Multiple routes to object matching from different viewpoints: mental rotation versus invariant features.
نویسندگان
چکیده
Previous research has shown that object recognition from different viewpoints often yields strong effects of viewpoint. However, for some objects and experimental paradigms almost complete viewpoint invariance is obtained. This suggests the existence of multiple routes to object recognition. In this study we further strengthen this notion by designing two different conditions using the same experimental paradigm (simultaneous matching) and highly similar objects (multiblock figures). In the first condition (involving a handedness violation), strong effects of viewpoint were obtained. In the second condition (involving an invariance violation), the effects of viewpoint were negligible. This result illustrates that asking under what circumstances object recognition is viewpoint dependent or independent is more fruitful than attempting to show that object recognition is either viewpoint dependent or independent.
منابع مشابه
Pose Invariant Generic Object Recognition with Orthogonal Axis Manifolds in Linear Subspace
This paper addresses the problem of pose invariant Generic Object Recognition by modeling the perceptual capability of human beings. We propose a novel framework using a combination of appearance and shape cues to recognize the object class and viewpoint (axis of rotation) as well as determine its pose (angle of view). The appearance model of the object from multiple viewpoints is captured usin...
متن کاملCategorization 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 کاملLearning an object from multiple views enhances its recognition in an orthogonal rotational axis in pigeons
In the natural environment, most objects are seen from several different viewpoints. We explored the nature of recognition after training with multiple views and compared it to recognition after training with only one view. Pigeons were taught with either five views or one view of each of four single-geon objects. Pigeons trained with five views responded more accurately to novel views of an ob...
متن کاملA New RSTB Invariant Image Template Matching Based on Log-Spectrum and Modified ICA
Template matching is a widely used technique in many of image processing and machine vision applications. In this paper we propose a new as well as a fast and reliable template matching algorithm which is invariant to Rotation, Scale, Translation and Brightness (RSTB) changes. For this purpose, we adopt the idea of ring projection transform (RPT) of image. In the proposed algorithm, two novel s...
متن کاملIntegration of Multi-view Panoramic Range Data Using Global Features
In this paper, we propose a robust and efficient method to integrate the multi-view panoramic range data using the global features acquired from panorama range data. In our approach, the planes with similar normal vectors are handled as one group, and multiple plane groups are extracted from the multi-view panoramic range data. Next, the transformation ( r e tation and translation) parameters b...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Perception
دوره 30 9 شماره
صفحات -
تاریخ انتشار 2001