Design of an LED-based sensor system to distinguish human skin from workpieces in safety applications

Abstract

Commercial light curtains use a technique known as muting to differentiate between work pieces and other objects (e.g., human limbs) based on precise model knowledge of the process. At manually fed machinery (e.g., bench saws), such precise models cannot be derived due to the way the machinery is used. This paper presents a multispectral scanning sensor to classify an object's surface material as a new approach for the problem. The system is meant to detect the presence of limbs and therefore optimized for human skin detection. Evaluation on a test set of skin and (wet) wood samples showed a sufficiently high reliability with respect to safety standards.

Design of an Active Multispectral SWIR Camera System for Skin Detection and Face Verification

“…In our previous work, we presented an active multispectral point sensor for contactless skin detection which can be used for both safety and security applications, as well as a "proof of concept" of an active multispectral imaging system [16,17]. Both the sensor and the imaging system acquire a "spectral signature" of object surfaces: a specific combination of remission intensities in distinct, narrow wavebands that is used for the classification of the object's surface material.…”

Material classification through distance aware multispectral data fusion

“…In this work, the proposed multispectral point sensor is the most promising approach. Since then, an advanced design concept for such a sensor system as well as a prototypical implementation was developed [2].…”

“…As exemplified in figure 6, when the ratio of two arbitrary Gaussian distributions G 1 , G 2 with different means μ 1 , μ 2 and variances σ 2 1 , σ 2 2 is computed, the result can be a Gaussian distribution (or similar) as well [14]. As ideal Gaussian distributions are symmetric, a unique mapping of a value (on the y-axis) to a certain displacement (on the x-axis) is impossible.…”

“…Distance estimation from 100 to 800 mm on actual sensor data using GCC and QBTM.is measuring the edge of a round target. The quality of the signal acquired in such configurations strongly depends on the sensor's beam quality[2].Theminimum, median and mean RSDs of all parameters in s and s alt indicate an advantage of the weighted averaging function s [b] over the simple averaging function s alt [b].…”

Local pixel wise skin detection algorithm based on FPGA

“…The traditional window image processing method, based on FPGA, requires numbers of FIFO, so taking up many hardware resources. The method mentioned in the [9][10] is all used a number of D flip-flop circuit and FIFO to cache data in corresponding pixel lines which will then be processed as a window. But, when the window is large, such as a window of 16 by 16 for processing, it will take up more storage resources.…”