TWM590686U - Fruit sweetness detecting device combined with artificial intelligence and spectral detection - Google Patents

Abstract

A fruit sweetness detecting device combined with artificial intelligence and spectral detection are disclosed. A detection platform is provided for disposing a fruit. An near infrared detecting device generates an infrared beam to illuminate the fruit and receive the reflected beam. A processing device compares the sweetness database corresponding to the fruit variety according to a set of wavelength data in the reflected light beam to determine the sweetness data of the fruit, wherein the processing device uses the artificial intelligence framework to train and establish a sweetness database corresponding to the variety of the fruit. The identification code printing machine is configured to print an identification code on the sticker according to a printing command of the processing device, wherein the identification code corresponds to the information, so that the user can scan the information of the identification code to at least obtain the sweetness of the fruit.

Description

Fruit sweetness detection device combining artificial intelligence and spectrum detection

This creation is a detector, and especially a fruit sweetness detection device combining artificial intelligence and spectrum detection.

Ordinary fruit farmers are unable to purchase high-cost sweetness testing machines, so they generally only screen the appearance of the fruit and record the weight of the fruit, and if there are a large number of fruit harvests, it takes more time to screen, only when the fruit is sent to the farmers association or fruit marketer After that, it is possible to measure the sweetness and then grade the fruit grade, but this will take too much time, and its measurement method will destroy the appearance of the fruit and affect the sale. At present, most of Taiwan's agriculture uses human or destructive technical tests to learn the sweetness of fruits, which not only consumes a lot of manpower, but also has unstable accuracy.

According to the current production traceability system for agricultural products, the QR code of each farm is used to query which fruit farmer is the producer and what products are produced, so as long as the traceability number is marked in the production traceability system, you can know that the fruits and vegetables that consumers buy are Where did it come from, but the traceability number is attached to the fruit carton by QR Code, which is very likely to be forged, and the box of fruit that the consumer may get is not produced by the real farmer.

In view of this, the purpose of this creation is to provide a fruit sweetness detection device that combines artificial intelligence and spectral detection.

In order to achieve one of the aforementioned objectives, the present invention provides a fruit sweetness detection device combining artificial intelligence and spectral detection, at least including: a detection platform for placing a fruit; and a near infrared detection device for generating at least one infrared beam Irradiate fruits and receive at least one reflected beam of reflected light; a processing device, based on a set of wavelength data in the reflected beam, compares the sweetness database corresponding to a variety of fruit to determine the sweetness data of the fruit, where The processing device uses an artificial intelligence framework training to create a sweetness database corresponding to the variety of fruits; and an identification code printer for printing an identification code on a sticker according to a printing instruction of the processing device, wherein the identification code Corresponds to a piece of information, so that the user can identify the identification code information by scanning to obtain at least the sweetness data of the fruit.

The processing device uploads the sweetness data of the fruit and/or the production history of the fruit to a cloud database in a cloud, and the information of the identification code corresponds to an access link in the cloud database.

Among them, the access link is time-sensitive, so that the identification code has a validity period.

Among them, the fruit system has an expiration date, and the cloud database records both the sweetness data and the expiration date of the fruit.

Among them, the validity period of the identification code corresponds to the consumption period of the fruit.

Among them, the group wavelength of the reflected light beam is composed of 450nm, 500nm, 550nm, 570nm, 600 and 650nm.

Among them, the artificial intelligence architecture is a random forest classification architecture, and the processing device uses the random forest classification architecture to train based on the group wavelengths of a plurality of sample fruits and the sweetness values of the sample fruits to obtain a sweetness database.

Among them, the sweetness value of the sample fruit is measured with a sugar meter.

Wherein, the detection platform has a rotating object tray for placing fruit, so that the fruit rotates relative to the near-infrared detection device, so that the near-infrared detection device receives the reflected light beam of the torus of the fruit.

Among them, the artificial intelligence architecture is an inverted transitive neural network architecture, and the processing device is trained with the inverted transitive neural network architecture according to the group wavelength of a plurality of sample fruits and the sweetness value of the sample fruits to obtain a sweetness database.

The fruit sweetness detection device combining artificial intelligence and spectrum detection according to this creation has the following advantages:

(1) Non-destructive measurement of the sweetness of the fruit, so there is no need to worry about destroying the appearance of the fruit, thereby ensuring farmers' rights to produce high-quality fruit.

(2) The near-infrared detection device of this creation only uses the data of six wavelengths, so it is different from the traditional high-end spectrometer with a price of hundreds of thousands of Taiwan dollars, and this creation has certain accuracy and low price. Generally used by small farmers.

(3) The identification code of this creation is time-sensitive, which can prevent the identification code from being forged.

In order to better understand the technical characteristics, content and advantages of this creation and the achievable effects, the accompanying drawings of this creation are described in detail in the form of expressions of the embodiments, and the drawings used therein have the main purpose It is only for the purpose of illustration and supplementary instruction, and may not be the true proportion and precise configuration after the implementation of the creation, so the ratio and configuration relationship of the attached drawings should not be interpreted and limited to the scope of rights of the actual implementation of the creation. In addition, for easy understanding, the same elements in the following embodiments are denoted by the same symbols. In addition, the size ratios of the components shown in the drawings are only for the convenience of explaining the elements and their structures, and are not intended to be limiting.

In addition, the terms used throughout the specification and the scope of patent application, unless otherwise specified, usually have the ordinary meaning that each term is used in this field, in the content disclosed here, and in the special content. Certain terms used to describe this creation will be discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in describing the creation.

Secondly, if the words "include", "include", "have", "include", etc. are used in this article, they are all open terms, which means including but not limited to.

Most of the current methods for detecting the sweetness of fruits on the market are using destructive analysis methods, and this creation uses a near-infrared spectrometer and uses only six wavelengths of data to analyze compounds, which is a type of non-destructive analysis. method. The principle is to use the reflectance caused by the difference in energy level between the molecules and atoms in the substance to identify the characteristic substance in the test substance according to the wavelength change, and then cooperate with the characteristic spectral database of the known substance to launch the composition of each point And structure. Near-infrared spectroscopy is the most studied non-invasive analysis technique. The wavelength range of the near-infrared light region is 780~2500 nm. The molecular functional groups of most substances such as CH, OH, NH, etc., have fixed absorption vibration spectra in this range. As a basis for sweetness measurement, to achieve the purpose of measuring the sweetness of fruit.

This creation is a fruit sweetness detection device combining artificial intelligence and spectrum detection. Please refer to FIG. 1, the fruit sweetness detection device combining artificial intelligence and spectrum detection in this creation includes at least a detection platform 10, a near infrared detection device 20, a processing device 30 and an identification code printer 40. Among them, the detection platform 10 has an object tray 11 for placing the fruit 100. The near-infrared detection device 20 is disposed on the detection platform 20, for example, beside the tray 11, for generating at least one infrared beam to irradiate the surface of the fruit 100 on the tray 11 and receive at least one of the surfaces reflected from the fruit 100 Reflected beam. In this embodiment, the variety of fruits is exemplified by guava. However, this creation is not limited to this, and the varieties applicable to this creation may also be watermelon, pineapple, or cantaloupe, for example. The tray 11 can be stationary or rotating. Among them, if it is a stationary storage tray 11, the near-infrared detection device 20 can measure the data of the reflected beam of the single surface of the fruit 100. If the tray 11 is rotated, the fruit 100 can rotate relative to the near-infrared detection device 20, so the near-infrared detection device 20 can measure the data of the reflected beam of the torus of the fruit 100.

In the fruit sweetness detection device of the present creation, the processing device 30 is provided on the detection platform 10 and is electrically connected to the infrared detection device 20 via a wire, for example. The processing device 30 receives the data signal of the reflected light beam measured by the near-infrared detection device 20 for comparison and analysis. In detail, the processing device 30 compares the sweetness database with a set of specific wavelength data in the reflected light beam to determine the sweetness data of the fruit, wherein the sweetness database corresponds to the variety of the fruit. One feature of this creation is the use of non-destructive detection methods, and the aforementioned set of wavelengths consists of only six wavelengths, of which the six wavelengths are 450nm, 500nm, 550nm, 570nm, 600 and 650nm. In addition, another feature of this creation is the use of artificial intelligence framework to train and establish a sweetness database based on the variety of fruits. For example, the creation can first use artificial intelligence framework to train and establish a sweetness database for a specific variety, such as pearl guava. After the user places the pearl guava on the storage tray 11 and the reflected beam of the fruit is detected by the near-infrared detection device 20, the processing device 30 can set up a sweetness database in advance than the six wavelengths in the reflected beam of the fruit Data (as shown in Figure 2), to determine the sweetness data of this fruit. Similarly, for this creation, for example, the artificial intelligence framework can be used to separately train and establish a sweetness database for various fruit varieties, so that the sweetness data can be detected and judged for various fruit varieties. Taking the guava as an example, the fruit variety may be, for example, pearl guava, imperial guava, red guava, or guava. The artificial intelligence architecture adopted in this creation is, for example, a back propagation neural network architecture (BPNN, Back Propagation Neural Network) or a random forest classification architecture (random decision forests).

For example, as shown in FIG. 3, the processing device 30 is trained based on the random forest classification architecture according to the group wavelengths of a plurality of sample fruits and the sweetness values of the sample fruits to obtain the types corresponding to the sample fruits, respectively Sweetness database. Taking guava as an example, the sample fruit can be, for example, pearl guava, imperial guava, red guava, or guava. Random forest classification is a machine learning integrated learning algorithm. The process is to randomly generate a forest, and the forest is composed of multiple decision trees. The nodes of each tree are the characteristics of the original training. When there is a new When the input sample is entered, each decision tree in the forest is judged separately. In this creation, the data of the six different wavelength bands obtained by the spectral detection device is first used, and then the fruit (sample fruit) is cut to measure the sweetness using the commercially available sugar content measurement to establish a database. After calculating by random forest method, and then predicting which category the fruit spectrum belongs to. In terms of the pearl ballet, which is the subject of this experiment, the corresponding sugar content is between 10-15, and the detection results will be divided into one of six categories. According to the teaching of this creation, those with ordinary knowledge in this creation should know how to use random forest method to train based on the data of six spectral wavelengths to build a database, so this creation will not be described here.

In addition, as shown in FIG. 4, the processing device 30 of the present creation may be based on the sets of wavelengths of a plurality of sample fruits and the sweetness of the sample fruits using, for example, a Back Propagation Neural Network (BPNN) The degree value is trained to obtain a sweetness database corresponding to the types of sample fruits, respectively. Backward transfer neural network architecture is a supervised learning algorithm combined with back propagation (Back Propagation) algorithm, which calculates the gradient of the neural network and corrects the weights to achieve better model accuracy and is trained by supervised learning The data in the spectral database trains the detection model for analyzing the sweetness of the fruit in this creation, and uses artificial intelligence (AI) to reduce the labor cost and the error rate caused by human factors and improve the quality of the fruit. For the same reasons as above, since those who have common knowledge in this creation based on the teachings of this creation, they should be able to learn how to build a database based on the data of six spectral wavelengths with an inverted transitive neural network architecture. The creation is not repeated here.

The creation may also have, for example, an identification code printer 40, commonly known as a labeling machine, which is electrically connected to the processing device 30, for example, by wires, and prints the identification code 44 on the sticker 42 according to the printing instruction of the processing device 30, so as A fruit supplier (for example, a farmer) can stick this sticker 42 on the fruit 100. In other words, after the processing device 30 determines the sweetness data of the fruit, the processing device 30 can generate a print instruction for printing the identification code 44 on the sticker 42. The identification code 44 corresponds to a piece of information, so that a user (such as a consumer) can identify the information corresponding to the identification code 44 by scanning. The identification code 44 is, for example, a two-dimensional code, and the user can scan and identify the information corresponding to the identification code 44 with a two-dimensional code scanner (not shown) such as a mobile phone to obtain at least the sweetness data of the fruit 100 . The type and model of the identification code printer 40 are not particularly limited, as long as the sticker 42 with the identification code 44 can be printed, it can be applied to this creation. In addition, the identification code printer 40 can also be a laser printer, for example, the sticker can be omitted and the two-dimensional code can be printed directly on the surface of the fruit.

In one embodiment of the present creation, the processing device 30 further uploads the sweetness data of the fruit 100 and/or the production history of the fruit to the cloud database 202 located in the cloud 200, and the information of the identification code 44 is, for example, corresponding Here is the access link to the cloud database 202. Therefore, when the user scans with a QR code scanner such as a mobile phone and recognizes the access link corresponding to the identification code 44, the user can read the cloud database 202 on the mobile phone to obtain at least the sweetness data of the fruit 100 . In other words, the identification code 44 of a certain fruit or batch of fruit is only applicable to this fruit or batch of fruit. However, in order to prevent the identification code 44 from being stolen by others and being copied in large quantities, another feature of this creation is that the aforementioned access link is time-sensitive, so that the identification code 44 has an expiration date. For example, the effective time of the aforementioned access link may be, for example, two weeks, for example, September 1, 2019 to September 14, 2019. When the user scans the identification code at a time outside this period of time, even if the access link is obtained, the cloud database cannot be read because of the timeliness of the access link. In this way, this creation can improve food safety and prevent others from forging (piracy printing) label stickers. In another embodiment, the cloud database 202 can also record the sweetness data and the consumption period of the fruit 100 at the same time. Therefore, when the user (consumer) reads the cloud database 202, not only can he know the sweetness data of the fruit, but also whether the fruit has exceeded the consumption period. In yet another embodiment, the expiration date of the identification code 44 may also be, for example, the expiration date corresponding to the fruit 100. In other words, if the consumption period of the fruit 100 is one month, the validity period of the identification code 44 can also be set to one month, for example. Therefore, even if the identification code is pirated by others, it will be easily recognized by the user because the identification code has an expiration date.

The fruit sweetness detection device combining artificial intelligence and spectrum detection according to this creation has the following advantages:

(1) Non-destructive measurement of the sweetness of the fruit, so there is no need to worry about destroying the appearance of the fruit, thereby ensuring farmers' rights to produce high-quality fruit.

(2) The near-infrared detection device of this creation only uses the data of six wavelengths, so it is different from the traditional high-end spectrometer with a price of hundreds of thousands of Taiwan dollars, and this creation has certain accuracy and low price. Generally used by small farmers.

(3) The identification code of this creation is time-sensitive, which can prevent the identification code from being forged.

The above is only exemplary, and not restrictive. Any equivalent modifications or changes made without departing from the spirit and scope of this creation shall be included in the scope of the attached patent application.

10‧‧‧ Testing platform 11‧‧‧Storage tray 20‧‧‧Infrared detection device 30‧‧‧Processing device 40‧‧‧Identification code printer 42‧‧‧ Sticker 44‧‧‧Identification code 100‧‧‧fruit 200‧‧‧Cloud 202‧‧‧ cloud database

FIG. 1 is a schematic diagram of the fruit sweetness detection device combining artificial intelligence and spectrum detection in this creation.

FIG. 2 is a graph showing the wavelength data of fruits measured by the near-infrared detection device of the present invention.

Figure 3 is a schematic diagram showing the random forest classification framework used in this creation.

FIG. 4 is a schematic diagram showing the architecture of a reverse transfer neural network used in this creation.

10‧‧‧ Testing platform

11‧‧‧Storage tray

20‧‧‧Infrared detection device

30‧‧‧Processing device

40‧‧‧Identification code printer

42‧‧‧ Sticker

44‧‧‧Identification code

100‧‧‧fruit

200‧‧‧Cloud

202‧‧‧ cloud database

Claims (10)

A fruit sweetness detection device combining artificial intelligence and spectrum detection, at least comprising: A testing platform for placing a fruit; A near-infrared detection device for generating at least one infrared beam to irradiate the fruit and receive at least one reflected beam reflected; A processing device that compares a sweetness database corresponding to a variety of the fruit based on a set of wavelength data in the reflected beam to determine a sweetness data of the fruit, wherein the processing device uses an artificial intelligence framework Training to establish the sweetness database corresponding to the variety of the fruit; and An identification code printer for printing an identification code on a sticker according to a printing instruction of the processing device, wherein the identification code corresponds to a piece of information, so that the user can identify the identification code by scanning Information to obtain at least the sweetness data of the fruit. A fruit sweetness detection device combining artificial intelligence and spectral detection as described in item 1 of the patent scope, wherein the processing device uploads the sweetness data of the fruit and/or the production history of the fruit to a cloud A cloud database, and the information of the identification code corresponds to an access link of the cloud database. As described in Item 2 of the patent application scope, a fruit sweetness detection device combining artificial intelligence and spectral detection, wherein the access link has a timeliness, so that the identification code has a validity period. A fruit sweetness detection device combining artificial intelligence and spectrum detection as described in item 3 of the patent application scope, wherein the fruit has an expiration date, and the cloud database simultaneously records the sweetness data of the fruit and the expiration date . As described in Item 4 of the patent application scope, a fruit sweetness detection device combining artificial intelligence and spectral detection, wherein the validity period of the identification code corresponds to the consumption period of the fruit. The fruit sweetness detection device combining artificial intelligence and spectrum detection as described in item 1 of the patent application scope, wherein the set of wavelengths of the reflected beam is composed of 450nm, 500nm, 550nm, 570nm, 600 and 650nm. A fruit sweetness detection device combining artificial intelligence and spectral detection as described in item 1 of the patent application scope, wherein the artificial intelligence architecture is a random forest classification architecture, and the processing device is based on a plurality of sample fruits based on the random forest classification architecture The set of wavelengths and the sweetness values of the sample fruits are trained to obtain the sweetness database. As described in item 7 of the patent application scope, a fruit sweetness detection device combining artificial intelligence and spectrum detection, wherein the sweetness values of the sample fruits are measured by a sugar meter. The fruit sweetness detection device combining artificial intelligence and spectrum detection as described in item 1 of the patent scope, wherein the detection platform has a rotating tray for placing the fruit so that the fruit is relative to the near infrared detection device Rotating, so that the near-infrared detecting device receives the reflected beam of the torus of the fruit. A fruit sweetness detection device combining artificial intelligence and spectrum detection as described in item 1 of the patent scope, wherein the artificial intelligence architecture is an inverted transitive neural network architecture, and the processing device is based on the inverted transitive neural network The architecture is trained based on the set of wavelengths of a plurality of sample fruits and the sweetness values of the sample fruits to obtain the sweetness database.

Images