Object Recognition and Categorization Using Modal Matching

نویسندگان

  • Stan Sclaroff
  • Alex P. Pentland
چکیده

Recently we have proposed a new method for establishing correspondences and computing canonical descriptions [6], based on the idea of describing objects by their generalized symmetries, as defined by the object’s vibration or deformation modes. In this paper we extend this method to the problems of object recognition and categorization. Examples of recognizing hand tools and airplanes are shown.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Modal Matching for Correspondence and Recognition

--Modal matching is a new method for establishing correspondences and computing canonical descriptions. The method is based on the idea of describing objects in terms of generalized symu&ries, as defined by each object’s eigenmodes. The resulting modal description is used for object recognition and categorization, where shape simihuities are expressed as the amounts of modal deformation energy ...

متن کامل

A Reinforcement Learning Approach for Attentional Control Based on a Multi-Modal Sensory Feedback

In this work we present a reinforcement learning framework that integrates the processing of information acquired from a multi-modal sensory system (vision and touch). Visual and Haptic features extracted selectively from input buffers are used for object categorization. In this way we can relate sensed information to actions, abstracting and providing a feedback (identification/recognition and...

متن کامل

Categorization via Agglomerative Correspondence Clustering

This paper presents computationally efficient object detection, matching and categorization via Agglomerative Correspondence Clustering (ACC). We implement ACC for feature correspondence and object-based image matching exploiting both photometric similarity and geometric consistency from local invariant features. Objectbased image matching is formulated here as an unsupervised multi-class clust...

متن کامل

A comparison of the effects of depth rotation on visual and haptic three-dimensional object recognition.

A sequential matching task was used to compare how the difficulty of shape discrimination influences the achievement of object constancy for depth rotations across haptic and visual object recognition. Stimuli were nameable, 3-dimensional plastic models of familiar objects (e.g., bed, chair) and morphs midway between these endpoint shapes (e.g., a bed-chair morph). The 2 objects presented on a ...

متن کامل

Category Training Induces Cross-modal Object Representations in the Adult Human Brain

The formation of cross-modal object representations was investigated using a novel paradigm that was previously successful in establishing unimodal visual category learning in monkeys and humans. The stimulus set consisted of six categories of bird shapes and sounds that were morphed to create different exemplars of each category. Subjects learned new cross-modal bird categories using a one-bac...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994