Robust string text detection for industrial optical character recognition
Abstract:
A robust string text detection and recognition system is provided to improve the reading performance of sliding-window based OCR solutions (such as histogram of oriented gradient (HOG) OCR and convolutional neural network (CNN) OCR). A search algorithm is created that is robust enough to detect outliers and false detections. A general Text Search algorithm structure is created allows the specification of different constraints/assumptions to guide the search in multiple text lines detection and recognition.
Information query
Patent Agency Ranking
0/0