مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields

 مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields

… دانلود …

مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields دارای 8 صفحه می باشد و دارای تنظیمات در microsoft word می باشد و آماده پرینت یا چاپ است

فایل ورد مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields کاملا فرمت بندی و تنظیم شده در استاندارد دانشگاه و مراکز دولتی می باشد.

توجه : در صورت  مشاهده  بهم ريختگي احتمالي در متون زير ،دليل ان کپي کردن اين مطالب از داخل فایل ورد مي باشد و در فايل اصلي مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields،به هيچ وجه بهم ريختگي وجود ندارد


بخشی از متن مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields :


محل انتشار: دوازدهمین کنفرانس ملی سیستمهای هوشمند
تعداد صفحات:8
نویسنده(ها):
Mostafa Borhani – Faculty of Electrical & Computer Engineering Tarbiat Modares University Tehran, Iran
Hassn Ghassemian – Faculty of Electrical & Computer Engineering Tarbiat Modares University Tehran, Iran

چکیده:

The proposed approach of this paper is based on integration of the local weighted Markov Random Fields (MRF) on support vector machine (SVM) framework for hyperspectralspectral-spatial classification. Our proposed method consists of performing probabilistic SVM classification followed by a spatialregulation based on the MRF. One important innovation of this paper is the use of marginal weighting function in the MRFenergy function, which preserves the edge of regions. Theproposed spectral-spatial classification was examined with four real hyperspectral images such as aerial images of urban,agriculture and volcanic with different spatial resolution (1.3m and 20m), different spectral channels (from 102 to 200 bands)and different sensors (AVIRIS and ROSIS). The novel approach was compared with some pervious spectral-spatial methods suchas ECHO and EMP. Experimental results are presented and compared with class map visualization, and some measurements such as average accuracy, overall accuracy and Kappa factor. The proposed method improves accuracy of classification especially in cases where spatial additional information is significant (such as forest structure).

از حضور شما عزیزان در سایت بسیار خوشحالیم و آرزو داریم محصولات ما رضایت شما را فراهم آورد
اینک شما با جستجوی مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields وارد صفحه فروش فایل دانلودی مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields شده اید.
توضیحات کامل و اطلاع از ریز مطالب این فایل با کلیک روی دکمه ی ادامه ی مطلب

مقاله Hyperspectral Image Classification Based on Spectral-Spatial Features Using Probabilistic SVM and Locally Weighted Markov Random Fields