An Analysis of the Effect of Gaussian Error in Object Recognition.
Abstract
Object recognition is complicated by clutter, occlusion, and sensor error. Since pose hypotheses are based on image feature locations, these effects can lead to false negatives and positives. In a typical recognition algorithm, pose hypotheses are tested against the image, and a score is assigned to each hypothesis. We use a statistical model to determine the score distribution associated with correct and incorrect pose hypotheses, and use binary hypothesis testing techniques to distinguish between them. Using this approach we can compare algorithms and noise models, and automatically choose values for internal system thresholds to minimize the probability of making a mistake. Alignment, Geometric hashing, Object recognition, Gaussian error.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1994
- Accession Number
- ADA279822
Entities
People
- Karen B. Sarachik
Organizations
- Massachusetts Institute of Technology