A method for image character detection and identification

Abstract

The invention provides an image character detection and identification method which comprises the following steps: first, making a standard black-and-white image of a corresponding character; second, acquiring a test image in real time, extracting the position of the character and processing the test image into a test black-and-white image; and third, comparing the test black-and-white image obtained from the second step with the standard black-and-white image made in the first step to judge whether the test black-and-white image is qualified. The method can completely solve the problem that image characters cannot be identified in automatic flat-panel television test, promotes realization of automatic detection on flat-panel television core components and improves product quality and labor efficiency.

Description

technical field

[0001] The invention relates to a method for detecting and discriminating image characters, in particular to a method for detecting and discriminating collected image characters suitable for the field of automatic testing of flat-panel TVs. Background technique

[0002] Due to the limitation of incoming materials and production process in the process of processing the core components of flat-panel TVs, the core components after welding will have defects to varying degrees. The existing test and inspection methods are basically manual wiring or a bed of needles connected to the display screen, and the quality judgment of image defects is judged by manual visual inspection. This method has the influence of misjudgment and missed judgment caused by human subjective factors. And with the continuous rise of labor costs, automatic detection is gradually applied. In the automatic detection, it is necessary to detect the collected image characters. The general OCR c...

Images