Providing unbiased ground truths for large size images is a complex task that is difficult to achieve in practice. The aim of our method is to easily produce reliable ground truths, from images covering large areas while respecting the physical nature of the observed data. The first step localizes all classes existing in a large size image without any a prior knowledge, as well as the samples that make them up. Next, the user selects classes from these unbiased detected classes, in order to build a true ground truth adapted to this application. No transformation is carried out on of characteristics (spectral features) of the hyperspectral image pixels measured objectively by the sensor. To prove the relevance of the learning sample selection method, we use three supervised classification methods requiring training samples. Two hyperspectral images are selected to illustrate the performance of the obtained training samples. The results of the proposed method are also compared to those available of some state of the art deep learning methods.
Affinity propagation (AP) is one of the most recent unsupervised classification methods used. Its property is very interesting, but its use reveals the existence of three drawbacks which seriously hamper its usage. These concern its sensitivity to: (i) the presence of identical objects in the population to be partitioned; (ii) the value of the preference parameter p and (iii) the value of the regularization parameter λ introduced for the updating of responsibilities and availabilities criteria. In this paper, an optimization of AP clustering method is proposed which provides an appropriate solution to each drawback underlined above. For the first two, we adapt the value of the preference parameter p for a given object, to the values of the similarities between this object and the others only. In the similarity matrix, any null distance for a given row is reassigned a preference value p, which corresponds to the minimum or average value of this row. Finally, to eliminate the regularization parameter while ensuring the convergence of the algorithm and the optimality of the solution, a smoothing operation on the elements of the responsibilities and the availabilities is introduced, involving the current estimated value and the three previous ones. This approach is tested on synthetic data and hyperspectral images and shows its efficiency. We show both the relevance of the results and their stability without the identified three drawbacks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.