Classifying image features

A technology of images and image piles, applied in the directions of instruments, computing, character and pattern recognition, etc.

Active Publication Date: 2008-03-26
CAMBRIDGE RES & INSTR
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, either because the multiple colorations are in fact confined to common structures in the sample, or because due to the preparation method, a...

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
  • Classifying image features
  • Classifying image features
  • Classifying image features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] overview

[0037] The methods and systems disclosed herein can be used to classify a wide variety of biological or other samples based on spectral and / or structural features present on images of the samples. The classification method includes at least some steps performed in an automated fashion using machine vision algorithms and techniques. A collection of images of samples is obtained and may be transformed before being submitted to an automatic classifier. Transformation of image sets may include mathematical transformations, such as conversion from intensity to optical density; spectral unmixing and operations, computation of composite images; and formation of classified data sets that may include only a subset of available sample images. The classified data set is then submitted to a machine-based classifier, which can be a neural network or another type of classifier. Image pixels may be classified multiple times, and a final classification is performed based o...

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

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Description

technical field [0001] The present invention relates to sorting tissue samples. Background technique [0002] Chromogenic staining techniques have been developed empirically to create visual contrast between various components within a tissue sample. Staining techniques and protocols enable the generation of mixtures of dyes in different tissue components, and using microscopes and other imaging equipment, human observers have learned to distinguish these staining patterns that are unique to specific components. Modern scaled staining methods that can be specific to a certain portion of a chemical molecule and / or to an arrangement of molecular structure can produce stained tissue in which two or more chromogenic or fluorescent stains overlap significantly in space . In fact, either because the multiple colorations are in fact confined to common structures in the sample, or because, due to the preparation method, a structure containing one coloration overlaps a second struc...

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): G06K9/00
CPCG06K9/628G06K9/00127G06K9/6247G06V20/69G06V10/7715G06F18/21G06F18/2135G06F18/2431G06F18/2433
Inventor 理查德·利文森克利福德·C·霍伊特柯克·W·戈西奇
Owner CAMBRIDGE RES & INSTR
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