Abstract
Metal stamping character (MSC) automatic identification technology plays an important role in industrial automation. To improve the accuracy and stability of segmentation and recognition for MSCs, an algorithm based on multi-directional illumination image fusion technology is proposed. First, four grayscale images are taken with four bar-shape directional light sources from different directions. Next, based on the difference in surface grayscale characteristics for the different illumination directions of the surface’s stamped depression regions and flat regions, the image background is extracted and eliminated. Second, the images are fused using the difference processing on the images in the two groups of relative illuminant directions. Third, mean filter, binarization, and morphological closing operations are performed on the fused image to locate and segment the character string in the image, and the characters are normalized by correcting the skew of the segmented character string. Finally, histogram of oriented gradient features and a backpropagation neural network algorithm are employed to identify the normalized characters. Experimental results show that the algorithm can effectively eliminate the interference of factors such as oil stains, rust, oxide, shot-blasting pits, and different background colors and enhance the contrast between MSCs and background. The resulting character recognition rate can reach 99.6%.
Highlights
Characters are one of the main methods for information identification, recording, and storage
The results show that a change in α has little effect on the image fusion result of the target characters
These results show that the recognition rate with the proposed method is suitable for industrial online application, and the recognition rates of HOG1 and HOG3 are better than those of HOG2 and HOG4 because they have higher dimensions d, which mean that the histogram of oriented gradient (HOG) feature contains more information for feature discrimination
Summary
Characters are one of the main methods for information identification, recording, and storage. Metal stamping characters (MSCs) are widely used in the identification of industrial products because they are hard to alter and permanently preserved. The high-quality automation of character recognition on industrial products is highly desirable in the manufacturing and periodic inspection of these products. Inspection is performed at various production stages. It is clear that the earlier method of using human inspectors, misses a considerable number of defects because humans are unsuitable for such simple and repetitive tasks. Automated vision inspection can be a good alternative to reduce human workload and labor costs as well as to improve inspection accuracy and throughput
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
