Trainable Convolution Filters and Their Application to Face Recognition

—In this paper, we present a novel image classification system that is built around a core of trainable filter ensembles that we call Volterra kernel classifiers. Our system treats images as a collection of possibly overlapping patches and is composed of three components: 1) A scheme for a single patch classification that seeks a smooth, possibly nonlinear, functional mapping of the patches into a range space, where patches of the same class are close to one another, while patches from different classes are far apart—in the L2 sense. This mapping is accomplished using trainable convolution filters (or Volterra kernels) where the convolution kernel can be of any shape or order. 2) Given a corpus of Volterra classifiers with various kernel orders and shapes for each patch, a boosting scheme for automatically selecting the best weighted combination of the classifiers to achieve higher per-patch classification rate. 3) A scheme for aggregating the classification information obtained fo...

• Type: Journal
• Year: 2012
• Where: PAMI
• Authors: Ritwik Kumar, Arunava Banerjee, Baba C. Vemuri, Hanspeter Pfister
• Keywords: Classification Rate, Convolution Kernel, PAMI 2012, Software Engineering, Volterra Kernels