João Francisco Gonçalves Antunes

Contextual superpixel description for remote sensing image classification

The performance of pattern classifiers depends on the separability of the classes in the feature space - a property related to the quality of the descriptors - and the choice of informative training samples for user labeling - a procedure that usually requires active learning. This work is devoted to improve the quality of the descriptors when samples are superpixels from remote sensing images. We introduce a new scheme for superpixel description based on Bag of visual Words, which includes information from adjacent superpixels, and validate it by using two remote sensing images and several region descriptors as baselines.

Ainfo: a experiência da Embrapa na disponibilização e recuperação de informação

AINFO is an information system developed by Embrapa-CNPTIA which allows the integrated management of document data bases and bibliographical processes, providing speediness and flexibility in capturing, managing and information retrieval, besides offering to its users several usage facilities. Starting with its use at Embrapas libraries, it became possible to offer access to the general public to the acquired material as well as thesis and the scientific production of Embrapas researchers. A large and important colectior of national and international periodicals is also available for research in CD-ROM and on the Internet.