Mode recognition method in imaging spectrum object recognition analysis
A pattern recognition and imaging spectrum technology, applied in the field of imaging spectrum target recognition and analysis, can solve the problems of low recognition accuracy and high complexity of pattern recognition methods, and achieve the effect of high result accuracy
Active Publication Date: 2014-07-30
BEIHANG UNIV
View PDF4 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The invention solves the technical problem: overcomes the deficiencies of the prior art, and provides a pattern recognition method in the recognition and analysis of imaging spectrum targets, so as to solve the problems of high complexity and low recognition accuracy of the pattern recognition method in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] The technical solutions of the present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.
[0049] The flowchart of the pattern recognition method in the imaging spectrum target recognition analysis provided by the present invention, as figure 1 As shown, it mainly includes the following steps:
[0050] In step 101, obtain a pixel spectrum two-dimensional matrix of the three-dimensional imaging spectral data in the image pixel to be tested.
[0051] The acquired three-dimensional imaging spectral data of the image pixel to be tested is expressed as a two-dimensional matrix of the imaging spectral reflectance, as follows:
[0052] R m×n =[p 1 ,p 1 ...p y×i+j ...p x×y ], 0
[0053] or R m×n =[p 1 ,p 1 ...p i+x×j ...p x×y ], 0
[0054] Among them, formula (1) is the expression form of image pixel to be predicted expanded by row, formula (2) is the expression form 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
Login to View More Abstract
The invention provides a mode recognition method in imaging spectrum object recognition analysis. The mode recognition method comprises the steps that a pixel spectrum two-dimensional matrix of three-dimensional imaging spectrum data in pixels of an image to be measured is obtained; preprocessing of spectrum error correction is conducted on a pixel spectrum matrix to be predicted, so that the preprocessed pixel spectrum two-dimensional matrix is obtained; according to the feature weight of a training sample, the weight Euclidean distance between a prediction sample and the training sample is calculated, nc neighbors of the training sample in each training sample category are obtained according to the weight Euclidean distance, and hyperplanes are built according to the obtained neighbors; the minimum distance between the prediction sample and each built hyperplane is calculated; which hyperplane is the closest to the prediction sample is judged, and the result of mode recognition is that the prediction sample belongs to the category of the hyperplane. The mode recognition method in imaging spectrum object recognition analysis solves the problem that a mode recognition method is high in complexity and low in recognition accuracy in the prior art.
Description
technical field [0001] The invention relates to the technical field of imaging spectrum target recognition and analysis, in particular to a pattern recognition method in imaging spectrum target recognition and analysis. Background technique [0002] Imaging spectroscopy is one of the most important technological breakthroughs in the Earth observation system in the 20th century. It overcomes the limitations of traditional multi-band and multi-spectral in terms of band number, band range, and fine information expression. A large number of bands provides target information, and can subdivide and identify targets from spectral space, and has been widely used in many fields. After obtaining the imaging spectral data information, it is necessary to classify and distinguish the spectra of the target, classify the spectra that reflect different materials and component contents, and determine the composition of the target, and then determine the nature of the target. Due to the grea...
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
Login to View More IPC IPC(8): G06K9/62
Inventor 李庆波张广军高琦硕
Owner BEIHANG UNIV