Abstract
A smartphone contains many critical components that are produced in highly automated and precisely monitored facilities throughout the complex manufacturing process. Even with the rapid development in the smartphone manufacturing industry today, the physical buttons are still existing on the smartphone because of the crucial importance of both in terms of their functionality and role. The smartphone’s physical buttons are small in size and have non-planar and shiny surfaces that lead to difficulty in detecting defects not only with human eyes but also with most AOI systems. Besides, most defects are tiny, with low contrast which is a huge challenge for deep learning models-based defect detection. To overcome these challenges, we propose a novel framework based on machine vision named highlight defect region by using higher-order singular value decomposition of wavelet subband-based tensor (HHoWST) for real-time smartphone’s physical buttons quality inspection. First, a modern image acquisition system is designed to obtain a high-quality smartphone’s physical button image dataset with a total of 500 images containing 13,472 samples of six defect types. Next, a wavelet subband-based third-order tensor of the smartphone’s physical button color image is constructed. Finally, higher-order singular value decomposition is proposed to estimate the components that contain the global illumination information and highlight the defective regions of the image. The experiments performed on HHoWST images reveal that our proposed method significantly improves the defect detection efficiency of deep learning models, such as SSD, Faster R-CNN, and YOLOv5, especially the performance in detecting the tiny defect types.
Highlights
INTRODUCTIONThe smartphone manufacturing industry has grown rapidly. A smartphone company depends on its own manufacturing alone and has a lot of suppliers that it relies on for procuring components for assembly
In recent years, the smartphone manufacturing industry has grown rapidly
We propose a method to construct a tensor called wavelet subbands-based tensor (WST), which is based on the combination of the wavelet representation and tensor theory to express the image information in high-order dimensions
Summary
The smartphone manufacturing industry has grown rapidly. A smartphone company depends on its own manufacturing alone and has a lot of suppliers that it relies on for procuring components for assembly. By using image processing algorithms embedded in the image preprocessing part of the AOI system, this favorable information (the defect feature) can be enhanced, whereas the redundant information is eliminated It results in the improvement of the defect recognition performance of the AOI system. These methods can clarify the features of the defect on the product image They only focus on different frequency subbands separately, lead to an unsatisfactory inspection recognition rate. Image preprocessing, based on the combination of the wavelet transform and tensor theory, we propose a defect enhancement method called the highlight defect region by using higher-order singular value decomposition of wavelet subband-based tensor (HHoWST) to highlight the defect region on the smartphone's physical button image.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have