CN109919940B

CN109919940B - Article detection system and method

Info

Publication number: CN109919940B
Application number: CN201910245122.XA
Authority: CN
Inventors: 吴耀光; 季国强; 吴志鹏; 兰枫; 陶雪璇; 郭庆; 吕学文
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2019-03-28
Filing date: 2019-03-28
Publication date: 2020-08-07
Anticipated expiration: 2039-03-28
Also published as: CN109919940A

Abstract

The embodiment of the application provides an article detection system and method, wherein the system comprises: the device comprises a first conveyor belt (1), an image acquisition device (2), a radio frequency identification reader (3), a memory (4) and a processor (5). When detecting an article, firstly, acquiring the identifier of the detected article by using a radio frequency identification reader (3), then acquiring the current image of the detected article by using an image acquisition device (2), and finally, processing by using a processor (5), wherein the method comprises the following steps: determining the type of the detected article according to the identification of the detected article, comparing the current image with the standard image, analyzing whether the detected article meets the preset standard or not, and sending out a signal so as to further process the detected article which does not meet the preset standard in time. By adopting the article detection system and method, whether the surface of the detected article is damaged or stained can be better detected.

Description

Article detection system and method

Technical Field

The embodiment of the application relates to the technical field of detection, in particular to an article detection system and method.

Background

In actual life, most factories generally set quality detection links for articles in order to ensure that the finally processed articles meet certain quality requirements. Taking the example of washing linen in a washing factory, linen is generally folded before being put into a washing system (for example, linen with a large area is folded in advance by a folding machine), which may cause that stains on the inner layer cannot be washed in the washing process, resulting in the final backwashing, so how to detect uncleaned linen is an essential work for the linen washing industry.

In the related art, how to detect uncleaned linen is generally provided with the following technical schemes: 1) the scheduling staff checks at the folder: the cleaned linen is usually folded automatically by a folding machine, and if an inspector detects unclean linen in advance in the folding process of the folding machine, the dirty linen is not folded; 2) setting a rechecking link: manually checking the linen inspected by the folding machine again, and selecting the linen which is not cleaned; 3) check before use: for example, a hotel attendant, upon checking in a room (e.g., laying sheets, tablecloths, etc.), may find uncleaned linen.

However, the above-mentioned several technical solutions have certain drawbacks: 1) when the folder is checked, only one folded side can be detected, and the other side is possibly stained and cannot be detected; 2) the setting of the rechecking link requires additional manpower consumption (generally 1 to 2 persons), which increases the labor cost; 3) the method is characterized in that the time for backwashing the linen is delayed and the use experience of a user is influenced if unclean linen is not detected before use.

Therefore, in the related art, how to better detect the object is an urgent problem to be solved.

Disclosure of Invention

The embodiment of the application provides an article detection system and method, which aim to solve the problems in the related art.

A first aspect of an embodiment of the present application provides an article detection system, including:

the system comprises a first conveyor belt 1, an image acquisition device 2, a radio frequency identification reader 3, a memory 4 and a processor 5;

the first conveyor belt 1 has a first end 1111 and a second end 1112 for transmitting the detected item carrying the rfid tag from the first end 1111 to the second end 1112;

the radio frequency identification reader 3 is arranged above or at the side of the first conveyor belt 1, and the radio frequency identification reader 3 is used for reading a radio frequency signal returned by the detected object when the detected object passes through the radio frequency identification reader so as to determine the identifier of the detected object;

the memory 4 stores parameter values of standard images corresponding to the types of the detected articles;

the image acquisition device 2 is arranged below or on the side of the second end 1112 and is used for acquiring a current image of the detected object during the sliding process of the detected object from the second end 1112;

the processor 5 is configured to identify the type of the detected object according to the identifier of the detected object, compare the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object, and output a signal indicating whether the surface of the detected object is damaged or stained.

A second aspect of the embodiments of the present application provides an article detection method, which is applied to an article detection system, where the system includes: the system comprises a first conveyor belt, an image acquisition device, a radio frequency identification reader, a memory and a processor; the first conveyor belt has a first end and a second end for conveying the detected items carrying radio frequency identification tags from the first end to the second end; the radio frequency identification reader is arranged above or on the side of the first conveyor belt; the image acquisition device is arranged below or on the side of the second end part; the memory stores parameter values of a standard image corresponding to the identification of the detected object;

the method comprises the following steps:

the radio frequency identification reader transmits a radio frequency signal, and receives and processes the radio frequency signal returned by the detected object when the detected object passes through the radio frequency identification reader so as to determine the identification of the detected object;

the image acquisition device acquires a current image of the detected object during the period that the detected object slides off the second end part and sends the current image to the processor;

the processor performs the steps of:

identifying the type of the detected object according to the identifier determined by the radio frequency identification reader;

reading parameter values of a standard image corresponding to the type of the detected object from the memory;

comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object;

and outputting a signal representing whether the surface of the detected object is damaged or stained according to the comparison result.

By adopting the article detection system and the method provided by the embodiment of the application, firstly, the identification of the detected article is obtained by utilizing the radio frequency identification reader 3 during the movement of the detected article along with the first conveyor belt 1; then, during the period that the detected object slides down from the first conveyor belt 1, the current image of the detected object is acquired by the image acquisition device 2; finally, the processor 5 processes the current image of the detected object, including: the type of the detected article is determined according to the identifier of the detected article, the current image of the detected article read from the image acquisition device 2 is compared with the standard image corresponding to the type of the detected article read from the memory 4 to determine whether the detected article meets a preset standard (for example, the detected article does not meet the preset standard when stains or damages exist on the surface of the detected article), and a signal is sent so that a worker or related equipment can timely perform further processing on the detected article which does not meet the preset standard. By adopting the article detection system and the article detection method, whether the surface of the detected article is damaged or stained can be better detected. In addition, the steps are automatically executed by the system, manual participation is not needed, and labor cost is greatly reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.

FIG. 1 is a schematic diagram illustrating an item detection system according to one embodiment;

FIG. 2 is a schematic diagram (top view) illustrating capturing a current image of a detected item according to one embodiment;

FIG. 3 is a schematic diagram (top view) illustrating capturing a current image of a detected item according to another embodiment;

FIG. 4 is a flow diagram illustrating a method of item detection according to one embodiment.

In the figure: a first conveyor belt-1; a first end-1111; a second end-1112; an image acquisition device-2; a first image capturing device-21; a second image capturing device-22; a radio frequency identification reader-3; a memory-4; a processor-5; mirror surface-6; a first mirror surface-61; a second mirrored surface-62; an image rectification module-7; a light source-8; a light sensor-9; a regulating circuit-10; a second conveyor belt-11; an inlet end-1121; an outlet end-1122; a folder-12; an ironing machine-13; a server-14; sorter-15; a slide off sensor-16.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

FIG. 1 is a schematic diagram illustrating an item detection system, according to one embodiment. Referring to fig. 1, an article detection system provided in the embodiment of the present application includes a first conveyor belt 1, an image acquisition device 2, a radio frequency identification reader 3, a memory 4, and a processor 5;

the radio frequency identification reader 3 is arranged above or on the side of the first conveyor belt 1, and the radio frequency identification reader 3 is used for reading a radio frequency signal returned by the detected object when the detected object passes through the radio frequency identification reader 3 so as to determine the identifier of the detected object.

In this embodiment, the detected object carrying the rfid tag enters the first conveyor belt 1 from the first end portion 1111 and follows the first conveyor belt 1 to the second end portion 1112. The rfid reader 3 can be disposed at any position before the detected object enters the first end portion 1111, at any position above the first end portion 1111 and the second end portion 1112, at any position at the exit of the second end portion 1112, and at any other position which does not affect the motion state of the detected object and can better identify the rfid tag. The different types of the RFID tags carried by the detected objects are different in identification, and the RFID reader 3 can judge the identification of the detected object according to the RF signal returned by the RFID tag.

Taking the example of detecting the damage or the stain on the linen when the detected article is the linen, firstly, the linen processed in the previous link (such as drying, ironing and the like) is put into the first end portion 1111 of the first conveyor belt 1 one by one, and during the movement of the linen along with the first conveyor belt 1, the radio frequency identification reader 3 emits a radio frequency signal, receives the radio frequency signal returned by the radio frequency identification tag, and determines the identification of the linen according to the returned radio frequency signal.

The memory 4 stores parameter values of a standard image corresponding to the type of the detected object.

In this embodiment, the standard image refers to an image that is previously recorded before any type of detected object is put into use for the first time. The parameter values refer to a plurality of indices describing image information such as color, style, and the like of the standard image. The color includes hue (i.e., a name indicating a certain color with a relatively high degree of certainty, such as rose bengal, orange, lemon yellow, etc.), lightness (i.e., brightness of the color, such as yellow having different effects such as deep yellow, medium yellow, light yellow, etc., at different lightness), and purity (i.e., purity of the color, which indicates a ratio of color components contained in the color, and the higher the ratio of color components contained in the color, the higher the purity).

Taking the detected object as linen for example, before detecting multiple types of linen (such as bed sheets, quilt covers and the like), the standard images of the detected objects of all types are collected firstly. For example: when the bed sheet is white and no pattern exists on the bed sheet, the acquired standard image is a picture with a white background; another example is: when the bed sheet is white and a star pattern is arranged on the bed sheet, the collected standard image is a picture with a white background and a star pattern arranged on the background. After the standard images of the detected objects of a plurality of types are collected, each image and the corresponding parameter value are stored in the memory 4.

The image capturing device 2 is disposed below or beside the second end 1112, and is configured to capture a current image of the detected object during the period that the detected object slides off the second end 1112. Specifically, the slip period herein means a period between a time when the first slip end of the detected article slips off the second end 1112 of the first conveyor belt 1 and a time when the last slip end of the detected article contacts another object (for example, the second conveyor belt). For example, a light sensor or a mechanical sensor (not shown) disposed at the second end 1112 of the first conveyor belt may be used to detect whether the detected object starts to slide down, or a light sensor or a mechanical sensor (not shown) disposed at the second conveyor belt may be used to detect whether the detected object finishes sliding down (i.e. the end that finally slides down contacts other objects). Here, since the image capturing device 2 is disposed below or on the side of the second end 1112 and captures the current image of the detected object during the period when the detected object slides off the second end 1112, it is not required that the conveyor belt is made of a transparent material, so that the multi-surface detection of the detected object can be realized, and the manufacturing cost of the apparatus is reduced; and through the mode of slipping off, there is no specific requirement (for example, the linen is required to be in a specific long strip shape) to the shape of the linen, the requirement to the linen is reduced, and the article detection system of the application can be more widely applied to the detection occasions of various articles.

In the present embodiment, the image capturing device 2 is used to capture images of the detected objects sliding off the first conveyor belt 1 one by one. The current image is an image of the detected object captured by the image capturing device 2 during the period of slipping. Here, the current image may be a frame of image acquired by the image acquisition device 2, a multi-frame image, or a frame of image spliced by a plurality of frames of images. In other words, the image capturing device 2 may capture one frame of image during the sliding of the linen, compare the frame of image with the standard image, splice the captured multiple frames of images into one frame of image, and compare the frame of image with the standard image, or compare the captured multiple frames of images with the multiple frames of standard images respectively.

The current image may be the same as or different from the standard image, for example: after the white bed sheet is polluted, the standard image is a picture with a white background, and the current image is a polluted image (not a picture with a pure white background), so that the current image is different from the standard image; another example is: the white bed sheet is not polluted, and the current image is the same as the standard image. It will be appreciated by those skilled in the art herein that the inspected article is in a spread state on the first conveyor belt, so that when it slides off the first conveyor belt, it is also in a spread state, so that the accuracy of the comparison by the processor 5 can be determined. The spreading of the inspected article may be accomplished by machine or manually prior to placement on the first conveyor.

In the present embodiment, the processor 5 has a function of analyzing the standard image and the current image. The processor 5 is in communication connection with the radio frequency identification reader 3, the memory 4 and the image acquisition device 2 respectively, and the specific working process is as follows: firstly, reading the identification of a detected article from a radio frequency identification reader 3, determining the type of the detected article according to the identification, and then acquiring the current image of the detected article from an image acquisition device 2 and reading a standard image corresponding to the type of the detected article from a memory 4; comparing the current image of the detected object with the standard image, comparing whether the parameter value corresponding to the current image is equal to the parameter value corresponding to the standard image, and if the parameter value corresponding to the current image is equal to the parameter value corresponding to the standard image, indicating that the detected object meets the preset standard, namely, no stain or damage exists; if the two are not equal, the detected object does not meet the preset standard, namely, the detected object is stained or damaged; thirdly, when the detected object does not meet the preset standard, the processor 5 sends out a signal, and the signal is used for representing whether the surface of the detected object is damaged or stained. Optionally, the processor 5 is connected to an alarm device, and the processor 5 controls the alarm device to send an alarm signal according to the sent signal, where the alarm signal may be sound or light as a medium, for example: sound alarm, light flashing, etc. Through the limitation of the image acquisition during the sliding process in the patent, the image acquired by the image acquisition device 2 can be ensured to be the image of the detected object, so that the processor 5 is prevented from comparing the image of the non-detected object with the standard image to obtain an error comparison result. If other matched software is added into the article detection system, the current image of the detected article is acquired during the falling period of the detected article, so that the consumption of computing resources caused by identifying and eliminating the image of the non-detected article can be reduced.

In various embodiments of the present application, the article detection system may detect whether there is a damage on the surface of the detected article by: when the breakage exists, the current image of the detected object is different from the standard image. For example: when the detected object is a bed sheet, if one part of the white bed sheet is damaged, even if there is no stain, the current image acquired by the image acquisition device 2 is different from the standard image.

The operation of the processor 5 will be described below by taking the example that the detected object is linen. If the processor 5 reads data during operation: if the linen is in the type of bed sheet, the current image is a picture with white background, and the standard image is a picture with white background, the obtained comparison result indicates that the bed sheet is not damaged or stained; if the processor 5 reads data during operation: the linen is in a type of bed sheet, the current image is a picture with white background and black stain, and the standard image is a picture with white background, the obtained comparison result is that the bed sheet is damaged or stained, and at the moment, the alarm device is controlled to send out an alarm signal and inform a worker to process or other equipment to carry out the next operation.

In each embodiment of the application, the fact that the current image is the same as the standard image means that the variation range of the parameter value of the current image is within a preset range compared with the parameter value of the standard image; the fact that the current image is different from the standard image means that the variation range of the parameter value of the current image is beyond the preset range compared with the parameter value of the standard image. For example: when the article detection system is applied to the linen washing industry, that is, when the detected article is linen, because the linen inevitably deforms after being washed for a plurality of times, the processor 5 needs to consider the geometric deformation condition (for example, new linen generally shrinks by about 10% after being washed for the first time) when comparing the current image with the standard image, and if the deformation degree of the current image is not beyond the preset range compared with the standard image, the linen is free of stains and damage; and if the deformation degree of the current image is larger than the preset range compared with the standard image, the stain or damage of the linen is represented. Another example is: when analyzing the current image and the standard image, the processor 5 considers the geometric deformation condition and the change condition of the step value of the color value, namely when the geometric deformation and the step value exceed the preset range, determines that the linen is stained or damaged.

In this embodiment, when the detected object moves along with the first conveyor belt 1, the detected object sequentially passes through the radio frequency identification reader 3 and the image acquisition device 2, wherein the radio frequency identification reader 3 is used for identifying the identifier of the radio frequency identification tag carried by the detected object, so as to determine the type of the detected object subsequently; the image acquisition device 2 is used for acquiring the current image of the detected object, and manual operation is not needed in the process, so that the labor cost is greatly reduced. Then, the processor 5 analyzes whether the detected object meets a preset standard (for example, the detected object does not meet the preset standard when stains or damages exist on the surface of the detected object) according to the parameter value of the current image of the detected object and the parameter value of the standard image corresponding to the type of the detected object read from the memory 4, and sends a signal so that a worker or related equipment can process the detected object in time. By adopting the article detection system and method provided by the application, whether the surface of the detected article is damaged or stained can be better detected, manual participation is not needed, and the labor cost is greatly reduced.

Preferably, with reference to fig. 1, the image acquisition device 2 comprises:

the first image acquisition device 21 and the second image acquisition device 22 are disposed on opposite sides of a lower left side of the second end 1112, and are configured to respectively acquire a current image of a first surface of the detected article and a current image of a second surface of the detected article during sliding of the detected article from the second end 1112, where the second surface is opposite to the first surface.

In this embodiment, the inspected article comprises at least two surfaces, one image capturing sub-assembly (e.g., the first image capturing device 21) captures a current image of one of the surfaces, and the other image capturing sub-assembly (e.g., the second image capturing device 22) captures a current image of the other surface. For example: when the detected article is a sheet, if the first image capturing device 21 is used to capture the current image of the front surface (usually the surface with patterns) of the sheet when the sheet slides off the second end 1112, the second image capturing device 22 is used to capture the current image of the back surface (usually the surface without patterns) of the sheet.

In addition, the image capturing device 2 in the embodiments of the present application may further include two or more image capturing sub-components, for example: when the detected object comprises a plurality of surfaces, an image acquisition sub-component can be respectively arranged in a plurality of key directions to acquire current images of the detected object in a plurality of directions, so that the accuracy of the final detection result is improved.

FIG. 2 is a schematic diagram (top view) illustrating an embodiment of capturing a current image of an inspected article. Fig. 2 is a plan view from above, in which the travel path of light is indicated by a straight line with arrows, and the inspected object is indicated by a rectangular vertical bar. In one embodiment, the image capture device 2 is disposed below the second end 1112; the system further comprises:

a first mirror surface 61 and a second mirror surface 62, wherein the first mirror surface 61 and the second mirror surface 62 are oppositely arranged below the second end 1112; the image capturing device 2 is used to capture a current image of a first surface and a current image of a second surface of the inspected object, which is opposite to the first surface, reflected by the first mirror surface 61 and the second mirror surface 62, respectively, during the period when the inspected object slides off the second end 1112.

In this embodiment, the article detection system further includes: a first mirror surface 61 and a second mirror surface 62. In this case, the image capturing device 2 may comprise only one image capturing sub-assembly. Referring to fig. 2, the first reflecting mirror 61, the second reflecting mirror 62 and the image capturing device 2 are respectively disposed according to the positions shown in fig. 2, when the object to be detected slides off the second end 1112 of the first conveyor belt 1, the first reflecting mirror 61 can reflect the first surface of the object to be detected, the second reflecting mirror 62 can reflect the second surface of the object to be detected, the image capturing device 2 captures the current image of the first surface of the object to be detected from the first reflecting mirror 61, and the current image of the second surface of the object to be detected from the second reflecting mirror 62. Since the first mirror surface 61 and the second mirror surface 62 are oppositely disposed below the second end portion 1112, the image capturing device 2 can capture the current image of the first surface of the detected object and the current image of the second surface opposite to the first surface through the two mirror surfaces. For example, in the current image, the current image of the first surface is a reflection image of the front surface of the detected object, and the current image of the second surface is a reflection image of the back surface of the detected object. In this case, the standard image of the first surface in which the reflection map of the front surface of the object to be inspected is stored and the standard image of the second surface in which the reflection map of the back surface of the object to be inspected is stored are also divided into the standard image of the first surface in which the reflection map of the back surface of the object to be inspected is stored.

In the embodiment, the two reflecting mirror surfaces (for example, the first reflecting mirror surface 61 and the second reflecting mirror surface 62) and the image acquisition device 2 are adopted to complete the acquisition of the current image of the detected object, and compared with the original method that two image acquisition devices 2 are used to respectively acquire the current images of the first surface and the second surface of the detected object, the image acquisition cost is saved.

FIG. 3 is a schematic diagram (top view) illustrating capturing a current image of a detected item according to another embodiment. Fig. 3 is a plan view from above, in which the travel path of light is indicated by a straight line with arrows, and the inspected object is indicated by a rectangular vertical bar. In another embodiment, the image capture device 2 is disposed below the second end 1112; the system further comprises:

a mirror surface 6 disposed below the second end 1112 so as to face the image pickup device 2;

the image capturing device 2 is configured to capture a current image of a first surface of the detected object and a current image of a second surface of the detected object, which is opposite to the first surface, reflected by the mirror surface 6 during the sliding of the detected object from the second end 1112.

In this embodiment, the article detection system further includes: a mirror surface 6. In this case, the image capturing device 2 may comprise only one image capturing sub-assembly. Referring to fig. 3, the mirror surface 6 and the image capturing device 2 are respectively disposed according to the positions shown in fig. 3, when the detected object slides off the second end 1112 of the first conveyor belt 1, the mirror surface 6 can reflect the first surface of the detected object, and since the image capturing device 2 is disposed at a side close to the second surface of the detected object, the image capturing device 2 can capture the current image of the first surface of the detected object while capturing the current image of the second surface of the detected object. Since the reflecting mirror surface 6 is disposed below the second end 1112 opposite to the image capturing device 2, the image capturing device 2 can directly capture the current image of the second surface of the detected object on the one hand, and can capture the current image of the first surface of the detected object through the reflecting mirror surface 6 on the other hand. For example, in the current image, the current image of the first surface is the image of the front side of the detected object, and the current image of the second surface is the reflection image of the back side of the detected object. In this case, the standard image of the first surface in which the reflection map of the front surface of the object to be inspected is stored and the standard image of the second surface in which the reflection map of the back surface of the object to be inspected is stored are also divided into the standard image of the first surface in which the reflection map of the back surface of the object to be inspected is stored.

In the embodiment, the current image of the detected object is acquired by adopting the reflecting mirror surface 6 and the image acquisition device 2, and compared with the original method that the two image acquisition devices 2 are used for respectively acquiring the current images of the first surface and the second surface of the detected object, the method saves the image acquisition cost.

Optionally, the item detection system further comprises: and the image correction module 7 is used for correcting the current image of the first surface and the current image of the second surface acquired by the image acquisition device 2.

Referring to fig. 2, since the first reflecting mirror 61 and the second reflecting mirror 62 are disposed at an angle to the horizontal plane, the current image of the first surface of the inspected article captured by the image capturing device 2 from the first reflecting mirror 61 may be distorted compared to the front image of the first surface, and the current image of the second surface of the inspected article captured from the second reflecting mirror 62 may be distorted compared to the front image of the second surface. Similarly, the current image of the detected object captured by the mirror surface 6 shown in fig. 3 may be distorted compared with the front image of the first surface, so that when the object detection system includes the image rectification module 7, the image captured by the image capture device 2 can be rectified, which is convenient for improving the accuracy of the comparison result obtained by the processor 5.

In combination with the foregoing embodiments, the article detection system may further include a light source 8, a light sensor 9, and an adjusting circuit 10, which are disposed below or beside the image capturing device 2. Wherein the light sensor 9 is different from the slip sensor 16.

In this embodiment, the light source 8 may be an incandescent lamp, an L ED lamp, or other elements for providing illumination, during the operation of the image capturing device 2, due to the external environment (e.g., weather factors such as cloudy days, rainy days, etc., or failure of the elements for providing illumination, etc.), sufficient brightness may not be obtained to capture the current image of the detected object, or the quality of the captured current image is not high, so that in order to ensure efficient operation of the object detecting system, the light source 8 is additionally provided for the image capturing device 2.

The light source 8, the light sensor 9 and the adjusting circuit 10 are usually a set of light adjusting devices, which can be disposed under, beside or at other positions of the image capturing device 2 without affecting the operation of the image capturing device 2 and the movement of the object to be detected. The adjusting circuit 10 is electrically connected to the light source 8 and the light sensor 9, respectively.

The light sensor 9 is used for detecting the light intensity of the environment where the detected object is located.

The adjusting circuit 10 adjusts the intensity of the light emitted by the light source 8 according to whether the intensity of the light detected by the light sensor 9 is lower than a preset intensity.

In this embodiment, the light Sensor 9 (L light-Sensor, which can detect the brightness of the current environment of the target device and automatically adjust the brightness) can detect the brightness of the current environment of the image capturing apparatus 2 at any time and send the brightness value to the adjusting circuit (a circuit having the function of adjusting the intensity of the light emitted from the light source 8), the adjusting circuit 10 includes a comparing circuit, the input end of which can receive two input values, one is the brightness value sent by the light Sensor 9 and the other is a preset reference signal, and the output end of which is connected to an adjustable resistor in the power supply of the light source 8, and the adjusting circuit adjusts the intensity of the light by adjusting the adjustable resistor, specifically, when the brightness value is lower than the preset reference signal, the intensity of the light is increased, and when the brightness value is higher than the preset reference signal, the output end of the comparing circuit is connected to the input end, and the output value of the comparing circuit is applied to the input value of the input end to adjust the input end to achieve the adjustment

Taking the example that the image acquisition device 2 acquires the current image of the bed sheet when the detected object is the bed sheet, if the weather is dark at the acquisition time, the acquired current image may be dark, so that the processor 5 cannot well distinguish the difference between the current image and the standard image, and thus cannot clearly judge whether the bed sheet has stains or stains. Under the condition, if a light adjusting device (including a light source 8, a light sensor 9 and an adjusting circuit 10) is arranged, when the light adjusting device detects that the brightness value of the current environment is lower than a preset brightness value, the light is automatically supplemented to the image acquisition device 2, and the current image acquired by the image acquisition device 2 is ensured to meet certain definition.

In this embodiment, the light adjustment device (including the light source 8, the light sensor 9, and the adjustment circuit 10) can help the image capturing apparatus 2 better cope with the situation of insufficient light of the external environment, so that the current image captured by the image capturing apparatus 2 has sufficient definition, and the accuracy of the comparison result of the processor 5 is improved.

Referring to fig. 1, the article detection system further includes a second conveyor belt 11 and a folder 12;

the second conveyor belt 11 is located below the folder 12 or passes through the folder 12;

the second conveyor belt 11 has an inlet end 1121 and an outlet end 1122, the inlet end 1121 is located below the second end 1112 and above the image capturing device 2, the detected objects slide down from the second end 1112 to the inlet end 1121, and the second conveyor belt 11 is configured to convey the detected objects from the inlet end 1121 to the outlet end 1122;

the folding machine 12 folds or unfolds the detected article according to the signal sent by the processor 5.

In this embodiment, the article detection system including the folding machine 12 is suitable for a scene where the detected article is linen, and after washing the linen, the washing factory generally needs to fold the linen (for example, a bed sheet, a quilt cover, etc. need to be folded) and then deliver the linen to the customer, so the folding machine 12 generally needs to be arranged.

In practical applications, the second conveyor belt 11 may be arranged below the folding machine 12 or pass through the folding machine 12, and fig. 1 illustrates the second conveyor belt 11 passing through the folding machine 12 as an example.

The inlet end 1121 of the second conveyor belt 11 is located at the second end 1112 of the first conveyor belt 1 and enters the inlet end 1121 of the second conveyor belt 11 when the linen slides off the second end 1112. Before the linen enters the folding machine 12, the processor 5 can judge whether the linen is stained or damaged one by one and send a signal to the folding machine 12, and the folding machine 12 receives the indication signal and carries out corresponding operation on the detected object according to the indication signal. For example: when the detected object is linen, the folding machine 12 receives the indication signal sent by the processor 5 and judges, and if the indication signal is judged to represent that the surface of the detected object is damaged or stained, the folding operation is not executed on the linen; if the indication signal is judged to represent that the surface of the detected object is not damaged and has no stain, the linen is folded.

In the embodiment, the folding machine 12 does not perform the folding operation on the linen with stains or damaged, so that all the folded linen is ensured to be the linen without stains or damaged, and the folded linen is conveniently and directly delivered to the customer for use.

Referring to fig. 1, the article detection system further comprises an ironing machine 13, wherein the ironing machine 13 is located above the first conveyor belt 1 and is used for ironing the detected article on the first conveyor belt 1.

In this embodiment, the article detection system including the ironing machine 13 is suitable for a scene where the detected article is linen, and after the linen is washed, the washing plant generally needs to perform ironing processing and then folding processing.

In combination with the foregoing embodiments, the article detection system may further include: and the database is connected with the memory 4 and comprises parameter values of the standard images corresponding to the detected objects of various types respectively.

In this embodiment, the database stores the standard images and the corresponding parameter values corresponding to each type of the detected object, and when the standard images and the corresponding parameter values in the memory 4 are lost due to a failure or other reasons, they can be imported again from the database. The database provides a backup function for the standard image and the corresponding parameter values, ensuring that the processor 5 can work normally.

In combination with the foregoing embodiments, the article detection system may further include: a server 14 connected to the image capturing apparatus 2;

the image acquisition device 2 acquires standard images of various types of detected objects and sends the standard images to the server 14, and the server 14 analyzes the standard images of the various types of detected objects and determines parameter values of the standard images corresponding to the various types of detected objects respectively.

In this embodiment, the server 14 may be configured to store standard images and corresponding parameter values of each type of detected object, and the function of the server is similar to that of the database in the above embodiment, and the specific working process is as follows: first, a plurality of indices for describing an image are manually configured in the server 14, for example: selecting a hue (e.g., defining a color wheel); setting the brightness (e.g., the white to black transition can be set to ten steps); set purity, etc. Then, the standard images of the respective types of the inspected article acquired are received from the image acquiring device 2. Next, the standard image is analyzed to determine parameter values of the standard image corresponding to each type of the object to be detected, and for example, the parameter values of the standard image of each type of the object to be detected can be obtained by matching hue, lightness, and the like arranged in the server 14 with the standard image. Finally, the standard image and its carried parameter values are saved for easy reading from the server 14 by the memory 4.

In the above implementation, if the standard image received by the server 14 from the image capturing device 2 is composed of a plurality of identical parts, for example: if the standard image contains a plurality of identical checkered patterns or a plurality of identical pentagram patterns, the standard image is cut out, and the image containing the smallest pattern unit is reserved, for example: the standard image containing a plurality of identical checkered patterns is cut into an image containing only one checkered pattern, or the standard image containing a plurality of identical pentagram patterns is cut into an image containing only one pentagram pattern. Similarly, when reading the current image from the image capture device 2, the processor 5 only needs to read the image containing the smallest pattern unit, and does not need to read the current image containing all the patterns.

In this embodiment, server 14 may be used to store not only standard images of each type of item being inspected, but also current images of each type of item being inspected, and the results of each item being inspected as analyzed by processor 5, to facilitate evaluation or improvement of the item detection system.

In various embodiments of the present application, the memory 4 is further configured to store a plurality of images carrying smudge free markings or breakage free markings, such as: an intelligent image library is arranged in the memory 4 and is connected with the processor 5, and the intelligent image library comprises a plurality of images carrying stain-free marks or breakage-free marks. After the detected object is used for a long time, a wrinkle phenomenon may exist, or other normal phenomena without stains or damages may exist, but the phenomena may cause the processor 5 to misjudge that the stains or damages exist, so that the problem can be solved well by adding the intelligent image library.

Specifically, some common images, which are not dirty or damaged, may be added into the intelligent image library, and when the processor 5 compares and analyzes the standard image and the current image, if a dirty or damaged result is obtained, the standard image and the current image are matched again with the image in the intelligent image library, and if the matching is successful, the comparison result obtained at present is incorrect, that is, there is no dirty or damaged phenomenon. For example: when the article detection system is applied to the linen washing industry, some common images (such as wrinkled images, faded images and the like) which possibly cause misjudgment of the processor 5 can be added into the intelligent image library, and the comparison result finally obtained by the processor 5 can be ensured to be consistent with the actual situation as much as possible.

In combination with the foregoing embodiments, the article detection system may further include: and the sorter 15 is connected with the processor 5 and is used for sorting the detected object when the signal sent by the processor 5 indicates that the surface of the detected object is damaged or stained.

In the embodiment, the sorter 15 receives and judges the indication signal sent by the processor 5, and performs corresponding operation on the detected article according to the judgment result. For example: when the detected object is linen, if the sorter 15 judges that the indication signal represents the surface damage or the stain of the detected object, the detected object is sorted out; if the sorter 15 judges that the indication signal is indicative of no damage and no stain on the surface of the detected object, the detected object is not processed.

In connection with the above-described embodiment, in the case where the article detection system includes both the folder 12 and the sorter 15, since the folder 12 does not fold the linen determined to be broken or stained by the processor 5, and the sorter 15 can also sort out the unfolded linen output from the folder 12.

In combination with the above embodiments, the article detection system may further include: a slip sensor 16. The slipping sensor 16 is electrically connected to the image capturing device 2, and is configured to detect whether a detected object passes through and whether the detected object passes through completely, and provide a slipping start signal and a slipping end signal to the image capturing device 2. The supply signal may be directly supplied or indirectly supplied via another circuit element such as a processor. The slip start signal may be sent at the time when the slip sensor detects the passing of the detected object, and the slip end signal may be sent at the time when the slip sensor detects the complete passing of the detected object, or may be sent after a predetermined time (e.g., 1 second) after the time when the slip sensor detects the complete passing of the detected object.

The slip sensor 16, which may be an optical or mechanical sensor, may be located at any position below the second end 1112 of the first conveyor belt, for example: the second end 1112 of the first conveyor may be disposed at any position below (as shown in fig. 1), or may be disposed at the inlet end 1121 of the second conveyor (although not shown, those skilled in the art may determine the mounting position as needed), or may be disposed in the image capturing device 2. For example, when the slip sensor 16 is a light sensor, when the detected object passes through, the light of the light sensor changes from the non-shielded state to the shielded state, which causes the electrical signal of the light sensor to change, for example, from high level to low level, and the falling edge from high level to low level is used as the slip start signal. After the detected object completely passes through, the light of the light sensor is changed from a shielded state to an unshielded state, the electric signal of the light sensor is changed, for example, from a low level to a high level, and the rising edge from the low level to the high level is used as a sliding end signal; or the end-of-slipping signal may be sent after a predetermined time period after the rising edge from the low level to the high level. When the slip sensor 16 is a mechanical sensor, the mechanical sensor is triggered, for example, in the following manner: the change of the position of the probe triggered by the sliding of the detected object causes the change of the electric signal. How to define the slip start signal and the slip end signal may be similar to the above-mentioned definition of the light sensor, and for brevity, the detailed description is omitted. It is understood that the function of the slip sensor 16 may also be integrated within the image capturing device 2, i.e. the image capturing function and the slip sensing function are combined by the image capturing device 2. Specifically, the image capturing device 2 may capture a plurality of images of the detected object during the period in which the detected object slides down, then recognize an image not including the detected object and an image including the detected object from the plurality of images based on an image recognition algorithm, and generate a sliding start signal (for example, generated when the image including the detected object is detected for the first time) and a sliding end signal (for example, generated when the image including the detected object is detected for the last time) according to whether the plurality of images include the detected object.

Based on the same inventive concept, an embodiment of the present application provides an article detection method, which is applied to an article detection system, and the system includes: the system comprises a first conveyor belt 1, an image acquisition device 2, a radio frequency identification reader 3, a memory 4 and a processor 5; the first conveyor belt 1 has a first end 1111 and a second end 1112 for transmitting the detected item carrying the rfid tag from the first end 1111 to the second end 1112; the radio frequency identification reader 3 is arranged above or at the side of the first conveyor belt 1; the image acquisition device 2 is arranged below or on the side of the second end part 1112; the memory 4 stores parameter values of a standard image corresponding to the identification of the detected object;

FIG. 4 is a flow diagram illustrating a method of item detection according to one embodiment. Referring to fig. 4, the method includes the steps of:

step S11: the radio frequency identification reader transmits radio frequency signals, and receives and processes the radio frequency signals returned by the detected object when the detected object passes through the radio frequency identification reader so as to determine the identification of the detected object.

Step S12: the image capturing device captures a current image of the detected object during the time the detected object slides off the second end 1112 and sends the current image to the processor.

Step S13: the processor analyzes the current image of the detected item.

Wherein, step S13 includes:

and identifying the type of the detected object according to the identifier determined by the radio frequency identification reader 3.

And reading the parameter value of the standard image corresponding to the type of the detected object from the memory 4.

And comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object.

In the embodiment of the application, the radio frequency identification reader 3 is used for determining the identification of the detected object and then sending the identification to the comparison processor 5; the memory 4 is used for storing standard images of various types of detected articles; the image acquisition device 2 is used for acquiring a current image of the detected object and then sending the current image to the processor 5; the processor 5 firstly determines the type of the detected object according to the identifier of the detected object, then compares the standard image of the detected object corresponding to the type, which is acquired from the memory 4, with the acquired current image, judges whether the detected object meets a preset standard (for example, when the detected object has stain or is damaged, the detected object does not meet the preset standard), and then sends a signal so as to facilitate other equipment or staff to further process the detected object. The specific implementation of steps S11-S13 is described above.

In one embodiment, the image capture device 2 comprises: a first image capturing device 21 and a second image capturing device 22, wherein the first image capturing device 21 and the second image capturing device 22 are disposed on opposite sides of the lower portion of the second end 1112.

Specifically, step S12 may include:

step S121 a: during the sliding of the detected object off the second end 1112, the first image capture device captures a current image of a first surface of the detected object;

step S122 a: during the time that the detected item slides off the second end 1112, the second image capture device captures a current image of a second surface of the detected item.

In the present embodiment, the image capturing device 2 captures current images of the detected object from two opposite directions, for example: when the detected object is linen, the current image of the first surface is acquired by the first image acquisition device 21, and the current image of the second surface (the first surface is opposite to the second surface) is acquired by the second image acquisition device 22, so that the accuracy of the comparison result of the processor 5 is improved.

In another embodiment, the image capturing device 2 is disposed below the second end 1112, and the system further comprises: a first reflective mirror surface 61 and a second reflective mirror surface 62, wherein the first reflective mirror surface 61 and the second reflective mirror surface 62 are oppositely disposed below the second end 1112.

Specifically, step S12 may include:

step S121 b: during the time that the inspected article slides off the second end 1112, the first image capture device captures a current image of the first surface of the inspected article reflected via the first mirror surface.

Step S122 b: during the time that the inspected object slides off the second end 1112, the second image capture device captures a current image of a second surface of the inspected object reflected via the second mirror surface, the second surface being opposite the first surface.

Referring to fig. 2, the first reflecting mirror 61 can reflect the current image of the first surface of the inspected object, and the second reflecting mirror 62 can reflect the current image of the second surface of the inspected object, so that when the image capturing device 2 has only one image capturing sub-assembly, the capturing of the current images of the first surface and the second surface of the inspected object can be completed if the first reflecting mirror 61 and the second reflecting mirror 62 are arranged as shown in fig. 2. The specific collection method can be referred to the above.

In another embodiment, the image capture device 2 is disposed below the second end 1112; the system further comprises: and a mirror surface 6 disposed below the second end 1112 so as to face the image pickup device 2.

Specifically, step S12 may include:

step S121 c: during the time that the detected object slides off the second end 1112, the image capture device captures a current image of the first surface of the detected object.

Step S122 c: during the time that the detected object slides off the second end 1112, the image capture device captures a current image of a second surface of the detected object reflected via the mirror surface, the second surface being opposite the first surface.

Referring to fig. 3, the mirror surface 6 can reflect the current image of the first surface of the inspected article, so that when the image capturing device 2 has only one image capturing sub-component, if the mirror surface 6 and the image capturing device 2 are arranged as shown in fig. 3, the capturing of the current image of the first surface and the second surface of the inspected article can be completed. The specific collection method can be referred to the above.

In combination with the above embodiments, the article detection system may further include: and an image rectification module 7. After the acquiring of the current image of the detected object and before comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object, the method further includes:

step S21: the image rectification module acquires a current image of the first surface and a current image of the second surface acquired by the image acquisition device.

Step S22: the image rectification module rectifies a current image of the first surface and a current image of the second surface.

In this embodiment, when the object detection system includes the image rectification module 7, the image collected by the image collection device 2 can be rectified, so as to improve the accuracy of the comparison result obtained by the processor 5.

In various embodiments of the present application, the item detection system may further include: and the light source 8, the light sensor 9 and the adjusting circuit 10 are arranged below or on the side of the image acquisition device 2.

Optionally, the method further comprises:

step S31: the light sensor detects the light intensity of the environment where the detected object is located.

Step S32: when the light intensity is lower than the preset intensity, the adjusting circuit controls the light source to enhance the emitted light intensity.

Step S33: when the light intensity is higher than the preset intensity, the adjusting circuit controls the light source to weaken the emitted light intensity.

In the present embodiment, the light adjusting device (including the light source 8, the light sensor 9 and the adjusting circuit 10) is arranged around the image capturing apparatus 2 to prevent the problem of the captured current image being blurred due to the dark external light, such as: when the weather is dark, in order to ensure that the image acquisition device 2 can normally acquire the current image of the detected object, the adjusting circuit 10 can automatically adjust the light intensity around the detected object according to the data of the light sensor 9.

In various embodiments of the present application, the item detection system may further include: a second conveyor belt 11 and a folder 12; the second conveyor belt 11 is located below the folder 12 or passes through the folder 12; the second conveyor belt 11 has an entrance end 1121 and an exit end 1122, the entrance end 1121 is located below the second end 1112 of the first conveyor belt 1, the detected objects slide down from the second end 1112 of the first conveyor belt 1 to the entrance end 1121 of the second conveyor belt 11, and the second conveyor belt 11 is configured to convey the detected objects from the entrance end 1121 to the exit end 1122.

Optionally, the method further comprises:

step S41: the folder receives the signal output by the processor.

Step S42: and when the signal represents that the surface of the detected object is damaged or stained, the folding machine folds the detected object.

Step S43: when the signal represents that the surface of the detected object is damaged or stained, the folding machine does not fold the detected object.

In an actual scene, when the detected object is linen, a folding link is usually required to be set, for example: for some linen with larger area, after washing, the linen is folded by the folding machine 12 and then delivered to the customer, and the specific folding process can be referred to above.

In various embodiments of the present application, the item detection system may further include: the ironing machine 13 is located above the first conveyor belt 1, and before the detected article enters the first conveyor belt 1, the ironing machine 13 is used for ironing the detected article.

In various embodiments of the present application, the item detection system may further include: and the server 14 is connected with the image acquisition device 2.

Optionally, the method further comprises:

step S51: the image acquisition device acquires standard images of various types of detected objects and sends the standard images to the server.

Step S52: and the server analyzes the standard images of the detected objects of various types and determines the parameter values of the standard images corresponding to the detected objects of various types respectively.

Step S53: the server sends the parameter values of the standard image to the memory.

In this embodiment, the server 14 is mainly used to store standard images and parameters of each type of detected object, current images and parameters, the result of the detected object analyzed by the comparison circuit, or other data helpful for evaluating or improving the object detection system. The workflow of the server 14 can be referred to as described above.

Optionally, the memory 4 further stores an intelligent image library including a plurality of images carrying no-stain marks or no-breakage marks.

Specifically, comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object includes:

preliminarily comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object to obtain a preliminary comparison result;

and if the preliminary comparison result represents that the surface of the detected object is damaged or stained, matching the current image with the image in the intelligent image library.

Further, outputting a signal representing whether the surface of the detected object is damaged or stained according to the comparison result, comprising:

if the preliminary comparison result indicates that the surface of the detected object is not damaged and has no stains, outputting a signal indicating that the surface of the detected object is not damaged and has no stains, or

When the current image is successfully matched with the image in the intelligent image library, outputting a signal representing that the surface of the detected object is not damaged and has no stain;

and when the current image is failed to be matched with the image in the intelligent image library, outputting a signal representing that the surface of the detected object is damaged or stained.

After the detected object is used for a long time, a wrinkle phenomenon may exist, or other normal phenomena without stains or damages may exist, but the phenomena may cause the processor 5 to misjudge that the stains or damages exist, so that the problem can be solved well by adding the intelligent image library. For a detailed description of the intelligent image library, reference is made to the foregoing.

In various embodiments of the present application, the item detection system may further include: a sorter 15, said sorter 15 being connected to said processor 5. The method may further comprise:

the sorter 15 receives the signal output by the processor 5;

when the signal indicates that the surface of the detected object is damaged or stained, the sorter 15 sorts the detected object.

In various embodiments of the present application, the item detection system may further include: a slip sensor 16. The slipping sensor 16 is electrically connected to the image capturing device 2, and is configured to detect whether a detected object passes through and whether the detected object passes through completely, and provide a slipping start signal and a slipping end signal to the image capturing device 2.

It is understood that the function of the slip sensor 16 may also be integrated within the image capturing device 2, i.e. the image capturing function and the slip sensing function are combined by the image capturing device 2. Specifically, the image capturing device 2 may capture a plurality of images of the detected object during the period in which the detected object slides down, then recognize an image not including the detected object and an image including the detected object from the plurality of images based on an image recognition algorithm, and generate a sliding start signal (for example, generated when the image including the detected object is detected for the first time) and a sliding end signal (for example, generated when the image including the detected object is detected for the last time) according to whether the plurality of images include the detected object.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The above detailed description is provided for an article detection system and method, and specific examples are applied herein to illustrate the principles and embodiments of the present application, and the above description of the embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An item detection system, comprising:

the device comprises a first conveyor belt (1), an image acquisition device (2), a radio frequency identification reader (3), a memory (4) and a processor (5);

the first conveyor belt (1) has a first end (1111) and a second end (1112) for transporting a detected item carrying a radio frequency identification tag from the first end (1111) to the second end (1112);

the radio frequency identification reader (3) is arranged above or at the side of the first conveyor belt (1), and the radio frequency identification reader (3) is used for reading a radio frequency signal returned by the detected object when the detected object passes through the radio frequency identification reader so as to determine the identifier of the detected object;

the memory (4) stores parameter values of a standard image corresponding to the type of the detected object; the memory (4) is also used for storing an intelligent image library, the intelligent image library comprises a plurality of images carrying stain-free marks or breakage-free marks, and the images are images left by articles after long-term use;

the image acquisition device (2) is arranged below or on the side of the second end part (1112) and is used for acquiring a current image of the detected object during the sliding process of the detected object from the second end part (1112);

the processor (5) is used for identifying the type of the detected article according to the identifier of the detected article, and comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected article to obtain a preliminary comparison result;

and the processor (5) is also used for verifying the preliminary comparison result according to the image stored in the intelligent image library under the condition that the preliminary comparison result represents that the surface of the detected object is damaged or stained, so as to output a signal representing whether the surface of the detected object is damaged or stained.

2. The system according to claim 1, characterized in that the image acquisition device (2) comprises:

a first image acquisition device (21) and a second image acquisition device (22), wherein the first image acquisition device (21) and the second image acquisition device (22) are arranged at two opposite sides below the second end part (1112) and are used for respectively acquiring a current image of a first surface and a current image of a second surface of the detected object during the sliding of the detected object from the second end part (1112), and the second surface is opposite to the first surface.

3. The system according to claim 1, wherein the image acquisition device (2) is disposed below the second end portion (1112), the system further comprising:

a first mirror surface (61) and a second mirror surface (62), the first mirror surface (61) and the second mirror surface (62) being disposed opposite each other below the second end portion (1112);

the image acquisition device (2) is used for respectively acquiring a current image of a first surface and a current image of a second surface of the detected object, which are reflected by the first reflecting mirror surface (61) and the second reflecting mirror surface (62), during the sliding of the detected object from the second end part (1112), wherein the second surface is opposite to the first surface.

4. The system according to claim 1, characterized in that said image acquisition device (2) is disposed below said second end (1112); the system further comprises:

a mirror surface (6) disposed below the second end portion (1112) so as to face the image pickup device (2);

the image acquisition device (2) is used for acquiring a current image of a first surface of the detected object and a current image of a second surface of the detected object reflected by the reflecting mirror surface (6) during the sliding of the detected object from the second end part (1112), wherein the second surface is opposite to the first surface.

5. The system according to claim 3 or 4, characterized in that it further comprises: an image rectification module (7) for rectifying the current image of the first surface and the current image of the second surface acquired by the image acquisition device (2).

6. The system according to claim 1, characterized in that it further comprises a light source (8), a light sensor (9) and an adjusting circuit (10), arranged below or to the side of the image acquisition device (2);

the light sensor (9) detects the light intensity of the environment where the detected object is located;

the adjusting circuit (10) adjusts the light intensity emitted by the light source (8) according to whether the light intensity detected by the light sensor (9) is lower than a preset intensity.

7. The system of claim 1, further comprising: a second conveyor belt (11) and a folder (12);

the second conveyor belt (11) is located below the folder (12) or passes through the folder (12);

the second conveyor belt (11) is provided with an inlet end (1121) and an outlet end (1121), the inlet end (1121) is positioned below the second end (1112) of the first conveyor belt (1), the detected objects slide down from the second end (1112) of the first conveyor belt (1) to the inlet end (1121) of the second conveyor belt (11), and the second conveyor belt (11) is used for conveying the detected objects from the inlet end (1121) to the outlet end (1122);

the folding machine (12) folds or unfolds the detected article according to the signal sent by the processor (5).

8. The system of claim 1, further comprising: the ironing machine (13) is located above the first conveyor belt (1) and is used for ironing the detected articles on the first conveyor belt (1).

9. The system of claim 1, further comprising: a server (14) connected to the image acquisition device (2);

the image acquisition device (2) acquires standard images of various types of detected articles and sends the standard images to the server (14), and the server (14) is used for analyzing the standard images of the various types of detected articles and determining parameter values of the standard images corresponding to the various types of detected articles respectively.

10. The system of claim 1, further comprising: the sorter (15) is connected with the processor (5) and is used for sorting the detected object when the signal sent by the processor (5) indicates that the surface of the detected object is damaged or stained.

11. The system of claim 1, further comprising: the device comprises a sliding sensor (16), wherein the sliding sensor (16) is electrically connected with the image acquisition device (2) and is used for detecting whether the detected object passes through and whether the detected object passes through completely, and providing a sliding starting signal and a sliding ending signal for the image acquisition device (2), and the sliding period refers to the time between the generation moment of the sliding starting signal and the generation moment of the sliding ending signal.

12. An article detection method is applied to an article detection system, and the system comprises: the system comprises a first conveyor belt, an image acquisition device, a radio frequency identification reader, a memory and a processor; the first conveyor belt has a first end and a second end for conveying the detected items carrying radio frequency identification tags from the first end to the second end; the radio frequency identification reader is arranged above or on the side of the first conveyor belt; the image acquisition device is arranged below or on the side of the second end part; the memory stores parameter values of a standard image corresponding to the identification of the detected object; the storage also stores an intelligent image library, the intelligent image library comprises a plurality of images carrying no stain marks or no damage marks, and the images are images left after the article is used for a long time;

the method comprises the following steps:

the processor performs the steps of:

comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object to obtain a preliminary comparison result;

and under the condition that the preliminary comparison result represents that the surface of the detected object is damaged or stained, verifying the preliminary comparison result according to the image stored in the intelligent image library so as to output a signal representing whether the surface of the detected object is damaged or stained.

13. The method of claim 12, wherein the image acquisition device comprises: the first image acquisition device and the second image acquisition device are arranged on two opposite sides below the second end part;

the image acquisition device acquires a current image of the detected object during the sliding of the detected object from the second end, and the image acquisition device comprises:

the first image acquisition device acquires a current image of a first surface of the detected object during the sliding of the detected object from the second end; and

the second image acquisition device acquires a current image of a second surface of the detected object during the sliding of the detected object from the second end.

14. The method of claim 12, wherein the image capture device is disposed below the second end, the system further comprising:

the first reflecting mirror surface and the second reflecting mirror surface are oppositely arranged below the second end part;

the first image acquisition device acquires a current image of the first surface of the detected object reflected by the first reflection mirror surface during the sliding of the detected object from the second end part; and

the second image acquisition device acquires a current image of a second surface of the detected object reflected by the second reflection mirror surface during the sliding of the detected object from the second end, the second surface being opposite to the first surface.

15. The method of claim 12, wherein the image capture device is disposed below the second end; the system further comprises:

the reflecting mirror surface is arranged below the second end part opposite to the image acquisition device;

the image acquisition device acquires a current image of the first surface of the detected object during the sliding of the detected object from the second end; and

the image capture device captures a current image of a second surface of the inspected article reflected via the mirror surface during the period when the inspected article slides off the second end, the second surface being opposite to the first surface.

16. The method of claim 14 or 15, wherein the system further comprises: an image rectification module;

after the acquiring of the current image of the detected object and before comparing the parameter value of the current image with the parameter value of the standard image corresponding to the type of the detected object, the method further includes:

the image correction module acquires a current image of the first surface and a current image of the second surface acquired by the image acquisition device;

the image rectification module rectifies a current image of the first surface and a current image of the second surface.

17. The method of claim 12, wherein the system further comprises a light source, a light sensor, and an adjustment circuit disposed below or to the side of the image capture device;

the method further comprises the following steps:

the light sensor detects the light intensity of the environment where the detected object is located;

when the light intensity is lower than the preset intensity, the adjusting circuit controls the light source to enhance the intensity of the emitted light;

when the light intensity is higher than the preset intensity, the adjusting circuit controls the light source to weaken the emitted light intensity.

18. The method of claim 12, wherein the system further comprises: a second conveyor belt and a folder; the second conveyor belt is positioned below the folding machine or passes through the folding machine; the second conveyor belt is provided with an inlet end and an outlet end, the inlet end is positioned below the second end of the first conveyor belt, the detected objects slide down from the second end of the first conveyor belt to the inlet end of the second conveyor belt, and the second conveyor belt is used for conveying the detected objects from the inlet end to the outlet end;

the method further comprises the following steps:

the folding machine receives the signal output by the processor;

the folding machine executes the following operations on the detected article according to the signal:

when the signal represents that the surface of the detected object is damaged or stained, the folding machine folds the detected object;

when the signal represents that the surface of the detected object is damaged or stained, the folding machine does not fold the detected object.

19. The method of claim 12, wherein the system further comprises: an ironing machine positioned above the first conveyor belt, the method further comprising, prior to the detected article entering the first conveyor belt:

the ironing machine irons the detected articles.

20. The method of claim 12, wherein the system further comprises: the server is connected with the image acquisition device;

the method further comprises the following steps:

the image acquisition device acquires standard images of various types of detected articles and sends the standard images to the server;

the server analyzes the standard images of the detected objects of various types and determines the parameter values of the standard images corresponding to the detected objects of various types respectively;

the server sends the parameter values of the standard image to the memory.

21. The method of claim 12, further comprising:

if the preliminary comparison result represents that the surface of the detected object is not damaged and has no stains, outputting a signal representing that the surface of the detected object is not damaged and has no stains;

the step of verifying the preliminary comparison result according to the image stored in the intelligent image library to output a signal indicating whether the surface of the detected object is damaged or stained under the condition that the preliminary comparison result indicates that the surface of the detected object is damaged or stained comprises the steps of:

if the preliminary comparison result represents that the surface of the detected object is damaged or stained, matching the current image with the image in the intelligent image library;

22. The method of claim 12, wherein the system further comprises: a sorter coupled to the processor;

the method further comprises the following steps:

the sorter receives the signal output by the processor;

when the signal represents that the surface of the detected object is damaged or stained, the sorter sorts out the detected object.

23. The method of claim 12, wherein the system further comprises: the image acquisition device is electrically connected with the image acquisition device and used for acquiring the image of the detected object; the slip period is a time between a generation time of the slip start signal and a generation time of the slip end signal.