Multi-Bands Image Segmentation: A Scalar Approach

In the domain of multi-bands image processing, two different approachescan be considered: the scalar one and thevectorial one. This paper presents a method that belongs to the first approach. The method is achieved in three steps. The first steptempts to eliminate redundant observationsby making a selection of relevant bands. In the second step, each of the selected bands is segmented using a technique of histogram multi-thresholding. In the laststep, a fusionby a combination of the results of the selected bands allows to obtain the final segmentation. This scheme is illustrated in the frame of an application in high-resolution multispectral imagery acquired by the Compact Airborne SpectrographicImager (CASI).

• Type: Conference
• Year: 2000
• Where: ICIP
• Authors: Chafik Kermad, Kacem Chehdi
• Keywords: Compact Airborne SpectrographicImager, ICIP 2000, Image Processing, Relevant Bands