2014 · 14 citations · 27 references
ComputingComputer ScienceFrenchComputer VisionMachine LearningNatural Language ProcessingDeep LearningDocument Image AnalysisOptical Character RecognitionPattern RecognitionWord RecognitionBenchmark DatasetsHandwriting RecognitionHandwritten Character RecognitionNoisy Image RecognitionText Line DetectionText Line Segmentation
We propose a state-of-the-art system for recognizing real-world handwritten images exposing a huge degree of noise and a high out-of-vocabulary rate. We describe methods for successful image demising, line removal, deskewing, deslanting, and text line segmentation. We demonstrate how to use a HMM-based recognition system to obtain competitive results, and how to further improve it using LSTM neural networks in the tandem approach. The final system outperforms other approaches on a new dataset for English and French handwriting. The presented framework scales well across other standard datasets.
27
IFN/ENIT: database of handwritten arabic words
Mario Pechwitz, Samia Snoussi Maddouri, Volker Märgner et al. · 2002 · 428 citations