A new per-field classification method using mixture discriminant analysis

Abstract

In this study, a new per-field classification method is proposed for supervised classification of remotely sensed multispectral image data of an agricultural area using Gaussian mixture discriminant analysis (MDA). For the proposed per-field classification method, multivariate Gaussian mixture models constructed for control and test fields can have fixed or different number of components and each component can have different or common covariance matrix structure. The discrimination function and the decision rule of this method are established according to the average Bhattacharyya distance and the minimum values of the average Bhattacharyya distances, respectively. The proposed per-field classification method is analyzed for different structures of a covariance matrix with fixed and different number of components. Also, we classify the remotely sensed multispectral image data using the per-pixel classification method based on Gaussian MDA.

Estimation of critical nitrogen contents in peach orchards using visible-near infrared spectral mixture analysis

“…Studies have reported that accuracy coefficient values of ≥0.70 are considered to be “robust” in the estimation of the N contents of plants using spectral reflectance values and that they are considered to be “reliable” for the created models. 45 , 83 Based on the results presented here, the success of the GMDA in studies on the classification of spectral data, 84 , 85 could also be achieved by ground-based hyperspectral measurements. Distributions consisting of two or more components are called mixture distributions, and mixture distribution models provide a mathematical approach to creating statistical models for measurements collected of different aspects of natural events that are fully random in many fields.…”

“…86 Thus, they are considered to be useful for the analysis of spectral data, since each spectrum can be separated from a specific spectral data. 85 , 87 , 88 However, there is a lack of literature on the use of mixture discriminant models in the categorization and estimation of nutrient levels in plants using spectral techniques. In fact, stepwise multiple linear regression, 89 partial least squares regression, 72 and multivariate linear regression, 14 models have been commonly used in many studies conducted in this field.…”

Şeker pancarı yapraklarında azot durumunun spektral diskriminant analizi ile belirlenmesi

“…Yapılan çalışmalarda bitkilerin %N içeriklerinin spektral yansıma değerleri ile tahmininde doğruluk katsayısı %70 ve üzeri değerler "kuvvetli" olarak nitelemekte ve üretilen modeller için "güvenilir" olarak belirtmektedir (Fitzgerald ve ark., 2010;Feng ve ark., 2014). Çalışma sonucu elde edilen bulgulara göre KDA modelinin spektral verilerin sınıflamasına yönelik çalışmalardaki başarısı (Ju ve ark., 2003;Çalış and Erol, 2012), yersel hiperspektral ölçümler ile de sağlanmıştır. Diskriminant modelleri birçok alanda rasgelelik içeren doğal olayların farklı özellikleri hakkında toplanan ölçüm değerlerine istatistiksel olarak model oluşturmada matematiksel bir yaklaşım sağlamakta (Manolakis ve ark., 2001), ve spektral verilerin analizinde belirli bir spektral veriden her bir spektrumun ayrıştırabilir olmasından dolayı kullanışlı bir yöntem olarak değerlendirilmekte ve kullanılmaktadır (Gillis ve ark, 2008;Çalış ve Erol, 2012;Deng ve ark., 2015).…”