The Sole Texture's Automatic Identification And Classification Based On The Pattern Identification

The footprint and shoe print is very important evidence which Is easy to be gotten in the case, It is very important in series-parallel case . But because of every local police' s footprint management method is different from each other and the form is single, It makes footprint can not be used like fingerprint in criminal case. So the sole texture' s automatic identification and classification has a great economic significance and social significance.In this paper , based on the analysis of many footprint images and the research work in edge detection field that have been done in recent years by Image Processing Institute of Xi' an Jiaotong University and Dalian Maritime University, the algorithms are brought forward as following:1. the punctuate texture is identified by the image probability method--inertia moment.2. the interlaced texture is identified by detecting the number of edge' s cross dot, based on the wavelet edge detect .3. The shape analysis is used to analyze the main shape of the edge image. Some character is found like length, width, the ratio of length and width, acreage, and so on.4. the flexuous texture and line texture are identified by using he ratio of length and width and detecting the inflexion' s number in the thinning image of the label image.5. the nubbly texture is identified by using the ratio of length and width, the width and detecting the cross dot' s number in the thinning image of the label image.6. the circular texture , the elliptical texture and the nubbly texture are distinguished by using the ratio of length and width and Houghtransform.7. the thin texture in the big nubbly texture is identified by the multiresolution analysis.