This paper presents a methodology of recognition, identification and classification of built objects in a dense urban area by morphometric approach with Spot 5 panchromatic image. The methodology is based on the sequence of image processing: fusion of Laplacian enhancements, intermediate symbolic representation (ISR) method of segmented build-up objects, and unsupervised classification by hierarchical ascending classification from morphometric attributes of each build-up objects extracted by ISR. The intermediate symbolic visualization method generates automatically a vector mapping of segmented buildings and an urban object-oriented morphometric database. Each build-up object is morphologically characterized by fifty geometric attributes.