OCR-based cable character detection method and system

Abstract

The invention discloses an OCR-based cable character detection method and system, and relates to the field of image detection and recognition. The method includes acquiring characters on a normal cable sheath, and taking each segment of characters as an element; all elements are sequentially connected as Two-way linked list, based on the characters in the two-way linked list to generate templates; the template is used as a training sample to train the classifier; the characters on the cable to be detected are input into the trained classifier, and the classifier uses the characters on the cable to be detected The characters are compared and recognized with the characters in the template. If the characters on the cable to be tested can be recognized, it means that the characters on the cable to be tested are not defective. Otherwise, the characters on the cable to be tested are defective. The invention can quickly realize the detection of whether the characters printed on the cable have defects, replaces the manual detection, and reduces the production cost.

Description

technical field [0001] The invention relates to the field of image detection and recognition, in particular to an OCR-based cable character detection method and system. Background technique [0002] During the production process of the optical cable, for the characters on the appearance of the sheath, when the printing block is improperly installed or the embossing is too shallow, the characters are not displayed clearly, and some characters are missing, resulting in incomplete display of the cable model, length and other information, which affects the later laying construction. , The customer experience is damaged; when the printing machine imprints too deeply, the cable core sleeve is stressed, causing abnormal fiber attenuation and seriously affecting product quality. [0003] The existing character detection method is manual detection, relying on the operator to observe and identify the character quality on the surface of the sheath with the naked eye. When the productio...

AI Technical Summary

Problems solved by technology

[0002] During the production process of the optical cable, for the characters on the appearance of the sheath, when the printing block is improperly installed or the embossing is too shallow, the characters will not be displayed clearly, and some characters will be missing, resulting in incomplete display of the cable model, length and other information, which will affect the later laying construction. , the customer experience is damaged; when the printing machine imprints too deeply, the cable core sleeve is stressed, resulting in abnormal fiber attenuation, which seriously affects product quality

[0003] The existing character detection method is manual detection, relying on the operator to visually observe and identify the character quality on the surface of the sheath. When the production speed of the optical cable sheath is fast, the detection speed of the operator is difficult to keep up, and the optical cable production method is continuous. Continuous detection will cause fatigue, and it is easy to miss detection. At the same time, different operators have different subjective consciousness, and it is difficult to unify the detection standards, which limits the production efficiency of optical cables, makes it difficult to improve product quality, and keeps rising labor costs.

Images