A PDF417 Angle Automatic Detection Algorithm under Complex Background

It is extremely prerequisite to rotate collected image to the horizontal for automatic identification of PDF417 bar code, which is very sensitive to the skew angle. However, the existing skew angle detection methods are defective because of computationally expensive or high complexity. Here, a new tool mathematical morphology which is useful for image processing is used to extract PDF417 from complex background, with PDF417's character that the start symbol, the stop symbol and the edge of the module presents straight lines. And morphological opening operation played an important role to detect the lines. At last, Combined with genetic algorithm, these straight lines are extracted, and then the image angle is obtained. Time spending on different images keeps to about only 0.45s, and the precision is basically around 0.1° . Experimental results show that the algorithm's computing time is little and precision is high.