CN102565794B - Microwave security inspection system for automatically detecting dangerous object hidden in human body - Google Patents

Abstract

The invention relates to a microwave security inspection system for automatically detecting a dangerous object hidden in a human body. The microwave security inspection system includes a microwave emitting and receiving device, a data acquisition device, an imaging treatment device and a device for automatically detecting the dangerous object hidden in a human body, wherein the microwave emittingand receiving device, the data acquisition device, the imaging treatment device and the device for automatically detecting the dangerous object hidden in the human body can be connected sequentially.The system has very high detection accuracy, meets the use requirement, and solves the problem of automatically detecting the dangerous object hidden in the human body during the security inspection process.

Description

A kind of dangerous object hidden in human body detects microwave security inspection system automatically

Technical field

The present invention relates to a kind of safe examination system, be specifically related to a kind of dangerous object hidden in human body and automatically detect microwave security inspection system, belong to image and process and the safety check technical field.

Background technology

Microwave has certain penetrability in communication process.By microwave Imaging Technique, can the imaging results image that affect such as obtain not to be subjected to that clothing blocks to being scanned human body; Then automatically finish the detection of hiding the dangerous object that carries under detected person's clothing based on the microwave result, such as metal cutter, unclarified liquid, sharp objects etc., be a kind of quick, safe and effective security and guard technology means.If in testing process, directly finish the detection of suspicious dangerous object by the macroscopic mode of safety check operator, the manpower that need to cost a lot of money, financial resources and time.Therefore, design can realize that the microwave security inspection system that automatically detects has great importance to the different attribute that may exist on the human body, the hiding dangerous object of type.

Existing dangerous object detecting system: on the one hand, the dangerous object automatic testing method in the system is mainly based on the visible images data; On the other hand, adopt constant false alarm rate detection method (CFAR) based on the interesting target detection system of microwave imagery, the detected characteristics that the CFAR method is utilized is real-valued amplitude characteristic, i.e. gray feature more.But hiding dangerous object at the application's human body detects in the microwave security inspection system application automatically, said method is also inapplicable, main cause is as follows: 1) microwave imagery and visible images imaging mechanism are essentially different, the microwave imagery gray-level is low, sharpness is low, and is subjected to the impact of coherent spot multiplicative noise.Object detecting method in the visible images can not directly be suitable in microwave imagery; 2) there is various ways in the related hiding dangerous object of the application in the feature performance, gray scale only is a kind of possible detected characteristics wherein, therefore, the CFAR method of intensity-based detected characteristics can not satisfy the needs that dangerous object detects automatically in the microwave security inspection system.

In sum, for realizing the automatic detection of dangerous object hidden in human body, need to be for the characteristicness of dangerous object in the microwave imaging result images in the situations such as interested unlike material, shape, size, structure satisfies the detected characteristics that can distinguish dangerous object under the different situations, designs effective dangerous object hidden in human body and automatically detects microwave security inspection system.

Summary of the invention

Purpose of the present invention aims to provide a kind of microwave security inspection system that possesses the dangerous object hidden in human body automatic detection function, and it mainly comprises such as lower member:

The microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device, wherein, described microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device connect in turn, and described dangerous object hidden in human body automatic detection device comprises such as lower device: image-input device, local significantly luminance area feature deriving means, local gray level Variance feature analytical equipment, remove vertical direction Edge Gradient Feature device, the detected characteristics fusing device, danger body region pick-up unit, the testing result filtration unit, danger body region identity device; Described image-input device respectively with the remarkable luminance area feature deriving means in part, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected, the remarkable luminance area feature deriving means in described part, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected with the detected characteristics fusing device respectively, described detected characteristics fusing device, danger body region pick-up unit, testing result filtration unit, danger body region identity device connect in turn.

Preferably, local significantly luminance area feature deriving means is carried out following flow process:

1) setting the iterations of cutting apart that is used for the local remarkable luminance area of extraction is 2, cuts apart for the first time human region in the image is split from background, and human region gray scale segmentation threshold is T _bThe local significantly luminance area that the second time, iteration was cut apart the dangerous object of correspondence splits from human region, and danger body region gray scale segmentation threshold is T _d

2) in conjunction with danger body region gray scale segmentation threshold T _d, make up local significantly luminance area eigenmatrix G: will input that gray-scale value is higher than T among the microwave gray level image I _dPixel region extract, all the other positions are set to 0:

$G(x,y)=\left\{\begin{array}{cc}I(x,y)& I(x,y)\&GreaterEqual;T_d\\ 0& I(x,y)<T_d\end{array}\right.$

The line number of matrix G, columns equate with the row, column number of microwave gray level image I respectively.

Preferably, local significantly luminance area feature deriving means is in flow process 1) in the following sub-process of execution:

1-1) iteration is cut apart for the first time: at first the microwave gray level image I of input made up overall grey level histogram H _g, tonal range [0,255];

1-2) iteration is cut apart for the first time: adopt the automatic threshold segmentation algorithm at overall grey level histogram H _gMiddle calculating human region gray scale segmentation threshold T _b

1-3) iteration is cut apart for the second time: in conjunction with acquired human region gray scale segmentation threshold T _b, make up human region grey level histogram H _b, tonal range [T _b, 255];

1-4) iteration is cut apart for the second time: adopt the automatic threshold segmentation algorithm at human region grey level histogram H _bMiddle calculating danger body region gray scale segmentation threshold T _d

Preferably, local gray level Variance feature analytical equipment is carried out following flow process:

1) setting local gray level variance analysis window size is s, and s is natural number;

2) any point (x, y) of calculating in microwave gray level image I faces the square area L that the territory range size is s * s _{(x, y)}, interior gray variance value:

${\mathrm{var}}_{(x,y)}=\frac{\underset{1\&le;i\&le;s}{\mathrm{\&Sigma;}}\underset{1\&le;j\&le;s}{\mathrm{\&Sigma;}}{[L_{(x,y)}(i,j)-E\left(L_{(x,y)}\right)]}^2}{s^2}$

E (L _{(x, y)}) part located of representative point (x, y) faces territory L _{(x, y)}Gray average;

3) combining image local gray level the results of analysis of variance makes up local gray level Variance feature matrix V corresponding to microwave gray level image I:

V(x，y)＝var _(x，y)

The line number of matrix V, columns equate with the row, column number of microwave gray level image I respectively;

4) the local gray level Variance feature matrix V of gained is carried out normalized, obtain local gray level variance normalization eigenmatrix Namely the eigenwert among the V is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{V}(x,y)=255\&times;\frac{V(x,y)-\min \left(V\right)}{\max \left(V\right)-\min \left(V\right)}$

Wherein, function max (V), min (V) represent respectively to calculate maximal value and the minimum value in the local gray level Variance feature matrix V.

Preferably, go vertical direction Edge Gradient Feature device to carry out following flow process:

1) makes up horizontal direction arithmetic operators h _h, diagonal arithmetic operators h _s, back-diagonal direction arithmetic operators h _As, vertical direction arithmetic operators h _v:

$h_h=\left[\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right]$ $h_s=\left[\begin{array}{ccc}0& 1& 2\\ -1& 0& 1\\ -2& -1& 0\end{array}\right]$

$h_{\mathrm{as}}=\left[\begin{array}{ccc}2& 1& 0\\ 1& 0& -1\\ 0& -1& -2\end{array}\right]$ $h_v=\left[\begin{array}{ccc}-1& 0& 1\\ -2& 0& 2\\ -1& 0& 1\end{array}\right]$

2) to any point (x, y) among the microwave gray level image I, calculate this some place horizontal direction rim detection response e _h, diagonal rim detection response e _s, back-diagonal direction rim detection response e _As, vertical direction rim detection response e _v:

$e_h=I(x,y)\&CircleTimes;h_h$ $e_s=I(x,y)\&CircleTimes;h_s$

$e_{\mathrm{as}}=I(x,y)\&CircleTimes;h_{\mathrm{as}}$ $e_v=I(x,y)\&CircleTimes;h_v$

3) jointing edge detects the response checkout result, and calculation level (x, y) is located removes vertical direction edge feature e _{(x, y)}:

e _(x，y)＝|e _h|+|e _s|+|e _as|-|e _v|

Wherein, | .| is the computing function that takes absolute value;

4) in conjunction with the each point place go vertical direction edge feature result of calculation, make up microwave gray level image I corresponding remove vertical direction edge feature matrix E:

E(x，y)＝e _(x，y)

The line number of matrix E, columns equate with the row, column number of microwave gray level image I respectively;

5) the vertical direction edge feature matrix E that goes of gained carried out normalized, obtain to go vertical direction edge feature normalization matrix Namely the eigenwert among the E is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{E}(x,y)=255\&times;\frac{E(x,y)-\min \left(E\right)}{\max \left(E\right)-\min \left(E\right)}$

Wherein, function max (E), min (E) represent respectively to calculate maximal value and the minimum value of going among the vertical direction edge feature matrix E.

Preferably, the detected characteristics fusing device is in conjunction with local significantly luminance area eigenmatrix G, the local gray level variance normalization eigenmatrix of gained Remove vertical direction edge feature normalization matrix

Merge by weighting normalization, obtain two-dimentional fusion feature matrix F (x, y):

$F(x,y)=\mathrm{\&alpha;}\&times;G(x,y)+\mathrm{\&beta;}\&times;\stackrel{\&OverBar;}{V}(x,y)+\mathrm{\&gamma;}\&times;\stackrel{\&OverBar;}{E}(x,y),$ Satisfy alpha+beta+γ=1

Wherein, weighting coefficient α, β, γ are real number.

Preferably, danger body region pick-up unit is carried out following flow process:

1) in conjunction with two-dimentional fusion feature matrix F (x, y), sets fusion feature segmentation threshold T _f, T _fBe real number;

2) set the middle eigenwert of two-dimentional fusion feature matrix F (x, y) greater than fusion feature segmentation threshold T _fThe zone be rough dangerous object detection results area, this regional value is set to 255, the value of all the other positions is set to 0.

Preferably, the testing result filtration unit is carried out following flow process:

1) the rough dangerous object detection results area that obtains is carried out closing operation of mathematical morphology;

2) in the rough dangerous object detection results area of filtering area less than T _AreaSubregion, remaining subregion is dangerous object detection results area, T _AreaBe natural number.

Preferably, danger body region identity device is carried out following flow process:

1) in conjunction with the dangerous object detection results area that obtains, extracts the edge contour of dangerous object detection results area;

2) the extract edge contour that obtains is identified out in input microwave gray level image I.

The invention has the beneficial effects as follows: this system can effectively be practically applicable to have very high Detection accuracy during real safety check uses, and satisfies request for utilization, has solved in the safety check process the automatic test problems to dangerous object hidden in human body.

Description of drawings

Fig. 1 is that a kind of dangerous object hidden in human body of the present invention detects the microwave security inspection system structural representation automatically;

Fig. 2 is the structural representation of the dangerous object hidden in human body automatic detection device among Fig. 1;

Fig. 3 uses a kind of dangerous object hidden in human body of the present invention automatically to detect the cross-reference figure of microwave security inspection system.

Embodiment

Inventive principle

In microwave security inspection system (such as the near field millimeter wave imaging safety inspection system), after through microwave signal emission, reception and to received signal imaging, form the microwave gray level image, next need to finish the hiding dangerous object automatic testing process of detected human body clothing under blocking based on the microwave gray level image information, automatic testing result is presented to the Systems Operator.The present invention is used for the safety check process to the automatic test problems of dangerous object hidden in human body.

In microwave security inspection system, finish imaging processing for the microwave echoed signal after, need in to image result, be detected the hiding dangerous object of human body clothes under blocking and automatically detect, the operator judges with backup system, finishes the safety check process.Generally, interested dangerous object is varied in the attribute performance: aspect material, mainly contain liquid, metal, plastics, powder etc.; Mainly contain at vpg connection: rectangular, acute angle, short wide etc.On the one hand, the visible images object detecting system is inapplicable to the microwave imaging result data; On the other hand, existing safe examination system is difficult to satisfy the object detection demand under the different situations, as introducing in the background technology part.

In order to solve the above problems, to the invention provides a kind of accurately and effectively dangerous object hidden in human body and automatically detect microwave security inspection system.

The present inventor has found following technical characterstic through lot of experiments: the interested dangerous object of the materials such as metal, liquid shows as the higher regional area of gray-scale value in the microwave gray level image; Powdered object, the interested dangerous object that is in the human region boundary might not have very high gray-scale value in the microwave gray level image, but there is obvious grey scale change in self zone inside or with respect to the background area, shows as larger local gray level variance; And for the more special object of contour shape, such as strip, acute angle etc., in imaging results, show as obvious marginal texture feature.

The present invention utilizes this technical characterstic, in the dangerous object hidden in human body automatic detection device input microwave gray level image is extracted respectively three kinds of different dangerous object detection features, different detected characteristics is in order to distinguish, to detect the interested dangerous object under the different situations.Wherein, local significantly luminance area feature is distinguished obvious dangerous object interested in order to detect in gray scale intensities, such as the object of metal, liquid material etc.; There is the interested dangerous object of obvious grey scale change in the local gray level Variance feature in order to detection regional area in gray level image, such as plastic object, powdered object, and made from mixed materials object, human region border object etc.; Go the vertical direction edge feature that the effect of two aspects is arranged, on the one hand, edge feature can detect typical rigid structure object or have the interested dangerous object of obvious shape and structure, such as brick, cutter etc., on the other hand, can remove a large amount of vertically marginal informations of aspect that skeleton causes in the imaging results, reduce the false-alarm that may cause in the testing process.By after the yardstick processing reasonably, three kinds of different dangerous object detection features are weighted normalization merge.Finish at last the automatic detection of the dangerous object hidden in human body under the different situations by fusion feature.

Below in conjunction with drawings and Examples a kind of dangerous object hidden in human body of the present invention being detected microwave security inspection system automatically describes in detail.

As shown in Figure 1, dangerous object hidden in human body of the present invention automatically detects microwave security inspection system and mainly comprises: microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device, wherein, microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device connect in turn.

The microwave transmitting and receiving device for generation of, emission, receive electromagnetic wave; It is digital signal that data collector is used for analog-signal transitions; The imaging processing device is used for changing the echo digital signal into picture signal; Dangerous object hidden in human body automatic detection device automatic human body clothing in picture signal blocks lower entrained hiding dangerous object, the line identifier of going forward side by side.

Microwave security inspection system is by the extremely detected human body of microwave launcher launched microwave; Microwave receiving device receives the echoed signal of human body reflection, and is that digital form is processed by data collector with the signal from analog formal transformation; Next digital signal is passed to the imaging processing device, the imaging processing device obtains high-resolution two dimensional image signal by synthetic aperture processing; Then, the dangerous object hidden in human body automatic detection device blocks lower entrained hiding dangerous object by corresponding processing module to the human body clothing and automatically detects the line identifier of going forward side by side; At last, the result images of finishing the automatic detection of dangerous object hidden in human body is reached the calculator display organization of system outside, present to system operator and detected person.

The below is to core of the present invention---and the dangerous object hidden in human body automatic detection device elaborates.

As shown in Figure 2, the dangerous object hidden in human body automatic detection device in this system mainly comprises following assembly: image-input device, local significantly luminance area feature deriving means, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device, detected characteristics fusing device, danger body region pick-up unit, testing result filtration unit, danger body region identity device; Image-input device respectively with the remarkable luminance area feature deriving means in part, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected, local significantly luminance area feature deriving means, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected with the detected characteristics fusing device respectively, detected characteristics fusing device, danger body region pick-up unit, testing result filtration unit, danger body region identity device connect in turn.

The dangerous object hidden in human body automatic detection device both can pass through hardware (such as DSP, PC) in realization in conjunction with whole realization of form of software (such as the C/C++ programming), also can independently realize by the form molecular device of combination of hardware software, then finish by combination between sub-device.

Local significantly luminance area feature deriving means is used for microwave gray level image I is extracted local significantly luminance area feature, and it carries out following functional sequence:

1) setting the iterations of cutting apart that is used for the local remarkable luminance area of extraction is 2, cuts apart for the first time human region in the image is split from background, and human region gray scale segmentation threshold is T _bThe local significantly luminance area that the second time, iteration was cut apart the dangerous object of correspondence splits from human region, and danger body region gray scale segmentation threshold is T _d

1-1) iteration is cut apart for the first time: at first the microwave gray level image I (shown in subgraph among Fig. 3 (a)) of input made up overall grey level histogram H _g, tonal range [0,255];

1-2) iteration is cut apart for the first time: adopt the automatic threshold segmentation algorithm at overall grey level histogram H _gMiddle calculating human region gray scale segmentation threshold T _b

1-3) iteration is cut apart for the second time: in conjunction with acquired human region gray scale segmentation threshold T _b, make up human region grey level histogram H _b, tonal range [T _b, 255];

1-4) iteration is cut apart for the second time: adopt the automatic threshold segmentation algorithm at human region grey level histogram H _bMiddle calculating danger body region gray scale segmentation threshold T _d

2) in conjunction with danger body region gray scale segmentation threshold T _d, make up local significantly luminance area eigenmatrix G: will input that gray-scale value is higher than T among the microwave gray level image I _dPixel region extract, all the other positions are set to 0:

$G(x,y)=\left\{\begin{array}{cc}I(x,y)& I(x,y)\&GreaterEqual;T_d\\ 0& I(x,y)<T_d\end{array}\right.$

The line number of matrix G, columns equate with the row, column number of microwave gray level image I respectively.

Local gray level Variance feature analytical equipment is used for microwave gray level image I is extracted local gray level Variance feature matrix, and it carries out following functional sequence:

1) setting local gray level variance analysis window size is s, and s is natural number;

2) any point (x, y) of calculating in microwave gray level image I faces the square area L that the territory range size is s * s _{(x, y)}, interior gray variance value:

${\mathrm{var}}_{(x,y)}=\frac{\underset{1\&le;i\&le;s}{\mathrm{\&Sigma;}}\underset{1\&le;j\&le;s}{\mathrm{\&Sigma;}}{[L_{(x,y)}(i,j)-E\left(L_{(x,y)}\right)]}^2}{s^2}$

E (L _{(x, y)}) part located of representative point (x, y) faces territory L _{(x, y)}Gray average;

3) combining image local gray level the results of analysis of variance makes up local gray level Variance feature matrix V corresponding to microwave gray level image I:

V(x，y)＝var _(x，y)

The line number of matrix V, columns equate with the row, column number of microwave gray level image I respectively;

4) the local gray level Variance feature matrix V of gained is carried out normalized, obtain local gray level variance normalization eigenmatrix

Namely the eigenwert among the V is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{V}(x,y)=255\&times;\frac{V(x,y)-\min \left(V\right)}{\max \left(V\right)-\min \left(V\right)}$

Wherein, function max (V), min (V) represent respectively to calculate maximal value and the minimum value in the local gray level Variance feature matrix V.

Go vertical direction Edge Gradient Feature device to remove vertical direction edge feature matrix for microwave gray level image I is extracted, it carries out following flow process:

1) makes up horizontal direction arithmetic operators h _h, diagonal arithmetic operators h _s, back-diagonal direction arithmetic operators h _As, vertical direction arithmetic operators h _v:

$h_h=\left[\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right]$ $h_s=\left[\begin{array}{ccc}0& 1& 2\\ -1& 0& 1\\ -2& -1& 0\end{array}\right]$

$h_{\mathrm{as}}=\left[\begin{array}{ccc}2& 1& 0\\ 1& 0& -1\\ 0& -1& -2\end{array}\right]$ $h_v=\left[\begin{array}{ccc}-1& 0& 1\\ -2& 0& 2\\ -1& 0& 1\end{array}\right]$

2) to any point (x, y) among the microwave gray level image I, calculate this some place horizontal direction rim detection response e _h, diagonal rim detection response e _s, back-diagonal direction rim detection response e _As, vertical direction rim detection response e _v:

$e_h=I(x,y)\&CircleTimes;h_h$ $e_s=I(x,y)\&CircleTimes;h_s$

$e_{\mathrm{as}}=I(x,y)\&CircleTimes;h_{\mathrm{as}}$ $e_v=I(x,y)\&CircleTimes;h_v$

3) jointing edge detects the response checkout result, and calculation level (x, y) is located removes vertical direction edge feature e _{(x, y)}:

e _(x，y)＝|e _h|+|e _s|+|e _as|-|e _v|

Wherein, | .| is the computing function that takes absolute value;

4) in conjunction with the each point place go vertical direction edge feature result of calculation, make up microwave gray level image I corresponding remove vertical direction edge feature matrix E:

E(x，y)＝e _(x，y)

The line number of matrix E, columns equate with the row, column number of microwave gray level image I respectively;

5) the vertical direction edge feature matrix E that goes of gained carried out normalized, obtain to go vertical direction edge feature normalization matrix

Namely the eigenwert among the E is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{E}(x,y)=255\&times;\frac{E(x,y)-\min \left(E\right)}{\max \left(E\right)-\min \left(E\right)}$

Wherein, function max (E), min (E) represent respectively to calculate maximal value and the minimum value of going among the vertical direction edge feature matrix E.

The detected characteristics fusing device is in conjunction with local significantly luminance area eigenmatrix G, the local gray level variance normalization eigenmatrix of gained

Remove vertical direction edge feature normalization matrix

Merge by weighting normalization, obtain two-dimentional fusion feature matrix F (x, y):

$F(x,y)=\mathrm{\&alpha;}\&times;G(x,y)+\mathrm{\&beta;}\&times;\stackrel{\&OverBar;}{V}(x,y)+\mathrm{\&gamma;}\&times;\stackrel{\&OverBar;}{E}(x,y),$ Satisfy alpha+beta+γ=1

Wherein, weighting coefficient α, β, γ are real number.

Danger body region pick-up unit is used for fusion feature matrix F (x, y) is cut apart, and detects the danger body region, and it carries out following functional sequence:

1) in conjunction with two-dimentional fusion feature matrix F (x, y), sets fusion feature segmentation threshold T _f, T _fBe real number;

2) set the middle eigenwert of two-dimentional fusion feature matrix F (x, y) greater than fusion feature segmentation threshold T _fThe zone be rough dangerous object detection results area, this regional value is set to 255, the value of all the other positions is set to 0.

The testing result filtration unit is used for danger body region testing result is filtered, and it carries out following functional sequence:

1) the rough dangerous object detection results area that obtains is carried out closing operation of mathematical morphology;

2) in the rough dangerous object detection results area of filtering area less than T _AreaSubregion, remaining subregion is dangerous object detection results area, T _AreaBe natural number.

Danger body region identity device is used for the testing result behind the combined filtering, and the danger body region is identified, and it carries out following functional sequence:

1) in conjunction with the dangerous object detection results area that obtains, extracts the edge contour of dangerous object detection results area;

2) the extract edge contour that obtains is identified out in input microwave gray level image I, shown in subgraph among Fig. 3 (b).

By experiment checking, a kind of dangerous object hidden in human body of the present invention automatically detects microwave security inspection system and can effectively be practically applicable in the real safety check application, have very high Detection accuracy, satisfy request for utilization, solved in the safety check process the automatic test problems to dangerous object hidden in human body.

Above embodiment sets forth the restriction of doing for the present invention is known, real protection scope of the present invention is not limited to this, and all modification or changes of doing based on inventive concept are all within protection domain of the present invention.

Claims (6)

1. a dangerous object hidden in human body detects microwave security inspection system automatically, it is characterized in that, comprise: the microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device, wherein, described microwave transmitting and receiving device, data collector, imaging processing device and dangerous object hidden in human body automatic detection device connect in turn, and described dangerous object hidden in human body automatic detection device comprises such as lower device: image-input device, local significantly luminance area feature deriving means, local gray level Variance feature analytical equipment, remove vertical direction Edge Gradient Feature device, the detected characteristics fusing device, danger body region pick-up unit, the testing result filtration unit, danger body region identity device; Described image-input device respectively with the remarkable luminance area feature deriving means in part, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected, the remarkable luminance area feature deriving means in described part, local gray level Variance feature analytical equipment, go vertical direction Edge Gradient Feature device to be connected with the detected characteristics fusing device respectively, described detected characteristics fusing device, danger body region pick-up unit, testing result filtration unit, danger body region identity device connect in turn; The microwave transmitting and receiving device for generation of, emission, receive electromagnetic wave; It is digital signal that data collector is used for analog-signal transitions; The imaging processing device is used for changing the echo digital signal into picture signal; Dangerous object hidden in human body automatic detection device automatic human body clothing in picture signal blocks lower entrained hiding dangerous object, the line identifier of going forward side by side;

The remarkable luminance area feature deriving means in described part is carried out following flow process:

1) setting the iterations of cutting apart that is used for the local remarkable luminance area of extraction is 2, cuts apart for the first time human region in the image is split from background, and human region gray scale segmentation threshold is T _bThe local significantly luminance area that the second time, iteration was cut apart the dangerous object of correspondence splits from human region, and danger body region gray scale segmentation threshold is T _d

2) in conjunction with danger body region gray scale segmentation threshold T _d, make up local significantly luminance area eigenmatrix G: will input that gray-scale value is higher than T among the microwave gray level image I _dPixel region extract, all the other positions are set to 0:

$G(x,y)=\left\{\begin{array}{cc}I(x,y)& I(x,y)\&GreaterEqual;T_d\\ 0& I(x,y)<T_d\end{array}\right.$

The line number of matrix G, columns equate with the row, column number of microwave gray level image I respectively;

Described local gray level Variance feature analytical equipment is carried out following flow process:

1) setting local gray level variance analysis window size is s, and s is natural number;

2) any point (x, y) of calculating in microwave gray level image I faces the square area L that the territory range size is s * s _{(x, y}) interior gray variance value:

${\mathrm{var}}_{(x,y)}=\frac{\underset{1\&le;i\&le;s}{\mathrm{\&Sigma;}}\underset{1\&le;j\&le;s}{\mathrm{\&Sigma;}}{[L_{(x,y)}(i,j)-E\left(L_{(x,y)}\right)]}^2}{s^2}$

E (L _{(x, y)}) part located of representative point (x, y) faces territory L _{(x, y)}Gray average;

3) combining image local gray level the results of analysis of variance makes up local gray level Variance feature matrix V corresponding to microwave gray level image I:

V(x,y)=var _(x,y)

The line number of matrix V, columns equate with the row, column number of microwave gray level image I respectively;

4) the local gray level Variance feature matrix V of gained is carried out normalized, obtain local gray level variance normalization eigenmatrix

, namely the eigenwert among the V is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{V}(x,y)=255\&times;\frac{V(x,y)-\min \left(V\right)}{\max \left(V\right)-\min \left(V\right)}$

Wherein, function max (V), min (V) represent respectively to calculate maximal value and the minimum value in the local gray level Variance feature matrix V;

The described vertical direction Edge Gradient Feature device that goes is carried out following flow process:

1) makes up horizontal direction arithmetic operators h _h, diagonal arithmetic operators h _s, back-diagonal direction arithmetic operators h _As, vertical direction arithmetic operators h _v:

$h_h=\left[\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right],$ $h_s=\left[\begin{array}{ccc}0& 1& 2\\ -1& 0& 1\\ -2& -1& 0\end{array}\right],$

$h_{\mathrm{as}}=\left[\begin{array}{ccc}2& 1& 0\\ 1& 0& -1\\ 0& -1& -2\end{array}\right],$ $h_v=\left[\begin{array}{ccc}-1& 0& 1\\ -2& 0& 2\\ -1& 0& 1\end{array}\right];$

2) to any point (x, y) among the microwave gray level image I, calculate this some place horizontal direction rim detection response e _h, diagonal rim detection response e _s, back-diagonal direction rim detection response e _As, vertical direction rim detection response e _v:

$e_h=I(x,y)\&CircleTimes;h_h,$ $e_s=I(x,y)\&CircleTimes;h_s,$

$e_{\mathrm{as}}=I(x,y)\&CircleTimes;h_{\mathrm{as}},$ $e_v=I(x,y)\&CircleTimes;h_v;$

3) jointing edge detects the response checkout result, and calculation level (x, y) is located removes vertical direction edge feature e _{(x, y)}:

e _(x,y)=|e _h|+|e _s|+|e _as|-|e _v|

Wherein, | .| is the computing function that takes absolute value;

4) in conjunction with the each point place go vertical direction edge feature result of calculation, make up microwave gray level image I corresponding remove vertical direction edge feature matrix E:

E(x,y)=e _(x,y)

The line number of matrix E, columns equate with the row, column number of microwave gray level image I respectively;

5) the vertical direction edge feature matrix E that goes of gained carried out normalized, obtain to go vertical direction edge feature normalization matrix

, namely the eigenwert among the E is mapped in codomain [0, the 255] scope by linear mode:

$\stackrel{\&OverBar;}{E}(x,y)=255\&times;\frac{E(x,y)-\min \left(E\right)}{\max \left(E\right)-\min \left(E\right)}$

Wherein, function max (E), min (E) represent respectively to calculate maximal value and the minimum value of going among the vertical direction edge feature matrix E.

2. a kind of dangerous object hidden in human body as claimed in claim 1 detects microwave security inspection system automatically, it is characterized in that, the remarkable luminance area feature deriving means in described part is in flow process 1) in carry out following sub-process:

1-1) iteration is cut apart for the first time: at first the microwave gray level image I of input made up overall grey level histogram H _g, tonal range [0,255];

1-2) iteration is cut apart for the first time: adopt the automatic threshold segmentation algorithm at overall grey level histogram H _gMiddle calculating human region gray scale segmentation threshold T _b

1-3) iteration is cut apart for the second time: in conjunction with acquired human region gray scale segmentation threshold T _b, make up human region grey level histogram H _b, tonal range [T _b, 255];

1-4) iteration is cut apart for the second time: adopt the automatic threshold segmentation algorithm at human region grey level histogram H _bMiddle calculating danger body region gray scale segmentation threshold T _d

3. a kind of dangerous object hidden in human body as claimed in claim 1 detects microwave security inspection system automatically, it is characterized in that, described detected characteristics fusing device is in conjunction with local significantly luminance area eigenmatrix G, the local gray level variance normalization eigenmatrix of gained

, remove vertical direction edge feature normalizing

Change matrix

Merge by weighting normalization, obtain two-dimentional fusion feature matrix F (x, y):

$F(x,y)=\mathrm{\&alpha;}\&times;G(x,y)+\mathrm{\&beta;}\stackrel{\&OverBar;}{V}(x,y)+\mathrm{\&gamma;}\&times;\stackrel{\&OverBar;}{E}(x,y),$ Satisfy alpha+beta+γ=1

Wherein, weighting coefficient α, β, γ are real number.

4. a kind of dangerous object hidden in human body as claimed in claim 1 detects microwave security inspection system automatically, it is characterized in that, described danger body region pick-up unit is carried out following flow process:

1) in conjunction with two-dimentional fusion feature matrix F (x, y), sets fusion feature segmentation threshold T _f, T _fBe real number;

2) set the middle eigenwert of two-dimentional fusion feature matrix F (x, y) greater than fusion feature segmentation threshold T _fThe zone be rough dangerous object detection results area, this regional value is set to 255, the value of all the other positions is set to 0.

5. a kind of dangerous object hidden in human body as claimed in claim 1 detects microwave security inspection system automatically, it is characterized in that, described testing result filtration unit is carried out following flow process:

1) the rough dangerous object detection results area that obtains is carried out closing operation of mathematical morphology;

2) in the rough dangerous object detection results area of filtering area less than T _AreaSubregion, remaining subregion is dangerous object detection results area, T _AreaBe natural number.

6. a kind of dangerous object hidden in human body as claimed in claim 1 detects microwave security inspection system automatically, it is characterized in that, described danger body region identity device is carried out following flow process:

1) in conjunction with the dangerous object detection results area that obtains, extracts the edge contour of dangerous object detection results area;

2) the extract edge contour that obtains is identified out in input microwave gray level image I.

Images