A Manifold Learning Based Feature Extraction Method with Improved Discriminative Ability
عنوان مقاله: A Manifold Learning Based Feature Extraction Method with Improved Discriminative Ability
شناسه ملی مقاله: ICMVIP09_009
منتشر شده در نهمین کنفرانس ماشین بینایی و پردازش تصویر ایران در سال 1394
شناسه ملی مقاله: ICMVIP09_009
منتشر شده در نهمین کنفرانس ماشین بینایی و پردازش تصویر ایران در سال 1394
مشخصات نویسندگان مقاله:
Maryam Imani - Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran
Hassan Ghassemian - Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran
خلاصه مقاله:
Maryam Imani - Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran
Hassan Ghassemian - Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran
Feature reduction is a key step in hyperspectral image classification. In this paper, we propose a supervised feature extraction method which is based on manifold learningtheory. The proposed method uses a new weighting approach in object function to makes between-class samples farther away and makes within-class samples closer in low dimensional feature space. Therefore, discriminative ability of proposed method is improved. The hyperspectral image used in our experiments is collected by AVIRIS sensor over the Indian Pines over a mixedagricultural/forest area. The experimental results show the superiority of proposed method compared to some popular and state-of-the-art feature extraction methods with using limited number of training samples
کلمات کلیدی: manifold learning; discriminative ability; feature extraction; hyperspectral data
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/568536/