Method and device for human body feature analysis and based on barefoot or stocking-wearing footprint images
A feature analysis and footprint technology, applied in the fields of digital image processing, computer vision and criminal investigation, can solve problems affecting personal characteristics, human error, manual measurement, qualitative inference, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0070] Embodiment one: a kind of method based on the personal characteristics analysis of barefoot or wearing socks footprint image, comprises the following steps:
[0071] S1. Perform multi-layer pressure surface extraction on barefoot or socks footprint images;
[0072] S1.1. Preprocessing the barefoot or socks footprint image: filter the barefoot or socks footprint image, the filter formula of the image is as follows:
[0073] I=F*G
[0074] I(i,j)=Σ m Σ n F(i,j)G(i-m,j-n) (1)
[0075] Among them, * represents convolution, F represents the original shoe footprint image, G represents the filter, I represents the filtered footprint image, (i, j) represents the current pixel position, m and n represent the filter window in the x and y directions respectively the size of;
[0076] Specifically, the filter uses a two-dimensional Gaussian filter:
[0077] G ( u , v ) = ...
Embodiment 2
[0125] Embodiment 2: The technical solution is the same as Embodiment 1, the difference is that step S3.4 is to establish a mathematical model of the aspect ratio of gender and footprint:
[0126] Footprint aspect ratio = foot length / foot width (8)
[0127] The length-to-width ratios of male and female footprints are respectively subject to normal distribution and The overall G 3 , G 4 , where μ 3 , μ 4 G respectively 3 , G 4 the mean value of G respectively 3 , G 4 Variance; refer to the formula (6) to calculate the test footprint aspect ratio and the overall G 3 , G 4 Mahalanobis distance d 3 、d 4 ; Use the formula (9) to calculate and obtain the gender characteristics of the footprint owner;
[0128] r ∈ G 3 , d 3 ≤ ...
Embodiment 3
[0130] Embodiment 3: The technical solution is the same as Embodiment 1, and the difference is that step S3.4 is: establishing a mathematical model of sex and the pressure change rate between adjacent layers of the multi-layer pressure surface: denote S i , i=1, 2,..., n, is the area of the footprint pressure surface of the i-th layer, and the relative change rate of the footprint pressure surface area between adjacent layers
[0131] ΔS i =(S i+1 -S i ) / S i , i=1, 2, ..., n-1 (10)
[0132] Its coefficient of variation is
[0133] cv=σ / μ (11)
[0134] Among them, μ and σ are respectively {ΔS i} mean and variance;
[0135] Given a threshold T=0.3, and the coefficient of variation cv is greater than the threshold T, it is judged that the owner of the footprint is male, otherwise it is judged that the owner of the footprint is female.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com