PXPan Xiao

Pan Xiao

*This is an algorithmically generated author record based on publicly available information.

Pan Xiao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multiscale GAN With Region Adaptive Schemes for Online Inspection of Fabric Flexographic Printing Labels

    by Jinliang Long, Xueshen Lan, Shule Yan, Yinghong Zhou, Pan Xiao, Shaoqiu Xu, Shuang Wang, Nian Cai

    Online inspection of flexographic printing labels (FPLs) is significant for preventing batch misprints to ensure mass production quality. In this paper, an online inspection system is designed for fabric FPLs, in which a multi-scale generative adversarial network (GAN) framework with several region adaptive schemes is proposed to inspect the fabric FPL images acquired by the designed hardware system. To address the scarcity of defective samples in real production, the framework only employs qualified FPL samples to train the GAN template generators for generating the templates. Different from previous template generators, the framework incorporates skip connections and a multi-scale architecture to improve the template representation ability. To deal with tensions in the FPL substrates and to capture subtle defects, several region adaptive schemes are designed for the inspection stage, involving statistical region subtracter (SRS), region adaptive thresholding (RAT) and region defect assessment (RDA). Specifically, during inspection, the inspected FPL is adaptively divided into the character and background regions, which are dealt with these region adaptive schemes. Experimental results demonstrate that the proposed framework achieves the fabric FPL inspection performance of 0.1% omission rate and 1.8% error rate at a reasonable speed of 45ms per sample, which can meet with the online inspection requirements for real production.


  • Adaptive Hybrid Framework for Multiscale Void Inspection of Chip Resistor Solder Joints

    by Pan Xiao, Meng Xiao, Nian Cai, Baojun Qiu, Shuai Zhou, Han Wang

    During reflow soldering, voids inevitably emerge inside the solder joints of chip resistors, which will influence the reliability of the electronic device. In this paper, an adaptive hybrid framework is proposed for multi-scale void inspection of chip resistor solder joints. First, an adaptive partition scheme is proposed to adaptively divide the image of the chip resistor solder joint into two regions, which correspond to the solder beneath the chip resistor body (Region 1) and the solder fillet (Region 2). Then, the voids in the two regions are separately inspected by two proposed adaptive inspection methods. One is that the multi-scale convolution with adaptive circular kernels, guided filtering, and thresholding segmentation is proposed to inspect the voids in Region 1. The other is that an improved active contour model is proposed to inspect the voids in Region 2, which incorporates the gray adaptive strategy and shape prior of the void. Finally, the shape factor and average gray strategy are utilized for void fine inspection of the chip resistor solder joint. Experimental results indicate that the proposed framework is superior to some existing methods, with an inspection performance of 0.9069 average Dice coefficient, 0.9907 F1 Score, and 98.51% Accuracy at a reasonable inspection speed.