كاهش ابعاد داده‌هاي ابرطيفي به منظور افزايش جدايي‌پذيري كلاس‌ها و حفظ ساختار داده

Feature reduction of hyperspectral data for increasing of class separability and preserving of data structure

امروزه تصويربرداري ابرطيفي به‌منظور طبقه‌بندي داده‌هاي سطح زمين با دقت و جزئيات بالا بسيار مورد توجه است. به‌دليل كمبود نمونه آموزشي در دسترس، كاهش ابعاد دادۀ ابرطيفي به‌عنوان يك گام مهم پيش‌پردازش در تحليل و طبقه‌بندي تصاوير ابرطيفي به شمار مي‌رود. در اين مقاله يك روش استخراج ويژگي پيشنهاد شده كه سعي مي‌كند، علاوه‌بر افزايش جدايي‌پذيري طبقه‌ها، ساختار داده را نيز حفظ كند. براي اين منظور، دو تابع هدف پيشنهاد شده است. تابع هدف نخست از نمونه‌هاي آموزشي برچسب‌دار بهره مي‌برد و سعي مي‌كند نمونه‌هاي هم‌طبقه را در فضاي كاهش‌يافته تا جاي ممكن به هم نزديك كند. تابع هدف دوم از نمونه‌هاي بدون برچسب خوشه‌بندي‌شده‌ بهره برده و سعي مي‌كند نمونه‌هاي متعلق به يك خوشه را در فضاي كاهش‌يافته، تا جاي ممكن به هم نزديك گرداند. روش پيشنهادي بر روي سه دادۀ ابرطيفي واقعي مورد آزمايش قرار گرفته و برتري آن از نظر دقت طبقه‌بندي نسبت به تعدادي از روش‌هاي پركاربرد استخراج ويژگي نشان داده شده است.

Hyperspectral imaging with gathering hundreds spectral bands from the surface of the Earth allows us to separate materials with similar spectrum. Hyperspectral images can be used in many applications such as land chemical and physical parameter estimation, classification, target detection, unmixing, and so on. Among these applications, classification is especially interested. A hyperspectral image is a cube data containing two spatial dimensions and a spectral one. Generally, the Hughes phenomenon is occurred in the supervised classification of hyperspectral images due to the limited available labeled samples and the curse of dimensionality. So, feature reduction is an important preprocessing step for analysis and classification of hyperspectral data. Feature reduction methods are categorized into feature selection approaches and feature extraction ones. Our main focus in this paper is on feature extraction. The feature extraction methods are also divided into three main groups: supervised (with labeled samples), unsupervised (without labeled samples), and semi-supervised (with both labeled and unlabeled samples). The first group of feature extraction methods usually suffers from problems due to limited available training samples. These methods often consider the separability between classes, and so are efficient for classification applications. The second group has no need for training samples, but they often do not consider the separability between different classes and so, are not appropriate for classification. These methods are usually used for signal representation or preserving the local structure of data. The use of both labeled and unlabeled samples in the third group can increase the abilities of the feature extractor. A feature extraction method is proposed in this paper which belongs to the third group. The proposed method increases the class separability and tries to preserves the structure of data. The proposed feature extraction method uses the ability of unlabeled samples in addition to available limited training samples to improve the classification performance. The experimental results on three real hyperspectral images show the better performance of proposed method compared to some popular feature extraction methods in terms of classification accuracy.