Method adopting image segmentation for automatically testing LED indicator light of automobile instruments

Abstract

The invention discloses a method adopting image segmentation for automatically testing the LED indicator light of automobile instruments and provides a region-growing method based on the maximum between-cluster variance (Otsu's Method). The method comprises the following steps: automatically selecting the centroid in the light-emitting region of the LED light as the seed point to carry out the region-growing; realizing the region segmentation and extraction; and judging whether the brightness and color of the light are correct upon the seed point and the area of the region. The invention can effectively improve the testing accuracy rate and testing efficiency of the LED indicator light of the automobile instruments and provide effective means for the automatic production of the automobileinstruments.

Description

Automated Inspection Method of Automobile Instrument LED Indicators Using Image Segmentation technical field The invention relates to an automatic inspection technology for an automobile meter when it leaves the factory, in particular to an automatic inspection method for an LED indicator light of an automobile meter using image segmentation. Background technique With the improvement of car functions, the number of various indicator lights on the car instrument is increasing, such as turn indicator lights, working status lights, fault lights and warning lights, etc., the number is generally more than ten Many or even dozens, especially the indicator lights of passenger cars and heavy trucks are more in number and richer in function. These indicator lights generally use SMD LEDs at present, and the hardware cost can account for about 1 / 4 to 1 / 3 of the entire instrument, which has become an important part of the car instrument. However, during the production process, these...

AI Technical Summary

Problems solved by technology

However, during the production process, these indicator lights often have errors due to LED damage, manual welding errors, etc., or the lights are not lit at all, or the brightness is too low, or the color is incorrect, so a test for the brightness and color of the indicator lights is required. process

But so far, the inspection of indicator lights generally adopts the polling method, that is, each indicator light is powered on manually or automatically, and the color and brightness of the indicator lights are checked with the naked eye. However, as the number of indicator lights continues to increase, The polling inspection method takes a long time to work, which is likely to cause visual fatigue, resulting in a low inspection accuracy rate and difficult to guarantee product consistency

Images