Steel seal character image preprocessing method

Abstract

The invention discloses a steel seal character image preprocessing method, which comprises the following steps of: firstly, normalizing an acquired original grayscale image, and mapping a processed image I1 to a 0-255 interval to obtain an image I2; calculating K by using I2, and performing enhancement processing on each image point (x, y) by using a K value to obtain a gray value I''(x, y) of each point in the enhanced gray image I''; according to the method, calculating the K value according to the gray scale condition of the original image, so that the comparison condition of the original image can be directly reflected, the enhancement mapping function can be adjusted in a self-adaptive mode during enhancement processing, and the enhancement processing effect on the image is obvious; and therefore, the contrast between the background and the target object is effectively improved.

Description

technical field [0001] The invention relates to the field of image preprocessing, in particular to a method for preprocessing a stamped character image. Background technique [0002] Image preprocessing can effectively improve the quality of the original image, and plays a key role in the accuracy of subsequent foreground segmentation and target recognition. Common image preprocessing methods include: image filtering, denoising, enhancement, etc. For the original image with poor contrast, Image enhancement processing is particularly important. Existing image enhancement methods lack adaptive adjustment to images. When processing low-contrast images, it is easy to cause image mis-segmentation. In fact, low-contrast images widely exist in industrial inspection processes. Among them, The more typical low-contrast images are stenciled character images. Stenciled coded characters (such as part codes, car VIN codes) are stamped / engraved on the metal surface, which are the same col...

AI Technical Summary

Problems solved by technology

[0002] Image preprocessing can effectively improve the quality of the original image, and plays a key role in the accuracy of subsequent foreground segmentation and target recognition. Common image preprocessing methods include: image filtering, denoising, enhancement, etc. For the original image with poor contrast, Image enhancement processing is particularly important. Existing image enhancement methods lack adaptive adjustment to images. When processing low-contrast images, it is easy to cause image mis-segmentation. In fact, low-contrast images widely exist in industrial inspection processes. Among them, The more typical low-contrast images are stenciled character images. Stenciled coded characters (such as part codes, car VIN codes) are stamped / engraved on the metal surface, which are the same color as the metal surface, and often only show subtle differences in grayscale when imaging, namely : The gray scale of the characters is low, while the gray scale of the metal surface is high; the contrast between the two is not obvious; at the same time, due to the high reflectivity of the surface of the metal workpiece, the workpiece is deformed during processing; while the characters are prone to burrs and differences in engraving depth , these will cause contrast differences in character images on different workpieces. At this time, conventional image preprocessing methods cannot effectively improve the quality of low-contrast images

Images