Shoe Prints Identification And Classification Methods Based On Texture And Shape Characteristics

In criminal case investigation, footprints and shoe prints taken from the case spot are important in series and parallel cases . Since every local police has different footprint management methods, and only adopts manual operation, footprints can not be used like the fingerprints in the investigation criminal case. It is necessary to find a kind of image processing method under this background, to make use of the characteristics of fast speed of computers, and to carry out shoe prints identification and classification automatically , and to play an important role in criminal investigation.In this dissertation, the concrete analysis of the classification requests of shoe prints and the actual pictures are carried out, then based on the research works in image field that have been done in recent years by Dalian Maritime University, the algorithms are brought forward as following:1. The initial classification of the shoe prints by the method of a characteristic quantity which got from the Laws template convolution the image.2. The line texture is identified precisely be making use of the auto-registration of the magnitude spectra.3. After getting the object by means of Top_hat transform. The interlaced textures are identified by detecting cross dots in the thinned image of the edges; the dot textures are labeled image of the image object, and they are identified by the shape characteristics such as area, ratio of length and width.4. The edge images are labeled after the Canny operation and the false characteristics caused of the noise such as the hair are eliminated. The wave-shape textures are identified by means of the chain codes.The polygon textures and the circular textures are distinguished by making use of the circular degree and the ratio of the average value and the maximum value after the close area projecting.