Function Based Generic Recognition for Multiple Object Categories

نویسندگان

  • Melanie Sutton
  • Louise Stark
  • Kevin Bowyer
چکیده

In function based object recognition an object category is represented by knowledge about object function Function based approaches are important because they provide a principled means of constructing generic recognition systems Our work concentrates speci cally on the relation between shape and function of rigid D objects Recognition of an observed shape is performed by reasoning about the function that it might serve Previous e orts have dealt with only a single basic level object category A number of important issues arise in extending this approach to deal with multiple basic level categories One issue is whether the knowledge about object function can be organized into general primitive chunks that are re usable across di erent categories Another issue is how to e ciently index the knowledge base so as to avoid exhaustive testing of an object shape against each known category In order to better explore these issues we have implemented a system whose domain of competence is a number of di erent object categories within the superordinate categories furniture and dishes The performance of this system has been evaluated on a database of over shapes

برای دانلود 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

Generic Object Recognition Using CAD-Based Multiple Representat ions

Real-world applications of computer vision usually involve a variety of object models making a single model representation somewhat inadequate for object recognition. Multiple representations, on the other hand, allow different matching strategies to be applied for the same object, or even for different parts of the same object. This paper is concerned with the use of CAD-derived hierarchical m...

متن کامل

Recognizing multiple objects based on co-occurrence of categories

Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple categories often appear together in an image. In this paper, we present a novel method for object recognition that explicitly deals with objects of multiple categories coexisting in an image. Furthermore, our proposed method a...

متن کامل

Recognizing Multiple Objects via Regression Incorporating the Co-occurrence of Categories

Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple categories often appear together in an image. In this paper, we present a novel method for object recognition that explicitly deals with objects of multiple categories coexisting in an image. Furthermore, our proposed method a...

متن کامل

Segmentation Assisted Object Distinction for Direct Volume Rendering

Ray Casting is a direct volume rendering technique for visualizing 3D arrays of sampled data. It has vital applications in medical and biological imaging. Nevertheless, it is inherently open to cluttered classification results. It suffers from overlapping transfer function values and lacks a sufficiently powerful voxel parsing mechanism for object distinction. In this work, we are proposing an ...

متن کامل

Comparison of Appearance Based Methods for Generic Object Recognition

In this paper, we present a large-scale examination of different appearance-based, segmentation-free classification methods for their usability in generic object recognition. Generic object recognition is a method to handle never before seen objects in classification by a hierarchical approach with a coarse-to-fine graduation. Unknown objects are only classified into coarse categories and rejec...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006