TY - GEN A1 - Jäger, Matthias A1 - Eberhardt, Jörg A1 - Cunningham, Douglas W. T1 - 3D reconstruction of partial foot scans using different state of the art neural network approaches T2 - Footwear Science N2 - As online shopping continues to grow in popularity, shoes are increasingly being purchased without being physically tried on. This has resulted in a significant surge in returns, causing both financial and environmental consequences. To tackle this issue, several systems are available to measure foot dimensions accurately either in-store or at home. By obtaining precise foot measurements, individuals can determine their ideal shoe size and prevent unnecessary returns. In order to make such a system as simple as possible for the user, only a single image should be sufficient to measure the foot. To make this possible, point clouds from one side of the foot, which are generated by taking a depth image, are to be used. Since these point clouds represent only one side of the foot, the other side has to be generated. For this purpose, different existing state of the art networks were tested and compared to determine which architecture is best suited for this task. After implementing, re-training on our own dataset and testing the different architectures, it can be concluded that the point/transormer-based network SnowflakeNet is the most efficient to be used for our task. KW - Foot measurement KW - Shape completion KW - Shape reconstruction KW - GAN KW - Neural network KW - Machine learning KW - CNN Y1 - 2024 U6 - https://doi.org/10.1080/19424280.2024.2319796 VL - Volume 16 IS - 2 SP - 105 EP - 114 PB - Taylor&Francis ER - TY - GEN A1 - Jäger, Matthias C. A1 - Eberhardt, Jörg A1 - Cunningham, Douglas William T1 - Experimental Analysis of Commercial Optical Methods for Foot Measurement T2 - Sensors N2 - Due to the increasing trend of online shopping, shoes are more and more often bought without being tried on. This leads to a strong increase in returns, which results in a high financial as well as ecological burden. To prevent this, feet can be measured either in the store or at home by various systems to determine the exact dimensions of the foot and derive an optimal shoe size. In this paper, we want to present an overview of the methods currently available on the market for the measurement of feet. The most important commercial systems are classified according to the underlying basic technology. Subsequently, the most promising methods were implemented and tested. The results of the different methods were finally compared to find out the strengths and weaknesses of each technology. After determining the measurement accuracy of the length and width for each measurement method and also comparing the general shape of the 3D reconstruction with the GT, it can be said that the measurement using a ToF sensor is currently the most robust, the easiest and, among other methods, the most accurate method. KW - foot measurement KW - time of flight KW - structured light KW - image processing KW - shape completion Y1 - 2022 U6 - https://doi.org/10.3390/s22145438 SN - 1424-8220 VL - 22 IS - 14 ER -