@incollection{fdi:010072201,
  title = {{G}{\'e}n{\'e}ration de contraintes pour le clustering {\`a} partir d'une ontologie : application {\`a} la classification d'images satellites},
  author = {{C}hahdi, {H}atim and {G}rozavu, {N}. and {M}ougenot, {I}. and {B}ennani, {Y}. and {B}erti-{E}quille, {L}aure},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n this paper, we present a new approach combining topological unsupervised learning with ontology based reasoning to achieve both: (i) automatic interpretation of clustering, and (ii) scaling ontology reasoning over large datasets. {T}he interest of such approach holds on the use of expert knowledge to automate cluster labeling and gives them high level semantics that meets the user interest. {T}he proposed approach is based on two steps. {T}he first step performs a topographic unsupervised learning based on the {SOM} ({S}elf-{O}rganizing {M}aps) algorithm. {T}he second step integrates expert knowledge in the map using ontology reasoning over the prototypes and provides an automatic interpretation of the clusters. {W}e apply our approach to the real problem of satellite image classification. {T}he experiments highlight the capacity of our approach to obtain a semantically labeled topographic map and the obtained results show very promising performances.},
  keywords = {{INTELLIGENCE} {ARTIFICIELLE} ; {TRAITEMENT} {D}'{IMAGE} ; {IMAGE} {SATELLITE} ; {CLASSIFICATION} ; {ONTOLOGIE} ; {CLUSTERING}},
  booktitle = {{N}eural information processing : 23rd international conference, {ICONIP} 2016, {K}yoto, {J}apan, {O}ctober 16-21, 2016 : proceedings, part {III}},
  numero = {9949},
  pages = {156--164},
  address = {{C}ham},
  publisher = {{S}pringer},
  series = {{L}ecture {N}otes in {C}omputer {S}cience},
  year = {2016},
  DOI = {10.1007/978-3-319-46675-0_18},
  ISBN = {978-3-319-46674-3},
  URL = {https://www.documentation.ird.fr/hor/fdi:010072201},
}