2016/04/01 by Sebastian Sudholt, Sudholt, Sebastian, Fink, Gernot A.
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction
paper · pdf · doi:10.48550/arxiv.1604.00187
openalex publication_date 2016/04/01 · openalex created_date 2017/09/15 · openalex updated_date 2026/07/28
In recent years, deep convolutional neural networks have achieved state of\nthe art performance in various computer vision task such as classification,\ndetection or segmentation. Due to their outstanding performance, CNNs are more\nand more used in the field of document image analysis as well. In this work, we\npresent a CNN architecture that is trained with the recently proposed PHOC\nrepresentation. We show empirically that our CNN architecture is able to\noutperform state of the art results for various word spotting benchmarks while\nexhibiting short training and test times.\n