Approach for sequential image interpretation using a priori binary perceptual topological and photometric knowledge and k-means-based segmentation
- 11 May 2018
- journal article
- research article
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 35 (6) , 936-945
Abstract
The proposed approach exploits a priori known qualitative inclusion and photometric relationships between image regions, represented by oriented graphs. Our work assumes a sequential image segmentation procedure where regions are progressively segmented and recognized by associating them with corresponding nodes in graphs related to the prior knowledge. The main contribution concerns the parameterization of the -means clustering algorithm, to be used during the segmentation procedure, and the graph-matching-based identification of resulting clusters, corresponding to regions declared in graphs. The parameterization of -means is based on known relationships as well as on regions that have been segmented and recognized at previous steps. Parameters are the region of interest within which -means clustering is constrained, the number of clusters, and seeding constraints. Photometric relationships built from resulting clusters are matched with a priori known relationships to identify each cluster, this being formulated as an exact graph-matching problem. The potential of this approach is studied in four use cases involving real gray-scale and color images with dedicated sequential analysis procedures. Processing results are compared with those obtained without the proposed parameterization of -means, as well as with some other clustering approaches. Results show the relevance of our approach, in particular in terms of segmentation accuracy, computation time, and seeding reliability.
Keywords
This publication has 24 references indexed in Scilit:
- Segmentation of images by color features: A surveyNeurocomputing, 2018
- A constraint propagation approach to structural model based image segmentation and recognitionInformation Sciences, 2013
- SLIC Superpixels Compared to State-of-the-Art Superpixel MethodsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Sequential model-based segmentation and recognition of image structures driven by visual features and spatial relationsComputer Vision and Image Understanding, 2012
- Qualitative spatial relationships for image interpretation by using a conceptual graphImage and Vision Computing, 2009
- Fuzzy spatial relation ontology for image interpretationFuzzy Sets and Systems, 2008
- Using anatomical knowledge expressed as fuzzy constraints to segment the heart in CT imagesPattern Recognition, 2008
- An interactive medical image segmentation system based on the optimal management of regions of interest using topological medical knowledgeComputer Methods and Programs in Biomedicine, 2006
- A Survey of Clustering Data Mining Techniques2006
- Knowledge-based organ identification from CT imagesPattern Recognition, 1995