Classification Of Sole Patterns From A 3-dimensional Shoe Model And Module Design

Currently, most studies of sole pattern classification are limited to processing two-dimensional images, and there are a variety of methods to identify the type of flat sole patterns. With the development of engineering technology, point cloud data which is collected by a laser scanner has been more and more frequently used as a representation format of 3-dimensional (3D) shapes, and has been widely used in many application areas such as reverse engineering, medical image processing and so on. This paper is composed of two parts:The first part is to classify the sole patterns from a 3D shoe model which is comprised of scattered point cloud data. Sole patterns can be divided into six categories based on the texture of each pattern, including dot texture, blocky texture, wavy texture, inter-wavy texture, circular texture, and linear texture. The point cloud data is sliced into a number of layers, and the unordered data points in each layer are projected onto a viewing plane to get a 2D shoeprint which is comprised of scattered point cloud data. A single texture element is gotten by region growing from the 2D shoeprint. The single texture element can be classified into two types, non-closed curve and closed curve, by detecting if there are point cloud data in each external unit of the region and looking for the nearest point cloud data. Finally, we can identify the type of the texture element into one of the six categories by analyzing its geometrical characteristics.The second part details how to use Microsoft Active Data Objects (ADO) and Visual C++ to manage database operations, and how to design each module of system framework under Visual C++ 6.0. We create a shoe database in SQL Sever 2000 and perform various database operations under Visual C++ 6.0, such as insert operation, update operation, delete operation and so on.