The focus of this journal is the computer analysis of image information It is a open Journal and has many topics on all areas of image analysis.
Link to Journal:
ISSN: 1077-3142
Impact factor: 2.22
Showing posts with label Pattern recognition. Show all posts
Showing posts with label Pattern recognition. Show all posts
Acoustics, Speech and Signal Processing, IEEE Transactions on
Good journal well regarded and lots of info on "machine learning and pattern analysis" as applied to articles on speech, music DSP.
Link to Journal:
ISSN: 0096-3518
Impact factor: 1.675
Link to Journal:
ISSN: 0096-3518
Impact factor: 1.675
Statistical pattern recognition: a review
May give me a different perspective to my Neural net:
Abstract:
The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field
Link to:
Abstract:
The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field
Link to:
Published in: Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume:22 , Issue: 1 )
Date of Publication: Jan 2000Page(s):4 - 37
Date of Publication: Jan 2000Page(s):4 - 37
- ISSN :
- 0162-8828
- INSPEC Accession Number:
- 6525225
- Digital Object Identifier :
- 10.1109/34.824819
- Date of Current Version :
- 06 August 2002
- Issue Date :
- Jan 2000
- Sponsored by :
- IEEE Computer Society
A machine vision system for grading lentils
A machine vision system for color grading of lentils was developed using a flatbed scanner as the image-gathering device. Grain samples belonging to different grades of large green lentils were scanned and analyzed over a two-crop season period. Image color, color distribution, and textural features were found to begood indicators of lentil grade. Linear discriminant analysis, k-nearest neighbors, and neural network based classifiers performed equally well in predicting sample grade. An online classification system was developed with a neural classifier that achieved an overall accuracy (agreement with the grain inspectors) of more than 90%.
Publication Number GRL# 809. Shahin, M.A. and Symons, S.J. 2001.
Keywords: lentils, grading, inspection, machine vision, color, image analysis, image classification, flatbed scanner
Publication Number GRL# 809. Shahin, M.A. and Symons, S.J. 2001.
Wi-Vi system uses Wi-Fi to see through walls
Researchers at MIT's Computer Science and Artificial Intelligence
Laboratory have developed what could become low-cost, X-ray vision. The
system, known as "Wi-Vi," is based on a concept similar to radar and
sonar imaging, but rather than using high-power signals, this tech uses
reflected Wi-Fi signals to track the movement of people behind walls and
closed doors.
Journal
http://people.csail.mit.edu/fadel/papers/wivi-paper.pdf
Journal
http://people.csail.mit.edu/fadel/papers/wivi-paper.pdf
conclusions .... So far
Specific wave length
colorimeter , using the Arduino we can build a quick embedded
circuit, to read the intensity of light passing though a liquid
can prove beers Lambert
law
add a base solution to
get calibration
add a pattern we want
to find i.e. caffeine
use software to process
signal
test different liquids
to see if pattern exists
may not happen as hard
to pull out signals unless have a reaction agent.
As all these solutions require signal processing that the next stop so after lots of research on alagroms .see keyworks this lead me onto Back propergation nureal networks seem to be the answer , as I will know the output signal Im looking for
colorimeter problem but this device has a disadvantage that the sensing area is very small. as only specfic wavelenghts , need either lots of differnt LED including IR and uv....? or full spectrometer.... but is very simple to implement , and that what im looking for
As all these solutions require signal processing that the next stop so after lots of research on alagroms .see keyworks this lead me onto Back propergation nureal networks seem to be the answer , as I will know the output signal Im looking for
colorimeter problem but this device has a disadvantage that the sensing area is very small. as only specfic wavelenghts , need either lots of differnt LED including IR and uv....? or full spectrometer.... but is very simple to implement , and that what im looking for
Subscribe to:
Posts (Atom)