how to create 2D polynomial regression?

hi I have a 22x34 image. how to create a function just like ax^2+by^2+cxy+dx+ey+f to fit this image

 採用された回答

dpb
dpb 2015 年 12 月 30 日

0 投票

If have CurveFitting Toolbox,
sf = fit([x, y], z, 'poly22'); % doc fit for details...
If not, write the specific model matrix and use \ to solve.
doc mldivide % illustrates
Oh, or if have Statistics Toolbox, there's the regress linear regression method.

その他の回答 (1 件)

Image Analyst
Image Analyst 2015 年 12 月 30 日

1 投票

You can use John D'Errico's polyfitn in the File Exchange: http://www.mathworks.com/matlabcentral/fileexchange/34765-polyfitn.
Attached is an example of how I used it to correct (flatten) a background.

カテゴリ

ヘルプ センター および File ExchangeLinear and Nonlinear Regression についてさらに検索

タグ

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by