Showing papers by "Laurent Heutte published in 2015"
TL;DR: A query by string word spotting system able to extract arbitrary keywords in handwritten documents, taking both segmentation and recognition decisions at the line level, with the superiority of the proposed framework over the classical GMM–HMM and standard HMM hybrid architectures.
Abstract: In this paper, we propose a query by string word spotting system able to extract arbitrary keywords in handwritten documents, taking both segmentation and recognition decisions at the line level. The system relies on the combination of a HMM line model made of keyword and non-keyword (filler) models, with a deep neural network that estimates the state-dependent observation probabilities. Experiments are carried out on RIMES database, an unconstrained handwritten document database that is used for benchmarking different handwriting recognition tasks. The obtained results show the superiority of the proposed framework over the classical GMM---HMM and standard HMM hybrid architectures.
28 citations
23 Aug 2015
TL;DR: This paper proposes an unsupervised, segmentation-free pattern spotting system that takes advantage of the most recent powerful compression and distance approximation techniques to efficiently index the great number of sub-windows produced by sliding windows and allows to retrieve small sized queries in a large indexed corpus.
Abstract: Pattern spotting consists of retrieving the most similar graphical patterns from a collection of document images. Inspired by the recent advances in computer vision and word spotting techniques, we propose in this paper an unsupervised, segmentation-free pattern spotting system. Overall, the system includes a powerful patch-based framework, the bag of visual word model with an offline sliding window mechanism to avoid heavy computational burden during the retrieval process. Our system takes advantage of the most recent powerful compression and distance approximation techniques (product quantization and asymmetric distance computation) to efficiently index the great number of sub-windows produced by sliding windows and allows to retrieve small sized queries in a large indexed corpus.
4 citations
11 Mar 2015
TL;DR: A simple yet efficient zero-shot learning algorithm that can learn a query-adapted distance function from a single image or from a few images, hence improving the quality of the retrieved images and is hence more applicable in real world use cases.
Abstract: This paper introduces a new distance function for comparing images in the context of content-based image retrieval. Given a query and a large dataset to be searched, the system has to provide the user – as efficiently as possible – with a list of images ranked according to their distance to the query. Because of computational issues, traditional image search systems are generally based on conventional distance function such as the Euclidian distance or the dot product, avoiding the use of any training data nor expensive online metric learning algorithms. The drawback is that, in this case, the system can hardly cope with the variability of image contents. This paper proposes a simple yet efficient zero-shot learning algorithm that can learn a query-adapted distance function from a single image (the query) or from a few images (e.g. some user-selected images in a relevance feedback iteration), hence improving the quality of the retrieved images. This allows our system to work with any object categories without requiring any training data, and is hence more applicable in real world use cases. More interestingly, our system can learn the metric on the fly, at almost no cost, and the cost of the ranking function is as low as the dot product distance. By allowing the system to learn to rank the images, significantly and consistently improved results (over the conventional approaches) have been observed on the Oxford5k, Paris6k and Holiday1k datasets.
2 citations