Detection and removal of form lines from bill images

Characters often overlap with form lines, which will greatly affect the performance of recognition system. A line detectionand removal algorithm is directly presented based on gray images, while many other algorithms are based on bi-level images. Line posi-tions and cross-points of characters and lines were first detected with edge information. Then pixels interior to a line were divided intotwo sets: protecting-set and erasing-set by crossing shape analysis. Finally, the gray level of the pixels in erasing-set was set to theirlocal background color. Experiments on 806 real life courtesy amount images demonstrate the efficient of this algorithm, and the reco-gnition rate is up to 91.4%.