Learn More
Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary(More)
—Spotting keywords in handwritten documents without transcription is a valuable method as it allows one to search, index, and classify such documents. In this paper we show that keyword spotting based on bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets can successfully be applied on online handwritten documents with non-text content. It(More)
Congenital heart defects affect almost 1% of human newborns. Recently, mutations in Notch ligands and receptors have been found to cause a variety of heart defects in rodents and humans. However, the molecular effects downstream of Notch are still poorly understood. Here we report that combined inactivation of Hey1 and HeyL, two primary target genes of(More)
—Handwritten word spotting aims at making document images amenable to browsing and searching by keyword retrieval. In this paper, we present a word spotting system based on Hidden Markov Models (HMM) that uses trained subword models to spot keywords. With the proposed method, arbitrary keywords can be spotted that do not need to be present in the training(More)
—The automatic transcription of historical documents is vital for the creation of digital libraries. In order to make images of valuable old documents amenable to browsing, a transcription of high accuracy is needed. In this paper, two state-of-the art recognizers originally developed for modern scripts are applied to medieval documents. The first is based(More)
Proteins containing the evolutionarily conserved SET domain are involved in regulation of eukaryotic gene expression and chromatin structure through their histone lysine methyltransferase (HMTase) activity. The Drosophila SU(VAR)3-9 protein and related proteins of other organisms have been associated with gene repression and heterochromatinization. In(More)
—Segmenting page images into text lines is a crucial pre-processing step for automated reading of historical documents. Challenging issues in this open research field are given e.g. by paper or parchment background noise, ink bleed-through, artifacts due to aging, stains, and touching text lines. In this paper, we present a novel binarization-free line(More)
Hes and Hey genes are the mammalian counterparts of the Hairy and Enhancer-of-split type of genes in Drosophila and they represent the primary targets of the Delta-Notch signaling pathway. Hairy-related factors control multiple steps of embryonic development and misregulation is associated with various defects. Hes and Hey genes (also called Hesr, Chf, Hrt,(More)
For retrieving keywords from scanned handwritten documents, we present a word spotting system that is based on character Hidden Markov Models. In an efficient lexicon-free approach, arbitrary keywords can be spotted without pre-segmenting text lines into words. For a multi-writer scenario on the IAM off-line database as well as for two single writer(More)
The fungus Fusarium fujikuroi causes "bakanae" disease of rice due to its ability to produce gibberellins (GAs), but it is also known for producing harmful mycotoxins. However, the genetic capacity for the whole arsenal of natural compounds and their role in the fungus' interaction with rice remained unknown. Here, we present a high-quality genome sequence(More)