Integrated Circuit Packaging Defect Analysis and Deep Learning Detection Method

Defects can be regarded as targets when using a target detection algorithm. Compared with conventional targets, chip defects have distinct characteristics. Their sizes are variable, and most defects are small in size. Defects lack texture features and can be viewed as anomalies relative to the background. Some defects exhibit elongated and strip-like characteristics, making the direct application of existing target detection algorithms less than ideal. In this article, we incorporate these characteristics as prior knowledge in the design and improvement of the target detection network structure. We propose a deep learning detection network, you only look once—with defect attention (YOLO-WDA), specifically tailored for chip defect data, using three targeted improvement methods. An anomaly attention mechanism (AAM) highlights defect features by contrasting information with normal chips. An improved module for small target defects uses the focus operation to retain more fine-grained information, combined with ghost convolution to adjust the channel redundancy and reduce network parameters. An Ameba convolution detection (AMBC-Detect) head can better capture continuous features such as curves. In experiments conducted on two chip datasets, YOLO-WDA achieved mean of average precision (mAP) scores of 65.5 and 43.2, outperforming the benchmark model, YOLOv8, by 2.7 and 4.8, respectively. Our model also outperforms other classical algorithms. Datasets are available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://pan.baidu.com/s/1vU3hkPUYSrzVHDKgGgt1MA?pwd=1</uri> yja