sparse representation, and relates to an EMD-based cell feature extraction method. The method comprises steps: an orthogonal subspace projection (OSP) method is firstly used for carrying out band section on a medical hyperspectral image, dimensions are reduced, and data redundancy is reduced; and then, a two-dimensional EMD method is used for carrying out feature extraction on the data after dimension reduction, and the data are decomposed into a series of IMF components whose frequencies are arranged from high to low. A sparse representation classifier (SRC) is used for classifying the data, samples are classified through comparing residual, and when the residual obtained through calculation is small, the sample is divided into the class. In the cell classifying method based on EMD feature extraction and sparse representation, the EMD shows good time frequency characteristics, and an obvious potential and advantages exist in hyperspectral data feature extraction. Meanwhile, as the sparse representation classifier (SRC) is used, the classifying precision is more greatly ensured.

Description

technical field [0001] The invention relates to an EMD (empirical mode decomposition)-based cell feature extraction method, which is classified and identified by a sparse representation classification method, and belongs to the field of medical hyperspectral classification and identification. Background technique [0002] The traditional medical detection method is a series of chemical analysis methods, staining the tissue sections, the experimental process is complicated, the cycle is long, the speed is slow, the intensity is large, the error is large, and the repeatability of the measurement is poor. The identification of cancer cells is realized through human eye observation. Affected by the subjectivity of the experimenter, it is easy to cause misdiagnosis. With the development of imaging technology, medical diagnosis is increasingly dependent on imaging technology. Imaging modalities include magnetic resonance imaging (MRI), computed tomography (CT), sonography, nuclea...

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
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06K9/62G06T7/00
CPCG06T7/0012G06T2207/30096G06T2207/10036G06T2207/20036G06V10/25G06V10/40G06V10/513G06F2218/10G06F18/24133
Inventor 李伟张秋实
Owner BEIJING UNIV OF CHEM TECH
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
Eureka Blog
Learn More
PatSnap group products