Image segmentation for the purpose of object-based classification

Darwish, Amani; Leukert, K.; Reinhardt, Wolfgang

doi:10.1109/igarss.2003.1294332

Cited by 77 publications

(55 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore many of these algorithms are about natural image segmentation [1,7]. An example of the application of these algorithms is remote sensing [8]. These al gorithms often cannot extract a complex object such as human, car, etc., in a real image.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge-based semantic image segmentation and global precedence effect

Tab

Naghdy

2005

2nd European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology (EWIMT 2005)

View full text Add to dashboard Cite

Knowledge-based semantic image segmentation and global precedence effect AbstractThis paper introduces a knowledge-based semantic image segmentation which extracts the "object(s)-ofinterest" from the image. Image templates are the high-level knowledge in the system. The major contribution of this work is the use of the "Global Precedence Effect" (forest before trees) of the human visual system (HVS) in image analysis and understanding. The "object-of-interest" is searched for hierarchically through an irregular pyramid by an affine invariant comparison between the different region combinations and the template starting from lowest to the highest resolutions. The global/large size objects are found at lower resolutions with significantly lower computational complexity. Disciplines Physical Sciences and Mathematics

show abstract

Section: Related Workmentioning

confidence: 99%

“…To date, perfect and Well implementation of this goal at this stage is far from reality [5)' and the existing algorithms suffer from many limitations such as only coping with scenes with includ ing special and limited objects [1,6,7). Therefore "object-of interest" extraction has been attracted great attention in recent years [2][3][4]8).…”

Section: [1-4)mentioning

confidence: 99%

Knowledge-based semantic image segmentation and global precedence effect

Tab

Naghdy

2005

2nd European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology (EWIMT 2005)

View full text Add to dashboard Cite

show abstract

“…Once the partition is defined, the search for objects is performed. As in (Darwish et al, 2003), one of the drawbacks is that the object detection task is done after a segmentation step producing a partition.…”

Section: Introductionmentioning

confidence: 99%

“…These features can significantly contribute to the definition of robust object detection algorithms. In this context, the ECognition software (Darwish et al, 2003) was developed. It relies on hierarchical segmentation and produces an image partition on which various region descriptors can be computed.…”

Section: Introductionmentioning

confidence: 99%

Object recognition in hyperspectral images using Binary Partition Tree representation

Valero

Salembier

Chanussot

2015

Pattern Recognition Letters

View full text Add to dashboard Cite

Article history:Object based image analysis Binary Partition Tree Hyperspectral Images Object RecognitionIn this work, an image representation based on Binary Partition Tree is proposed for object detection in hyperspectral images. This hierarchical region-based representation can be interpreted as a set of hierarchical regions stored in a tree structure, which succeeds in presenting: (i) the decomposition of the image in terms of coherent regions and (ii) the inclusion relations of the regions in the scene. Hence, the BPT representation defines a search space for constructing a robust object identification scheme. Spatial and spectral information are integrated in order to analyze hyperspectral images with a region-based perspective. For each region represented in the BPT, spatial and spectral descriptors are computed and the likelihood that they correspond to an instantiation of the object of interest is evaluated. Experimental results demonstrate the good performances of this BPT-based approach.

show abstract

“…A few methods for segmentation of multispectral and hyperspectral images have been introduced in the literature. Some of these methods are based on region merging methods, where neighboring segmented regions are merged with each other according to their homogeneity criterion, for instance Multiresolution Segmentation Method in the eCognition software is used this type of approach [5]. In [6], hierarchical segmentation algorithm is proposed, which performs region growing and spectral clustering alternately.…”

Section: Introductionmentioning

confidence: 99%