作者: Padmanabhan Soundararajan , Matthew Boonstra , Vasant Manohar , Valentina Korzhova , Dmitry Goldgof
DOI: 10.1007/11949619_74
关键词: Domain (software engineering) 、 Evaluation strategy 、 Optical character recognition 、 Computer science 、 Natural language processing 、 Word error rate 、 Metric (unit) 、 Baseline (configuration management) 、 Image processing 、 Artificial intelligence 、 Speech recognition 、 CLIPS
摘要: In this work, we present a recently developed evaluation framework for video OCR specifically English Text but could well be generalized other languages as well. Earlier works include the development of an strategy text detection and tracking in video, work is natural extension. We sucessfully port use ASR metrics used speech community here domain. Further, also show results on small pilot corpus which involves 25 clips. Results obtained are promising believe that good baseline will encourage future participation such evaluations.