Abstract

 In this paper, we are doing the segmentation of hyperspectral image using the binary partition tree. Hyper spectral imaging has enabled the characterization of regions based on their spectral properties. Segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as super pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. The work presented here proposes a new Binary Partition Tree pruning strategy aimed at the segmentation of hyper spectral images. The Binary Partition Tree is a region-based representation of images that involves a reduced the number of elementary primitive and therefore allows us to define robust and efficient segmentation algorithm. Here, the regions contained in the Binary Partition Tree branches are studied by recursive spectral graph partitioning. The goal is to remove subtrees composed of nodes which are considered to be similar. To this end, affinity matrices on the tree branches are computed using a new distance-based measure. Hyper spectral imaging has enabled the characterization of regions based on their spectral properties. This has lead to the use of such images in a growing number of applications, such as remote sensing, food safety, healthcare or medical research. Hence, a great deal of research is invested in the field of hyper spectral image segmentation. The number of wavelengths per spectrum and pixel per image as well as the complexity of handling spatial and spectral correlation explain why this approach is still a largely open research issue. The proposed work focuses on the problem of image segmentation and provides the better results.

Authors and Affiliations