Spatial-HMM : A new approach for semantic annotation of histological images

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)22_Publication in policy or professional journal

View graph of relations



Original languageEnglish
Article number1699928
Pages (from-to)663-666
Journal / PublicationProceedings - International Conference on Pattern Recognition
Publication statusPublished - 2006


Title18th International Conference on Pattern Recognition, ICPR 2006
CityHong Kong
Period20 - 24 August 2006


This paper presents a new spatial-HMM for automatically classifying and annotating histological images. Our model is a 2D generalization of HMM. Given a matrix of feature vectors for all blocks in an image, the most appropriate semantic labels determined by our models are used for annotation. Our experimental results showed that our model is superior to HMM in both recognition and annotation accuracy. © 2006 IEEE.