Search

Feature matching in omnidirectional vision systems is a challenging problem, mainly because complicated optical systems make the theoretical modelling of invariance and construction of invariant feature descriptors hard or even impossible. In this paper, we propose learning invariant descriptors using a training set of similar and dissimilar descriptor pairs.We use the similarity-preserving hashing framework, in which we are trying to map the descriptor data to the Hamming space preserving the descriptor similarity on the training set. A neural network is used to solve the underlying optimization problem. Our approach outperforms not only straightforward descriptor matching, but also state-of-the-art similarity-preserving hashing methods. more...

Artificial General Intelligence will not be general without computer vision. Biologically inspired adaptive vision models have started to outperform traditional pre-programmed methods: our fast deep / recurrent neural networks recently collected a string of 1st ranks in many important visual pattern recognition benchmarks: IJCNN traffic sign competition, NORB, CIFAR10, MNIST, three ICDAR handwriting competitions. We greatly profit from recent advances in computing hardware, complementing recent progress in the AGI theory of mathematically optimal universal problem solvers. more...

We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark. more...