Soldered ball surface defect detection device and method based on machine vision

Abstract

The invention relates to a device and a method based on machine vision for detecting the surface defects of solder balls in the field of automatic optical detection. An optical imaging system collects chip images, and an image collection system receives the collected chip images, intercepts a single-frame gray image from video stream signals output by the optical imaging system, and stores the single-frame gray image in the form of a two-dimensional integer matrix; an image segmentation module segments the whole two-dimensional integer matrix corresponding to the whole image into subsidiary matrices containing the solder balls, an image characteristic extraction module receives and processes the two-dimensional integer subsidiary matrices output by the mage segmentation module and outputs a one-dimensional floating point vector, and a probability neural network module receives, trains, and tests the one-dimensional floating point vector output by the image characteristic extraction module and divides the solder balls into two categories, namely good solder balls and defective solder balls. The device of the invention has simple structure, the graduation of a characteristic extraction method and a probability neural network is good, and the accuracy is high so as to realize the NDE (Non-Destructive Examination) of the surface defects of the solder balls.

Description

Technical field [0001] The invention relates to a detection device and method in the technical field of optical detection, in particular to a device and method for detecting solder ball surface defects based on machine vision. Background technique [0002] With the development of chip production and packaging technology, the traditional solder pin-based chip production method has been unable to meet the requirements, replaced by solder ball-based surface mount technology, which is typically represented by ball grid array chip BGA. As an important connection part, the quality of the solder balls plays an important role in the quality of the chip. Due to the small size of solder balls, manual visual inspection is not only inefficient, but also has a high false detection rate. Therefore, numerous solder ball quality inspection devices and methods have emerged. [0003] After searching the literature of the prior art, it was found that China Patent Publication No. CN101136346, publis...

AI Technical Summary

Problems solved by technology

Due to the small size of solder balls, manual visual inspection is not only inefficient, but also has a high false detection rate. Therefore, many solder ball quality detection devices and methods have emerged.

[0003] After searching the literature of the prior art, it was found that Chinese Patent Publication No. CN101136346, published on March 5, 2008, patent name: a device for on-line detection and defect identification of chip solder joints and a device for chip packaging, discloses a thermal-based The imaging detection device can conduct online detection of the solder joints after mounting, but it needs to heat the chip and an infrared thermal imager at the same time, and the device is relatively complicated

Chinese patent authorization number CN1306582C, date of authorization March 21, 2007, patent name: Ball grid array semiconductor device quality inspection system based on machine vision, discloses a ball grid array semiconductor device quality optical inspection method, but mainly focuses on the The detection of solder ball height, size, shape and position cannot effectively detect solder ball surface defects

Surface defects of solder balls include surface scratches and surface collapse. Large scratches or collapses will cause poor contact of solder balls and affect chip quality. Therefore, it is necessary to study an optical detection method for surface defects of solder balls

Images