CN202221578U - Self-adaptive feedback image security inspection rectification system - Google Patents

Abstract

The utility model relates to a self-adaptive feedback image security inspection rectification system, comprising an image detection device, an image acquisition device connected with the image detection device, an image analysis device connected with the image acquisition device and an image feedback device respectively connected with the image detection device, the image acquisition device and the image analysis device. The Image detection device detects the ray attenuation data obtained by transmitting an object to be detected and transmits the ray attenuation data to the image acquisition device. The ray attenuation data received by the image acquisition device is converted into the image data of the object to be detected and the operation direct towards the object to be detected is detected and then the conversion and detection result is sent to the image analysis device, wherein the image data comprises the display image of the current object to be detected and the kind of the material in the object. The image analysis device evaluates the image data from the image acquisition device and the operation direct towards the object to be detected and informs the evaluation result to the image feedback device. The image feedback device adjusts the operation of the object to be detected according to the evaluation result.

Description

A kind of image safety check deviation-rectifying system of self-adaptation feedback

Technical field

The utility model relates to radiation image-forming detecting system, relates in particular to a kind of image safety check deviation-rectifying system of self-adaptation feedback.

Background technology

Along with the raising of countries in the world to the public safety requirement; Especially on the airport, public place such as station, customs, harbour; All take measures hand baggage article, cargo container etc. are endured strict scrutiny, wherein, mostly the safety inspection technology that safe examination system provides is the radiant image technology.

At present, the radiant image technology is the mainstream technology in the widely used safe examination system in various countries, and this technology is the basis with the transmission attenuation principle of ray (like X ray).Common radiant image safe examination system comprises the radiographic source of a side that is arranged in detected material, is used to shine detected material.The ray harvester that is arranged in the detected material opposite side receives the ray that sees through detected material, and the decay ray data that this ray harvester will receive is exported to imaging device, shows in order to identification and composograph.Above-described image safe examination system is as shown in Figure 1, comprises image detecting apparatus 110, image acquisition equipment 120 and figure inspection person 130; Wherein, the ray by image detecting apparatus 110 detection transmission detected materials converts this ray data into and flows to said image acquisition equipment 120; 120 pairs of said data of said image acquisition equipment are discerned, and convert recognition result the view data of detected material into, and said view data comprises the original color image and the substance classes of detected material; And whether contain dangerous material in the detected object of radiation exposure, perhaps whether system exists fault then by figure inspection person artificial judgment.In practical application, as shown in Figure 2, said image detecting apparatus 110 is radiation imaging apparatus A, and said image acquisition equipment is industrial computer or computer equipment, and the C among Fig. 2 is figure inspection person.

Earlier figures as safe examination system in; Owing to the subjective factor and the different figure inspection persons that have introduced figure inspection person are difficult to carry out unified reasons such as image criterion; Can increase the uncertainty of testing result, so very easily cause safe examination system not have due safety inspection effect.

The utility model content

In view of this, the utility model embodiment provides a kind of image safety check method for correcting error and system of self-adaptation feedback, through setting up the reliability that closed-loop control improves the image safe examination system.

For addressing the above problem, the technical scheme that the utility model embodiment provides is following:

A kind of image safety check deviation-rectifying system of self-adaptation feedback comprises:

Image detecting apparatus;

The image acquisition equipment that links to each other with said image detecting apparatus;

The image analysis equipment that links to each other with said image acquisition equipment; And

The image feedback equipment that links to each other with said image detecting apparatus, image acquisition equipment and image analysis equipment respectively.

Adopt the utility model embodiment system; On the basis that does not influence normal picture safety check flow process, through the validity that analysis image obtains, image shows and be directed against the image manipulation instruction, and the detection of coupling system device parameter; Utilize the foundation of closed-loop control and feedback system; To image detecting apparatus or the indication of image acquisition equipment feedback adjustment, make system equipment to adjust safe examination system, thereby can improve the reliability of image safe examination system according to the adjustment indication.

Description of drawings

In order to be illustrated more clearly in the embodiment of the utility model, will do to introduce simply to the accompanying drawing of required use among the embodiment below.Obviously, the accompanying drawing in describing below only is the certain exemplary embodiment of the utility model, for those of ordinary skills, under the prerequisite of not paying creative work property, can also obtain other accompanying drawing according to these accompanying drawings.

Fig. 1 is that image safe examination system of the prior art is formed structural representation;

Fig. 2 is an image safe examination system practical application synoptic diagram of the prior art;

Fig. 3 is the image safety check method for correcting error schematic flow sheet of the utility model embodiment 1 self-adaptation feedback;

Fig. 4 judges among the utility model embodiment 1 whether display image the synoptic diagram of bad track occurs, and wherein Fig. 4 a is converted into resulting presentation graphs behind the gray level image with display image; Fig. 4 b illustrates gray level image is carried out the resulting Gray Projection value of Gray Projection by row; Fig. 4 c exemplarily illustrates the situation that occurs bad track in the said display image;

Fig. 5 is the image safety check deviation-rectifying system structural representation of the utility model embodiment 2 self-adaptations feedback.

Embodiment

The basic thought of the utility model is to be the basis with the conventional images safe examination system; Through the validity that analysis image obtains, image shows and be directed against the image manipulation instruction; And the detection of coupling system device parameter; Utilize the foundation of closed-loop control and feedback system, thereby can improve the reliability of image safe examination system.

Wherein, it should be noted that the goal of the invention that be to realize the utility model, the utility model embodiment has adopted " image detecting apparatus " of the prior art, and like radiation imaging apparatus etc., the function of its realization is with specifically the course of work is identical with prior art; Simultaneously; " image acquisition equipment " of the prior art improved; And increased in order to view data and operation " image analysis equipment " estimated and " the image feedback equipment " that system adjusted accordingly to the analysis result of image analysis equipment, its concrete realization will be described in detail in following each embodiment.

To combine the accompanying drawing among the utility model embodiment below, the technical scheme among the utility model embodiment will be carried out clear, intactly description; Obviously, described embodiment only is the utility model part embodiment, rather than whole embodiment.Based on the utility model embodiment, those of ordinary skills are not making the every other embodiment that is obtained under the creative work prerequisite, all belong to the scope of the utility model protection.

The utility model embodiment 1 provides the image safety check method for correcting error of self-adaptation feedback, and as shown in Figure 3, this method comprises:

Step 301: the ray attenuation data that detect the transmission detected material;

Can adopt the image detecting apparatus in the conventional images safe examination system in the present embodiment, utilize this image detecting apparatus to detect the ray attenuation data of transmission detected material; Wherein, said image detecting apparatus utilizes ray to penetrate principle, and the decay property that sees through object through sense radiation detects the ray attenuation data of current detected material, and concrete ray penetrates principle this paper and repeats no more.

Step 302: the view data with said ray attenuation data-switching is a detected material, detect the operation to detected material; Wherein, in the utility model embodiment, this is operated image acquisition equipment capable of using and realizes, but is not limited thereto; Especially it should be noted that: the said view data of obtaining should comprise the display image of current detected material and the substance classes that comprises thereof at least; And multiple mode is arranged usually to the operation of detected material; For example instruction mode, code means etc.; Present embodiment is that example is elaborated with instruction mode commonly used only, but is not limited thereto; Concrete,

1), adopt formation method of the prior art, according to the ray attenuation data of the detected current detected material of said image detecting apparatus, generate the original color image I of current detected material _ColorAnd substance classes Z, wherein, said original color image is without the display image of crossing artificial operation; Wherein, I _ColorIdentical with the Z size, establish it here and be the capable N row of M; In general, the value of Z can roughly be divided into 4 kinds, i.e. air, organism, potpourri and inorganics.

2), after obtaining the view data of current detected material, system shows on display.Single image supervision time section is designated as IITI (Image Inspection Time Interval) here, it is presented at the start time t on the display by picking up thing _In, concluding time t _OutForm, i.e. IITI={t _In, t _Out.General, t _InBe I _ColorAll appear at the moment on the screen, t _OutBe I _ColorAll shift out the moment of screen.Then, in the time period, write down the various set of parameter values P={I of said image detecting apparatus at this IITI, U, S}, wherein, I is a device current value among this IITI, and U is an equipment magnitude of voltage among the IITI, and S is a belt speed value among the IITI.At last, be recorded in this IITI in the time period, figure inspection person is to n operation instruction information O of image _iAnd corresponding instruction hypograph effect I _iThe operating effect atlas OI={O that constitutes _i, I _i, i ∈ [1, n].

Step 303: estimate said view data and operation; The evaluation of mentioning in the present embodiment normally utilizes image analysis equipment to realize; And can comprise various ways and content; Only be elaborated below, but those skilled in the art readily understand that said evaluation is not limited thereto with the several frequently seen example that is operating as:

1), judges whether occur bad track in the display image; Concrete, as shown in Figure 4:

At first with display image I _ColorBe converted into gray level image I _Gray, shown in Fig. 4 a;

Then with gray level image I _GrayCarry out Gray Projection by row, obtain Gray Projection value r _i, shown in Fig. 4 b; Wherein, said Gray Projection value

I ∈ [1, N], I _PiBe I _GrayThe value of the capable i of p row;

To Gray Projection r _iCarry out normalization and handle, and calculate the difference r that obtains this normalization result _i', shown in Fig. 4 c; Wherein, normalization result difference r _i'=(r _I+1-r _i), i ∈ [1, N-1];

According to said difference r _i' calculate its variances sigma=(∑ (r _i') ²/ (N-1)) ^1/2(" ∑ " expression summation operation.Down together.)

If r _i'＞σ then can judge in the said display image bad track to have occurred; For example shown in Fig. 4 c, show to have occurred 4 bad tracks in the display image.

2), judge whether the electric current of image detecting apparatus and/or voltage is normal;

As everyone knows, when the electric current of image detecting apparatus and/or voltage were on the low side, the gray-scale value in the display image can be on the low side; According to this principle, the image safety check method for correcting error of present embodiment proposes:

At first preset air gray threshold T _Air

The gray level image I that transforms according to display image then _GrayObtain the air average gray in the display image; Concrete, establish Z _AirBe air location of pixels matrix,

Z then _AirEach element z _{Air_i}For

Can know that thus the air average gray is: i _Air=(∑ I _GrayZ _Air)/(∑ Z _Air);

At this moment, if i _AirBe lower than preset air gray threshold T _Air, can judge that then the electric current of present image checkout equipment and/or voltage are on the low side.

3), judge whether image detecting apparatus transmits the speed of detected material normal;

As everyone knows, when image detecting apparatus detected detected material, if it transmits the excessive velocities of detected material, then the display image of follow-up generation will be by supercompression, thereby possibly cause image detail to be lost; Simultaneously, under the enough situation of statistical sample, the line correlation of natural image is normally consistent with the row correlation values, if less than the row correlativity, then there is loss of data in the line correlation property of image between each row of key diagram picture.Based on this principle, the method for present embodiment proposes following mode capable of using and judges whether said transfer rate is normal:

At first, utilize the above-mentioned mode of having mentioned that display image is converted into gray level image I _Gray

Secondly, obtain this gray level image I _GrayGradient map I _Grad, wherein,

(

The expression convolution algorithm.Down together.)

Choose I _GradK greatest gradient point p _k, k ∈ [1, K]; And calculate each gradient point p _kThe line correlation CR of position _kWith the relevant CC of row _kIf p _kPoint place image line vector is c _k, the I that then is adjacent _StepRow (I _StepIn [1,4] scope, all can obtain better effects.Be without loss of generality, get I _Step=2) row vector is c _k', then have:

${\mathrm{CR}}_k=\frac{\mathrm{\Σ}{c}_k{c_k}^{\′}}{\mathrm{K\Σ}{(c_k-{\stackrel{\‾}{c}}_k)}^2\mathrm{\Σ}{({c_k}^{\′}-{{\stackrel{\‾}{c}}_k}^{\′})}^2},$ In like manner, have:

${\mathrm{CC}}_k=\frac{\mathrm{\Σ}{r}_k{r_k}^{\′}}{\mathrm{K\Σ}{(r{k}_{}-{\stackrel{\‾}{r}}_k)}^2\mathrm{\Σ}{({r_k}^{\′}-{{\stackrel{\‾}{r}}_k}^{\′})}^2}$

According to gradient point p _kThe line correlation CR of position _kWith the relevant CC of row _kCan confirm said transfer rate S _r, that is, and S _r=∑ (CR _k/ CC _k)/K; Error for avoiding being brought by single image self property is asked S to n time nearest detection then _rAverage

General, n gets 20 can obtain ideal effect.When said

Less than preset threshold speed T _sThe time, can confirm that current transfer rate is too fast.

In like manner, the method is applicable to too and judges that rotating speed is slow excessively.But in view of practicality considers that hereinafter is no longer described the slow excessively situation of belt speed.This is because under the slow situation of rotating speed, though certain distortion appears in image, only can produce redundant information, and drop-out does not influence the spectral discrimination result.

4), judge whether the operation that is directed against detected material is corresponding with the substance classes that current detected material comprises;

Those skilled in the art readily understand that the common rule in the image safe examination system includes but not limited at present: if comprise large amount of organic in the article, then operation should be " organism rejecting "; If comprise a large amount of inorganicss in the article, then operational order should be " inorganics rejecting "; If article are more thick and heavy, then operational order should be " high energy penetrates "; If article are more frivolous, then operational order should be " low energy penetrates " or " super enhancing "; For example, if comprise clothing etc. in the display image, because its material is more frivolous, make that imaging effect and surrounding air are more approaching, be difficult to see interior details, then can obtain the effect that be more suitable for observe if use super enhancing or low energy to penetrate algorithm this moment; It should be noted that; The particular content of the various operational orders of mentioning in the present embodiment and realization are all mature technology of the prior art; Like halt switch instruction, mouse instructions etc.; This paper does not do specifically this and gives unnecessary details, and present embodiment only is described in detail the relation between substance classes and the respective operations:

At first calculate the number percent of the outer every kind of substance classes of deacration according to display image, be without loss of generality, the span of establishing substance classes Z is [0; 3]; Wherein, 0 corresponding air, 1 corresponding organism, 2 corresponding potpourris, 3 corresponding inorganicss then have the number percent R of each material _i:

$R_i=\underset{m}{\mathrm{\Σ}}\underset{n}{\mathrm{\Σ}(Z==i)/\mathrm{MN}\×100\%,}$ i＝(1，2，3，4)；

If the number percent of certain material has surpassed preset threshold T _Mat, then need operate accordingly;

For example, if R ₁＞T _Mat, then expression need be carried out " organism rejecting " operation; If R ₃＞T _Mat, then expression need be carried out " inorganics rejecting " operation;

The average gray i of calculation display image then _g, promptly

If said average gray i _gBe lower than preset thresholding T _Low, then the presentation video ash is spent secretly, need carry out " high energy penetrates " operation this moment; If said gray scale i _gBe higher than preset thresholding T _High, show that then gradation of image is bright excessively, need carry out " low energy penetrates " operation this moment; It should be noted that above-mentioned various rule is concrete preferred embodiment, in practical application, as long as given T _Mat, T _LowAnd T _HighAfter the parameter, can formulate various rule according to the actual requirements, judge with this whether the substance classes that comprises in said operational order and the current detected material is corresponding, concrete present embodiment repeats no more at this.

Step 304: according to the operation of evaluation result adjustment to detected material; In the present embodiment, image feedback equipment capable of using comes according to the operation of evaluation result adjustment to detected material; Specifically comprise following several kinds of situation, but be not limited thereto:

1), shows when bad track occurring in the display image when evaluation result, if this bad track then carries out data scaling again for occurring first; Otherwise, restart image detecting apparatus;

2), when evaluation result shows that the electric current of said present image checkout equipment and/or voltage are on the low side, then indicate said image detecting apparatus adjustment electric current and/or voltage; Wherein, electric current adjusted respectively by the indicating image checkout equipment and/or voltage can adopt following mode, but is not limited to this:

If said electric current and/or voltage are on the low side for occurring first; Then to device parameter P={I; U; Electric current I among the S}, voltage U are carried out specific aim adjustment: adjust electric current I+Δ I respectively separately, adjust voltage U+Δ U operation twice separately, and obtain the air average gray i in the image after twice adjustment respectively _Air, after the repetitive operation repeatedly, with the i of maximum _AirCorresponding operation is as final adjustment operation.

3), when evaluation result shows that image detecting apparatus transmits the excessive velocities of detected material, indicate said image detecting apparatus adjustment belt speed, be about to belt speed and be adjusted into S+ Δ S, carry out next iteration then, till belt speed satisfies condition.

4), show that current operation to detected material is not corresponding with the substance classes that detected material comprises when evaluation result, promptly current when being operating as improper operation, the insertion of triggering dangerous material (Threat Image Projection, TIP) flow process; Specifically include but not limited to:

A, send the standard abnormal image to image acquisition equipment;

B, send the dangerous material image, make it to superpose with true picture to image acquisition equipment;

C, in true picture, insert the image of the corresponding substance classes of proper operation;

It should be noted that in existing image safe examination system, said TIP technology is comparative maturity, and above-mentioned several kinds of modes are the usual way that present embodiment proposes, in practical application, can also comprise other forms, repeat no more at this this paper.

In addition, based on the foregoing description, said image safety check method for correcting error also can may further comprise the steps:

If the continuous multi-mode operation instruction to detected material all is that dangerous material are reported to the police, then can judge the current system failure, send the fault alarm indication.For the image safe examination system; The appearance of dangerous material belongs to small probability event: for example when explosive is checked; If in 100 luggage, find 20 explosives, be undesired situation from the angle of probability, it often is not true embodiment; But problem has appearred in the explanation image detecting system, and just need send the adjustment instruction to system this moment; Concrete, can adopt following mode to judge:

In image safety check process, if from N continuous _bCheck out D in the individual detected material _bIndividual detected material has problem, then its probability P that goes wrong _bFor: P _b=D _b/ N _bAnd according to the long-time statistical result, the preset actual probability that should go wrong is T _bPresent embodiment proposes, in continuous certain hour, if said P _b＞3T _b, show that then there is fault in the present image safe examination system, send the fault alarm indication this moment, with indication the present image safe examination system is adjusted operation.

Can find out, adopt the method for the foregoing description, on the basis that does not influence normal picture safety check flow process; Through the validity that analysis image obtains, image shows and be directed against the image manipulation instruction; And the detection of coupling system device parameter, utilize the foundation of closed-loop control and feedback system, to image detecting apparatus or the indication of image acquisition equipment feedback adjustment; Make system equipment to adjust safe examination system, thereby can improve the reliability of image safe examination system according to the adjustment indication.

Based on above-mentioned thought; The utility model embodiment 2 has proposed a kind of image safety check deviation-rectifying system of self-adaptation feedback again; As shown in Figure 5, this system 500 comprises: image detecting apparatus 510, the image acquisition equipment 520 that links to each other with said image detecting apparatus 510; The image analysis equipment 530 that links to each other with said image acquisition equipment 520, and the image feedback equipment 540 that links to each other with image analysis equipment 530 with said image detecting apparatus 510, image acquisition equipment 520 respectively;

Wherein, said image detecting apparatus 510 is used to detect the ray attenuation data of current detected material, and sends to said image acquisition equipment 520;

The view data that it is detected material that said image acquisition equipment 520 is used for the said ray attenuation data-switching that receives detects the operation to detected material, and will change and testing result sends to image analysis equipment; Said view data comprises the display image of current detected material and the substance classes that comprises thereof;

Said image analysis equipment 530 is used to estimate view data that said image acquisition equipment sends and to the operation of detected material, and notifies image feedback equipment with evaluation result;

Said image feedback equipment 540 is used for according to the operation of said evaluation result adjustment to detected material.

In addition, the said image analysis equipment in the present embodiment image safe examination system can comprise:

With said display image be converted into the conversion unit of gray level image, normalization processing unit that normalization after the gray level image Gray Projection is handled and first comparing unit that the variance of normalization result's difference and this difference is compared; If said difference is greater than said variance, then said first comparing unit is notified in the said image feedback equipment display image and bad track occurred.Based on this, said image feedback equipment comprises:

Be used to receive first receiving element of said first comparing unit notice and judge first indicating member whether bad track occurs first; If bad track is appearance first, the said first indicating member indicating image checkout equipment carries out data scaling again, otherwise the indicating image checkout equipment is restarted.

In addition, the said image analysis equipment in the present embodiment image safe examination system can comprise:

Pre-set the unit being set, calculating the computing unit of current display image air average gray and comparing the air gray threshold and second comparing unit of display image air average gray size of air gray threshold; When said air average gray less than said air gray threshold, said second comparing unit notifies the electric current and/or the voltage of said image feedback equipment present image checkout equipment on the low side.Based on this, said image feedback equipment comprises:

Be used to receive second receiving element of said second comparing unit notice, and indicate second indicating member of said image detecting apparatus adjustment electric current and/or voltage according to said notice.

It should be noted that the said image analysis equipment in the present embodiment image safe examination system also can comprise:

Display image is converted into the acquiring unit of gray level image or acquisition gradient point; The line correlation that calculates each gradient point is relevant with row and obtain the arithmetic element of image detecting apparatus transmission detected material velocity amplitude with this computing; The statistic unit of periodic statistics and computing velocity mean value, and the 3rd comparing unit that compares speed average and pre-set velocity threshold size; When said speed average during less than the pre-set velocity threshold value, said the 3rd comparing unit notifies said image feedback equipment present image checkout equipment to transmit the excessive velocities of detected material.Based on this, said image feedback equipment comprises:

Receive the 3rd receiving element of said the 3rd comparing unit notice, and indicate the 3rd indicating member of said image detecting apparatus adjustment belt speed according to said notice.

Preferably, the said image analysis equipment in the present embodiment image safe examination system comprises:

Judge to the operation of detected material and current detected material to comprise the first whether corresponding judging unit of substance classes, and notify the notification unit of said image feedback equipment judged result.Based on this, said image feedback equipment comprises:

Receive the 4th receiving element of said notification unit notice, and insert the trigger element of flow process according to these notification triggers dangerous material.

Based on the various embodiments described above; Said image feedback equipment in the present embodiment image safe examination system also comprises: judge whether the continuous multi-mode operation instruction to detected material all is second judging unit that dangerous material are reported to the police, and send the transmitting element of fault alarm indication according to the notice of second judging unit; When continuous a plurality of operational orders all are the dangerous material warning, said second judging unit notice transmitting element.

Those skilled in the art readily understand, the system described in the foregoing description has only been described and traditional images safe examination system difference, and its two total part this paper repeats no more; And in practical application, those skilled in the art readily understand, but any two or three in the said image acquisition equipment in the foregoing description system, image analysis equipment and the image feedback equipment all module turn to one, repeat no more at this.

Those skilled in the art can also further recognize; The unit and the algorithm steps of each example of describing in conjunction with embodiment disclosed herein; Can realize with electronic hardware, computer software or the combination of the two; For the interchangeability of hardware and software clearly is described, the composition and the step of each example described prevailingly according to function in above-mentioned explanation.These functions still are that software mode is carried out with hardware actually, depend on the application-specific and the design constraint of technical scheme.Those skilled in the art can use distinct methods to realize described function to each certain applications, but this realization should not thought the scope that exceeds the utility model embodiment.

The method of describing in conjunction with embodiment disclosed herein or the step of algorithm can be directly with the software modules of hardware, processor execution, and perhaps the combination of the two is implemented.Software module can place the storage medium of any other form known in random access memory (RAM), internal memory, ROM (read-only memory) (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or this area.

To the above-mentioned explanation of the disclosed embodiments, make this area professional and technical personnel can realize or use the utility model embodiment.Multiple modification to these embodiment will be conspicuous concerning those skilled in the art, and defined General Principle can realize under the situation of spirit that does not break away from the utility model embodiment or scope in other embodiments among this paper.Therefore, the utility model embodiment will can not be restricted to these embodiment shown in this paper, but will meet and principle disclosed herein and features of novelty the wideest corresponding to scope.

The above is merely the preferred embodiment of the utility model embodiment; Not in order to restriction the utility model embodiment; All within the spirit and principle of the utility model embodiment; Any modification of being done, be equal to replacement, improvement etc., all should be included within the protection domain of the utility model embodiment.

Claims (1)

1. the image safety check deviation-rectifying system of self-adaptation feedback comprises:

Image detecting apparatus;

The image acquisition equipment that links to each other with said image detecting apparatus;

The image analysis equipment that links to each other with said image acquisition equipment; And

The image feedback equipment that links to each other with said image detecting apparatus, image acquisition equipment and image analysis equipment respectively.

Images