Adrien Delaye's Homepage


Me at YuanMingYuan Park, Beijing, China (august 2008)
Welcome on my professional web page.

I am software engineer
working with Apple, in Cupertino, California. My previous positions were with
Samsung Electronics in Suwon, South Korea, and with Pattern Analysis and Learning group of at Chinese Academy of Sicences, Institute of Automation in Beijing, China. I obtained my PhD from INSA of Rennes and Intuidoc team of IRISA lab in Rennes, France.

My research interests cover aspects of:
  • Pattern Recognition, Machine Learning, Computer Vision
  • Human-Computer Interaction, pen-based interfaces
  • Gesture recognition, touch and multi-touch interaction
  • Document analysis and recognition, layout analysis
  • Handwriting recognition, character and symbol recognition, sketch understanding

 

Contact


                 LinkedIn    Twitter   ResearchGate
 
 

Recent Announcements

  • Supplementary material for paper   I just made public a file containing supplementary material related to the journal paper "A flexible framework for online document segmentation by pairwise stroke distance learning", Pattern Recognitoin, 2014. This document contains results of trained distance parameters for enabling quick exploitation of our segmentation results on handwritten datasets.
    Posted Nov 6, 2014, 3:05 AM by Adrien Delaye
  • Unpublished manuscript available (Category:work) A new manuscript entitled "Structured prediction models for online sketch recognition" is available for download. Abstract: In this work we investigate the application of structured probabilistic models for the interpretation of online handwritten sketches. A flexible and fully trainable approach is presented, comprising a method for training pairwise stroke distance and a structured prediction model for labeling strokes. Different variants of model structures are proposed for modeling the context. No symbol hypothesis generation is performed before stroke labeling and hard segmentation decisions are deferred to the post-processing stage. The system is validated by experiments showing high prediction accuracy over two different data sets of online handwritten sketches.
    Posted Oct 28, 2014, 4:20 AM by Adrien Delaye
  • New journal paper accepted (Category:work) Our latest paper "A flexible framework for online document segmentation by pairwise stroke distance learning" has just been accepted for publication in the Pattern Recognition journal. Abstract: A flexible framework for handling a variety of segmentation problems in online handwritten documents is introduced. The strategy relies on single linkage clustering and a pairwise stroke distance that is globally trained for direct optimization of the segmentation. We define a variety of features that can contribute to the pairwise distance definition and show how to select a good combination of features for dealing with a new online handwritten document segmentation task. Our experiments demonstrate the validity of the method on a large range of segmentation tasks over several types of ...
    Posted Oct 17, 2014, 7:38 AM by Adrien Delaye
  • Paper accepted for DRR 2015 (Category:work) Our paper "Structured prediction models for online sketch recognition" has been accepted as an oral presentation for the next Document Recognition and Retrieval conference (DRR), to be held in San Fransisco on 11-12 February, 2015. DRR is a part of the SPIE Electronic Imaging conference.
    Posted Oct 10, 2014, 11:54 PM by Adrien Delaye
  • Free handwritten document layout analysis project In this project page, I present the ideas behind our system for predicting the layout of unconstrained online handwritten documents. The full details on the implementation and experimental results is included in the paper "Multi-class segmentation of free-form online documents with Tree Conditional Random Fields" to be published in the International Journal on Document Analysis and Recognition.
    Posted Oct 10, 2014, 11:55 PM by Adrien Delaye
Showing posts 1 - 5 of 18. View more »