Evaluation of Quantization Error in Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Advances in neural information processing systems 2
The nature of statistical learning theory
The nature of statistical learning theory
Object Matching Using Deformable Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Support Vector Machines: Training and Applications
Support Vector Machines: Training and Applications
A multimodal approach to time-invariant scene retrieval from single overhead image
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
On transforming statistical models for non-frontal face verification
Pattern Recognition
On statistical approaches to target silhouette classification in difficult conditions
Digital Signal Processing
Fusion and mining spatial data in cyber-physical space with dynamic logic of phenomena
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
| Hi-index | 0.14 |
The problem of screening images of the skies to determine whether or not aircraft are present is of both theoretical and practical interest. After the most prominent signal in an infrared image of the sky is extracted, the question is whether the signal corresponds to an aircraft. Common approaches calculate the degree of similarity of the shape of the $2D$ signal with a model aircraft using a similarity measure such as Euclidean distance, and make a decision based on whether the degree of similarity exceeds a (prespecified) threshold. We present a new approach that avoids metric similarity measures and the use of thresholds, and instead attempts to learn similarity measures like those used by humans. In the absence of sufficient real data, the approach allows us to specifically generate an arbitrarily large number of training exemplars projecting near the classification boundary. Once trained on such a training set, the performance of our neural network-based system was comparable to that of a human expert and far better than a network trained only on the available real data. Furthermore, the results were considerably better than those obtained using an Euclidean discriminator.