|   | 
Details
   web
Records
Author C. Molina; J.B. Subirana
Title Reduction of complexity for object recognition algorithms Type Report
Year 1995 Publication CVC Technical Report #03 Abbreviated Journal
Volume Issue Pages (down)
Keywords
Abstract
Address CVC (UAB)
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number Admin @ si @ MoS1995a Serial 225
Permanent link to this record
 

 
Author C. Molina; J.B. Subirana
Title Polynomial-Time Algorithm for 2D object recognition. Type Miscellaneous
Year 1995 Publication VI National Simposium on Pattern Recognition and image Analysis Abbreviated Journal
Volume Issue Pages (down)
Keywords
Abstract
Address Cordoba
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number Admin @ si @ MoS1995b Serial 231
Permanent link to this record
 

 
Author J.R. Serra; S. Casadei; J.B. Subirana
Title Non-Cartesian Networks for Middle Level Vision. Type Miscellaneous
Year 1995 Publication VI National Simposium on Pattern Recognition and image Analysis Abbreviated Journal
Volume Issue Pages (down)
Keywords
Abstract
Address Cordoba
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number Admin @ si @ SCS1995 Serial 232
Permanent link to this record
 

 
Author Josep Llados; Enric Marti
Title Interpretacio de dibuixos lineals mitjançant tècniques d isomorfisme entre grafs Type Conference Article
Year 1995 Publication Trobada de Joves Investigadors Abbreviated Journal
Volume Issue Pages (down)
Keywords
Abstract L’anàlisi de documents té com a objectiu la interpretació automàtica de documents impresos sobre paper, amb la finalitat d’obtenir una descripció simbòlica d’aquests, que permeti el seu emmagatzemament i posterior tractament computacional. Les tècniques basades en grafs relacionals d’atributs permeten representar de manera compacta la informació continguda en dibuixos lineals i mitjançant mecanismes d’isomorfisme entre grafs, reconèixer-hi certes estructures i d’aquesta manera, interpretar el document. En aquest treball es dóna una visió general de les tènciques de grafs aplicades al reconeixement visual d’objectes en problemes d’anàlisi de documents. Aquestes tècniques s’il·lustren amb un exemple de reconeixement de plànols dibuixats a mà alçada. Finalment es proposa la utilització de tècniques de Hough com a mecanisme per accelerar el procés de reconeixement aplicant un cert coneixement sobre el domini en el que es treballa
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG;IAM Approved no
Call Number IAM @ iam @ LlM1995 Serial 1578
Permanent link to this record
 

 
Author Petia Radeva; Enric Marti
Title Facial Features Segmentation by Model-Based Snakes Type Conference Article
Year 1995 Publication International Conference on Computing Analysis and Image Processing Abbreviated Journal
Volume Issue Pages (down)
Keywords
Abstract Deformable models have recently been accepted as a standard technique to segment different features in facial images. Despite they give a good approximation of the salient features in a facial image, the resulting shapes of the segmentation process seem somewhat artificial with respect to the natural feature shapes. In this paper we show that active contour models (in particular, rubber snakes) give more close and natural representation of the detected feature shape. Besides, using snakes for facial segmentation frees us from the problem of determination of the numerous weigths of deformable models. Another advantage of rubber snakes is their reduced computational cost. Our experiments using rubber snakes for segmentation of facial snapshots have shown a significant improvement compared to deformable models.
Address
Corporate Author Thesis
Publisher Place of Publication Bellaterra (Barcelona), Spain Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes MILAB;IAM Approved no
Call Number IAM @ iam @ RAM1995a Serial 1633
Permanent link to this record