WO2020111611A1

WO2020111611A1 - Apparatus for analyzing food nutrient intake amount, and method thereof

Info

Publication number: WO2020111611A1
Application number: PCT/KR2019/015665
Authority: WO
Inventors: 문상준
Original assignee: 울산과학기술원
Priority date: 2018-11-29
Filing date: 2019-11-15
Publication date: 2020-06-04
Also published as: KR20200064508A

Abstract

An apparatus for analyzing food nutrient intake amount according to one embodiment of the present invention, comprises: a weight measurement part which has a shelf part capable of rotating in a state in which food is placed thereon, and a weight sensor, and obtains weight data on the food; a volume measurement part which obtains volume data on the food from a two-dimensional curvature image of the food rotated by the weight measurement part; an optical spectrum measurement part which obtains optical spectrum information about a specific point on the food rotated by the weight measurement part; and an analysis part which calculates weight information and volume information on the food by using the weight data and the volume data, respectively, and analyzes the nutrient composition ratio of the food and the content of each nutrient in the food by using the weight information, the volume information, and the optical spectrum information.

Description

Food nutrient intake analysis device and method

The present invention relates to an apparatus and method for analyzing food nutrient intake, and more particularly, to an apparatus and method for analyzing nutrient intake of a complex food.

People eat a variety of foods in their daily lives. Eating adequate calorie foods is good for your health, but consistently eating more calories than your daily recommendation is bad for your health. However, it is not easy to check and manage the calories of foods that people want to eat, and how many calories to eat.

As interest in health increased, so did the desire to know not only the calories consumed but also the nutrient intake of the foods consumed. An example is a food ingredient list attached to a complex food displayed in a convenience store or mart. However, in the case of cooked food, it is not easy to determine the intake amount for each nutrient, and it is only possible to measure calories or intake using data disclosed on the Internet.

An object of the present invention is to provide a food nutrient intake analysis device and a method capable of grasping the intake amount for each nutrient of a complex food as being devised to solve the aforementioned problems.

In order to solve the above problems, a food nutrient intake analysis device according to an embodiment of the present invention includes a shelf unit and a weight sensor that can rotate in a state where food is placed, and a weight measuring unit to obtain weight data of the food, Volume measurement unit for obtaining the volume data of the food from the two-dimensional curvature image of the food rotating by the weight measuring unit, a light spectrum for obtaining light spectrum information for a specific point of the food rotating by the weight measuring unit Calculate the weight information and the volume information of the food using the measurement unit and the weight data and the volume data, respectively, and analyze the nutrient component ratio and the nutrient content of the food by using the weight information, volume information, and light spectrum information Includes analysis section.

The weight sensor is characterized in that the FSR (Force Sensitive Resistor) sensor.

The volume measurement unit includes a grid generating projector that generates a plurality of two-dimensional curvature images by projecting light onto food rotating by the weight measurement unit, and an image acquisition unit that captures the plurality of two-dimensional curvature images, and the analysis unit comprises the Characterized in that the volume information of the food is calculated by converting a plurality of two-dimensional curvature images.

The optical spectrum measuring unit may obtain the optical spectrum information by using the laser mixed light of the grating generating projector as a light source.

The analysis unit is a nutrient analysis unit that calculates the nutrient component ratio from the light spectrum information using a pre-stored prediction model, and inputs the type of food, and analyzes a material that calculates the material composition ratio of the food using a pre-stored standard recipe DB Part, an additional analysis unit for calculating the nutrient component ratio for each material from the composition ratio of the material using the optical spectrum DB for each material and the optical spectrum DB for each nutrient, and the weight information, the volume information, the nutrient component ratio, and the nutrient component ratio for each material It characterized in that it comprises a content analysis unit for calculating the nutrient content of the food by using.

The prediction model is characterized in that it is a neural network generated by learning light spectrum information of a composite food.

Food nutrient intake analysis method according to another embodiment of the present invention is an input step of receiving a type of food, the measurement step of measuring the weight data, volume data and light spectrum information of the food and using the weight data and volume data And an analysis step of calculating the weight information and the volume information of the food and analyzing the nutrient component ratio and content of the food using the weight information, the volume information, and the light spectrum information.

The measuring step includes a weight measuring step in which the weight measuring unit measures the weight data using an FSR sensor, a volume measuring step in which the volume measuring unit captures a plurality of two-dimensional curvature images from food rotated by the weight measuring unit, and an optical spectrum. The measuring unit includes a light spectrum measuring step of obtaining light spectrum information on a specific point of the food, and the analyzing step is characterized in that the volume information is calculated by converting the plurality of two-dimensional curvature images.

The analysis step includes a component analysis step of calculating the nutrient component ratio of the food from the predictive model using the light spectrum information and a content for calculating the nutrient content of the food by using the weight information, the volume information, and the nutrient component ratio Characterized in that it comprises an analysis step.

The analysis step is a material analysis step of calculating the material composition ratio of the food from the standard recipe DB using the type of food before the content analysis step and the material composition ratio using the light spectrum DB for each material and the light spectrum DB for each nutrient. Further comprising an additional component analysis step for calculating the nutrient component ratio by material from the content analysis step is to calculate the nutrient content of the food by using the weight information, the volume information, the nutrient component ratio and the nutrient component ratio of each material It is characterized by.

The apparatus and method for analyzing food nutrient intake according to an embodiment of the present invention are not based on the individual's perception, but are analyzed using measured food information (weight, volume, and light spectrum), thereby enabling more accurate analysis. .

In addition, since the present invention uses a prediction model to which machine learning is applied, the precision of nutrient analysis through spectral information can be improved.

In addition, the present invention is calculated by considering the nutrient component ratio of each material as a single food as well as the nutrient component ratio of the composite food, so it is possible to accurately analyze the nutritional components.

1 is a view for explaining a method of measuring the nutrient intake of food according to the prior art.

2 is a view showing the configuration of a food nutrient intake analysis device according to an embodiment of the present invention.

3 is a view showing a food nutrient intake analysis device implemented according to an embodiment of the present invention.

4 is a flowchart illustrating a method for analyzing food nutrient intake according to another embodiment of the present invention.

5 is a flowchart illustrating in detail the analysis steps of the food nutrient intake analysis method according to another embodiment of the present invention.

The present invention can be applied to various changes and can have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

In describing each drawing, similar reference numerals are used for similar components. Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from other components.

For example, the first component may be referred to as a second component without departing from the scope of the present invention, and similarly, the second component may be referred to as a first component. The term "and/or" includes a combination of a plurality of related described items or any one of a plurality of related described items.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the present invention pertains.

Terms such as those defined in a commonly used dictionary should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Should not.

Hereinafter, an apparatus and method for analyzing food nutrient intake according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

Prior art analyzes nutrient intake based on individual perception.

Referring to FIG. 1, in the prior art, the user inputs information A, B applying a standard recipe DB, C analyzing food ingredients, D calculating food intake by component, and intake analysis result output It includes step E.

In step A, the user inputs the type of food ingested and estimates and inputs the volume and weight of the food with the naked eye. For example, in the case of volume, the scale of the improved vessel is visually checked and entered.

In step B, the material composition ratio according to the type of the ingested food is determined from the standard recipe DB. The standard recipe DB is a database containing information on the composition ratio of the composite food. The composite food means food containing a plurality of ingredients, for example, a dead composite food, and rice and water correspond to the ingredients. The material composition ratio is information on the proportion of rice, water, and other materials contained in porridge.

In step C, the nutrient content for each material is calculated using the nutritional ingredient DB for each material based on the composition ratio. The nutritional ingredient DB for each material is a database that stores information about the content of each nutrient based on the serving amount (g) for each material. For example, rice (high amount rice) is 67.8 g of carbohydrates and 10.1 g of protein based on one serving (100 g). Contains 3.7 g of fat.

Calculate the nutrient content of the intake food using the volume and weight information entered by the user in step D and the result of calculating the nutrient content for each material.

In step E, for the analysis of nutrient intake per day, the content of each nutrient and calorie calculation results are output together. Specifically, if you consumed 280 g of porridge, you would get results such as 84 g of carbohydrate, 14 g of protein and 12 g of fat, and 500 kcal of calories.

As described above, in the case of the prior art, accuracy may be lacked in that weight and volume must be measured and input based on the individual's perception.

2, the food nutrient intake analysis apparatus 100 according to an embodiment of the present invention includes a weight measuring unit 110, a volume measuring unit 120, a light spectrum measuring unit 130 and an analysis unit 140 It may include.

The weight measuring unit 110 measures food weight data. Specifically, the weight measuring unit 110 may include a shelf 111 that can rotate while the food is placed and a weight sensor 112 that senses the weight of the food. The food and drink may include a single food and a composite food.

The shelf 111 can be rotated 360 degrees in a state where the food is placed by the power means. Volume measurement and light spectrum measurement are possible by rotating the shelf 111. This will be described later.

The weight sensor 112 may be a pressure sensor. However, the present invention is not limited thereto, and the weight sensor 112 includes all types of sensors capable of measuring weight, such as a load cell or a Force Sensing Resistor (FSR) sensor.

The load cell is a load sensing sensor using an elastic body proportionally changed by an external force and a strain gauge that converts it into an electrical signal. The load cell plays a key role in factory control and automation in various industrial fields, from commercial electronic scales to industrial large-capacity electronic meters.

The FSR (Force Sensing Resistor) is a polymer film in which a decreasing resistance occurs when increasing the force on the sensor surface. The FSR has an advantage in that it has little electrical hysteresis when compared to conductive rubber, and has little influence of vibration and heat when compared to a piezo film, and has low cost.

Since the weight data does not correspond to the actual weight, but corresponds to the voltage or resistance value (ohm) measured by the sensor, the weight measurement unit 110 transmits the weight data to the analysis unit 140 to convert it into actual weight information.

The volume measurement unit 120 acquires volume data for the food. Specifically, the volume measurement unit 120 captures the two-dimensional curvature image of the food rotating by the weight measurement unit 110 to obtain the volume data. In more detail, the volume measurement unit 120 may include a grid generation projector 121 and an image acquisition unit 122.

The grid generation projector 121 generates a plurality of two-dimensional curvature images by irradiating laser light with respect to food rotating by the weight measuring unit 110. Specifically, the grid generating projector 121 may include a two-dimensional flat grid and a projector.

The two-dimensional planar grid has a grid shape, and it is possible to adjust the size of the grid and the size of a single unit according to the size of the food in consideration of volumetric resolution.

The projector may be implemented as a DLP laser projector. However, the present invention is not limited thereto, and the projector may include all types of laser projectors capable of irradiating laser mixed light. The DLP stands for Digital Light Processing.

According to an embodiment of the present invention, the grating generating projector 121 may operate as a light source of the light spectrum measuring unit 130.

The image acquisition unit 122 captures a plurality of two-dimensional curvature images. Specifically, the image acquisition unit 122 captures the two-dimensional curvature image multiple times while the food is rotated by the weight measurement unit 110.

The volume data refers to data including the plurality of two-dimensional curvature images, and, like the weight data, the volume measurement unit 120 analyzes the volume data for conversion because it is not the actual volume of the food. ).

The optical spectrum measuring unit 130 acquires the optical spectrum information of the food.

Specifically, the optical spectrum measurement unit 130 may include an optical spectrum generation unit 131 and an optical spectrum detection unit 132.

The optical spectrum generator 131 generates a spectrum capable of analyzing the chemical composition of the food. The optical spectrum generator 131 may include a light source, a filter, a first guide mirror, and an optical lens.

The light source may be combined with two or more plural laser light sources or a combination of one laser light source and an LED light source to generate light having a specific spectrum having a specific spectrum for analysis of food and beverage. Can produce The laser light source may be selectively combined according to foods to be analyzed during a Blu-ray optical pickup such as Near Infrared Ray, Red, and Violet. The light source can be replaced by a grid generating projector 121.

The first filter causes the light generated by the light source to scatter according to the chemical constituent molecules of the food, and at least one of a narrow band laser cleaning filter and a band-pass filter It can include any one.

The first guide mirror reflects the light scattered from the first filter to the optical lens, and transmits the reflected and transmitted light from the food to the optical spectrum detector 132.

The optical lens condenses light generated by the light source to be incident on the food. The optical lens may be implemented as an objective lens so that light transmitted and reflected from the food is transmitted toward the light spectrum detector 132.

The light spectrum detector 132 detects a spectrum of light transmitted and reflected from the food. Specifically, the optical spectrum detector 132 may include a second filter, a spectrometer, and a second guide mirror.

The second filter separates spectral signals of light transmitted and reflected from the food from disturbance. The second filter may include a long-pass filter.

The spectrometer receives the spectral signal separated by the first filter from the second guide mirror and detects light spectrum information of the food.

Specifically, the spectrometer may include an embedding unit and a CCD sensor. The embedding unit is a built-in microcontroller, and may be configured to include an Mbed, a device for connecting to the Internet, and an arduino, which is a substrate to which sensors and the like can be attached. The CCD sensor is a sensor that converts light into electric charges to obtain an image, and extracts specific spectral data for the sample.

The second guide mirror is installed on the optical path of light passing through the second filter to reflect the reflected light to the spectrometer.

The optical spectrum measurement unit 130 transmits the optical spectrum information to the analysis unit 140.

The analysis unit 140 analyzes the nutrient component ratio and the content of each nutrient in the food.

Specifically, the analysis unit 140 analyzes the nutrient component ratio and the content of each nutrient in the food using the weight information, the volume information, and the light spectrum information. In more detail, the analysis unit 140 may include a nutrient analysis unit 141, a material analysis unit 142, an additional analysis unit 143, and a content analysis unit 144.

In the prior art, in order to analyze the nutrient components of food, analysis was generally performed using statistics through a linear/nonlinear prediction model. This method of analysis is not suitable for complex foods containing various nutrients. In an embodiment of the present invention, a machine learning algorithm is applied to calculate the nutrient content ratio of the food.

Specifically, the nutrient analysis unit 141 calculates the nutrient component ratio from the light spectrum information using a pre-stored prediction model. The prediction model is a neural network formed by learning the light spectrum of a complex food.

The prediction model may be a convolutional neural network (CNN). However, the present invention is not limited thereto, and may be a neural network to which other machine learning algorithms are applied.

The material analysis unit 142 receives the type of the food and calculates the material composition ratio of the food by using a pre-stored standard recipe DB. The material analysis unit 142 may be implemented to include an input unit (not shown) to receive the type of food from the user. The input unit may be an external input device through a cable such as a keyboard or a mouse, or may be a touch panel integrally included in the configuration of the material analysis unit 142.

When the user inputs the type of food and beverage through the input unit, the material analysis unit 142 calculates a material composition ratio of the material and the proportion of the food and beverage using the standard recipe DB.

The standard recipe DB may be pre-stored in the material analysis unit 142, but is not limited thereto, and may be a standard recipe DB accessible through the Internet. To this end, the analysis unit 140 may be provided with a communication means for wired and wireless communication.

The material analysis unit 142 transfers the calculated material composition ratio to the additional analysis unit 143.

The light spectrum distinguishes the types of nutrients, but the fact that the intensity (intensity) of a specific peak (internal frequency) is high cannot be concluded as containing a lot of nutrients, and more precise measurement is required to know the nutrient content.

The present invention calculates the nutrient component ratio of each material as a single food as well as the nutrient component ratio as a composite food in order to increase the accuracy of the nutrient content calculation according to an embodiment.

Specifically, the additional analysis unit 143 calculates the nutrient component ratio for each material from the material composition ratio using the light spectrum DB for each material and the light spectrum DB for each nutrient.

The additional analysis unit 143 calculates the ratio of nutrients contained in each food material by using the light spectrum DB for each material and the light spectrum DB for each nutrient.

The light spectrum DB for each material means a database in which the light spectrum of food ingredients (eg, rice) is stored. The light spectrum DB for each nutrient means a database in which the light spectrum DB of nutrients (eg, carbohydrates) is stored.

The content analysis unit 144 calculates the nutrient content of the food by using the information about the food.

Specifically, the content analysis unit 144 calculates the weight and volume information of the food. Thereafter, the content analysis unit 144 calculates the nutrient content of the food by using weight information, volume information, the nutrient component ratio, and the nutrient component ratio for each material.

The content analysis unit 144 calculates the weight information of the food using weight data received from the weight measurement unit 110. When the weight sensor 112 is implemented as an FSR sensor, the content analysis unit 144 obtains the weight information of the food using the weight data using a mass correction DB.

The content analysis unit 144 calculates the volume information of the food by converting a plurality of 2D curvature images, which are volume data received from the volume measurement unit 120. Specifically, the content analysis unit 144 calculates the three-dimensional shape and volume information of the food by collecting the plurality of two-dimensional curvature images.

The content analysis unit 144 performs quantitative analysis using the nutrient component ratio and the nutrient component ratio for each material based on the calculated weight information and volume information. That is, the content analysis unit 144 calculates how much each nutrient is actually contained in the weight (or volume) of the food. The content analysis unit 144 calculates by using the nutrient ingredient ratio for each material together with the nutrient ingredient ratio to increase the accuracy of content analysis.

The content analysis unit 144 uses the weight information and volume information in performing quantitative analysis. Most light spectrum data do not take into account the weight of moisture. In order to know the moisture content of food, it is necessary to know the weight and density of the food. The density is mass per unit volume, and according to the definition, the content analysis unit 144 calculates the content of water contained in the food using the weight information and the volume information.

The content analysis unit 144 calculates each nutrient content using the water content, the nutrient content ratio, and the nutrient content ratio for each material. The content analysis unit 144 may express the content of each nutrient in grams (g), but is not limited thereto, and may also be expressed in a user-specified unit (for example, mL).

The content analysis unit 144 may output the results of calculation of each nutrient content to the user. To this end, the content analysis unit 144 may include a display unit (not shown). In this case, according to an embodiment of the present invention, the input unit of the material analysis unit 142 and the display unit of the content analysis unit 144 may be integrally implemented as a touch panel.

As described above, the apparatus 100 for analyzing food nutrient intake according to an embodiment of the present invention is not based on an individual's perception, but rather analyzes using measured food information (weight, volume, light spectrum). This is possible.

Although each component of the food nutrient intake analysis apparatus 100 in FIG. 3 is arranged as a separate component, this is illustratively illustrated for explanation. Referring to FIG. 3, an apple is placed on the shelf 111 and the weight sensor 112 measures the weight data of the apple. The weight sensor 112 may be implemented as an FSR sensor as a planar pressure sensor, but is not limited thereto, and may be implemented as a capacitive or resistive pressure sensor.

While the shelf 111 rotates, the grid generating projector 121 irradiates the mixed light of the laser to the apple to generate a plurality of two-dimensional curvature images, and the image acquisition unit 122 captures the plurality of two-dimensional curvature images do.

The image acquisition unit 122 may be implemented as a mobile phone CMOS camera or a 1.67um class external CMOS camera for miniaturization.

The spectrometer of the light spectrum measurement unit 130 may analyze near-infrared light or far-infrared light. Specifically, the spectrometer may be implemented as a near infrared light spectrometer (NIR spectrometer) for analyzing the 900 to 1700 nm band or a far infrared light spectrometer (FIR spectrometer) for analyzing the 1350 nm to 2490 nm band.

The light spectrum information (L), weight and volume information (W), which is the information of the food, is transmitted to the analysis unit 140. The analysis unit 140 may be implemented as a Raspberry Pi platform or a mobile phone or an application mounted on the mobile phone.

Referring to Figure 4, the food nutrient intake analysis method according to another embodiment of the present invention may include an input step (S200), a measurement step (S300) and an analysis step (S400).

In the input step (S200), the food nutrient intake analysis device 100 receives the type of food. Specifically, the material composition ratio of the food is calculated by inputting the food type and using a pre-stored standard recipe DB.

In the measurement step (S300), the food nutrient intake analysis device 100 measures the weight data, volume data, and light spectrum information of the food.

Specifically, the weight measuring unit 110 measures the weight data of the food. The volume measurement unit 120 captures a two-dimensional curvature image from food rotated by the weight measurement unit 110. The optical spectrum measuring unit 130 acquires optical spectrum information about a specific point of food that is rotated by the weight measuring unit 110.

In the analysis step (S400), the food nutrient intake analysis apparatus 100 calculates the weight information and the volume information of the food using the weight data and the volume data, and calculates the weight information, the volume information, and the light spectrum information. Analysis of the nutrient composition ratio and content of the food.

Referring to FIG. 5, the analysis step (S400) may include a component analysis step (S410), a material analysis step (S420), an additional component analysis step (S430), and a content analysis step (S440).

In the component analysis step (S410 ), the food nutrient intake analysis apparatus 100 calculates the nutrient component ratio of the food from the prediction model using the light spectrum information of the food. The prediction model is a neural network formed by learning the light spectrum of a complex food.

In the material analysis step (S420 ), the food nutrient intake analysis device 100 calculates the material composition ratio of the food from the standard recipe DB using the food type.

In the additional component analysis step (S430), the food nutrient intake analysis apparatus 100 calculates the nutrient component ratio for each material from the material composition ratio using the optical spectrum DB for each material and the optical spectrum DB for each nutrient.

In the content analysis step (S440), the food nutrient intake analysis device 100 calculates the nutrient content of the food by using the weight information of the food, volume information, the nutrient component ratio, and the nutrient component ratio of each material.

Specifically, the analysis device 100 calculates weight information and volume information, respectively, using the food weight data and volume data, and uses the nutrient component ratio and the nutrient component ratio for each material based on the calculated weight information and volume information. To perform quantitative analysis.

The analysis device 100 calculates the content of water in the food using the weight information and the volume information. The analysis device 100 calculates each nutrient content using the water content, the nutrient component ratio, and the nutrient component ratio for each material.

According to an embodiment, after the content analysis step (S440), an output step of outputting the analysis result may be further included. In the output step, all the results calculated for each step can be output.

Specifically, the analysis device 100 may output the material according to the type of food and its composition ratio, the nutrient composition ratio for each material, the nutrient composition ratio and calories of the food. However, the present invention is not limited thereto, and the analysis device 100 receives the user's information such as age and weight, calculates the recommended daily nutrient intake based on the information, and compares the recommended daily nutrient intake with the analysis result of the analysis step (S400). Whether the level is satisfied or not can be printed together.

As described above, the method for analyzing food nutrient intake according to another embodiment of the present invention is not based on an individual's perception, but is analyzed by using measured food information (weight, volume, light spectrum), thereby enabling more accurate analysis. .

The invention has been described above with the aim of method steps indicative of the performance of certain functions and their relationships. The boundaries and order of these functional components and method steps have been arbitrarily defined herein for convenience of explanation.

Alternative boundaries and sequences can be defined as long as the specific functions and relationships are properly performed. Any such alternative boundaries and sequences are therefore within the scope and spirit of the claimed invention.

Additionally, the boundaries of these functional components are arbitrarily defined for convenience of explanation. Alternative boundaries can be defined as long as certain important functions are properly performed. Likewise, flow chart blocks may also have been arbitrarily defined herein to indicate any important functionality.

For extended use, the flow chart block boundaries and order may have been defined and still perform some important function. Alternative definitions of both functional components and flowchart blocks and sequences are therefore within the scope and spirit of the claimed invention.

The invention may also be described, at least in part, in terms of one or more embodiments. The embodiments of the present invention are used herein to represent the present invention, its aspects, its features, its concepts, and/or its examples. A physical embodiment of an apparatus, article of manufacture, machine, and/or process embodying the present invention includes one or more aspects, features, concepts, examples, etc., described with reference to one or more embodiments described herein. It can contain.

Moreover, in the whole drawing, embodiments may incorporate the same or similarly named functions, steps, modules, etc. that may use the same or different reference numbers, and as such, the functions, The steps, modules, etc. may be the same or similar functions, steps, modules, etc., or others.

As described above, in the present invention, specific matters such as specific components and the like have been described by limited embodiments and drawings, but they are provided only to help a more comprehensive understanding of the present invention, and the present invention is not limited to the above embodiments , Anyone having ordinary knowledge in the field to which the present invention pertains can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention is limited to the described embodiments, and should not be determined, and all claims that are equivalent or equivalent to the scope of the invention as well as the claims below will be said to belong to the scope of the spirit of the invention. .

[Description of codes]

100: food nutrient intake analysis device

110: weight measuring unit

111: shelf

112: weight sensor

120: volume measurement unit

121: grid generation projector

122: image acquisition unit

130: optical spectrum measurement unit

140: analysis unit

141: nutrient analysis department

142: material analysis unit

143: additional analysis unit

144: content analysis unit

Claims

Weighing unit for obtaining the weight data of the food provided with a shelf and a weight sensor that can be rotated while placing the food;

A volume measuring unit for acquiring volume data of the food from a two-dimensional curvature image of the food rotating by the weight measuring unit;

An optical spectrum measuring unit that acquires light spectrum information on a specific point of food rotated by the weight measuring unit; And

Includes an analysis unit that calculates the weight information and the volume information of the food using the weight data and the volume data, respectively, and analyzes the nutrient component ratio and the nutrient content of the food using the weight information, volume information, and light spectrum information. Food nutrient intake analysis device.
According to claim 1,

The weight sensor is a food nutrient intake analysis device, characterized in that the FSR (Force Sensitive Resistor) sensor.
According to claim 1,

The volume measurement unit,

A grid-generating projector for generating a plurality of two-dimensional curvature images by projecting light onto food rotating by the weight measuring unit and

It includes an image acquisition unit for capturing the plurality of two-dimensional curvature image

The analysis unit

Food nutrient intake analysis device, characterized in that for calculating the volume information of the food by converting the plurality of two-dimensional curvature image.
According to claim 3,

The optical spectrum measurement unit

Food nutrient intake analysis device, characterized in that for obtaining the light spectrum information using the laser mixed light of the grid generating projector as a light source.
According to claim 1,

The analysis unit

A nutrient analyzer for calculating the nutrient component ratio from the light spectrum information using a pre-stored prediction model;

A material analysis unit that receives the type of food and drinks and calculates a material composition ratio of the food and drink using a pre-stored standard recipe DB;

An additional analysis unit that calculates a nutrient component ratio for each material from the material composition ratio using a pre-stored optical spectrum DB for each material and a light spectrum DB for each nutrient; And

And a content analysis unit that calculates a nutrient content of the food by using the weight information, the volume information, the nutrient component ratio, and the nutrient component ratio for each material.
The method of claim 5,

The prediction model is a food nutrient intake analysis device, characterized in that the neural network generated by learning the light spectrum information of the composite food.
In the food nutrient intake analysis method using the food nutrient intake analysis device,

An input step of receiving a type of food;

A measurement step of measuring the weight data, volume data, and light spectrum information of the food; And

And an analysis step of calculating weight information and volume information of the food using the weight data and volume data, and analyzing the nutrient component ratio and content of the food using the weight information, the volume information, and the light spectrum information. How to analyze food nutrient intake.
The method of claim 7,

The measuring step,

A weight measuring step in which the weight measuring unit measures the weight data using an FSR sensor;

A volume measurement step of capturing a plurality of two-dimensional curvature images from food rotating by the volume measurement unit by the volume measurement unit; And

The optical spectrum measuring unit comprises an optical spectrum measuring step of obtaining the optical spectrum information for a specific point of the food and drink

The analysis step,

Food nutrient intake analysis method, characterized in that for calculating the volume information by converting the plurality of two-dimensional curvature image.
The method of claim 7,

The analysis step,

A component analysis step of calculating a nutrient component ratio of the food from a prediction model using the light spectrum information; And

And a content analysis step of calculating the content of each nutrient in the food by using the weight information, the volume information, and the nutrient component ratio.
The method of claim 9,

The analysis step,

Before the content analysis step

A material analysis step of calculating a material composition ratio of the food from a standard recipe DB using the food type; And

Further comprising an additional component analysis step of calculating the nutrient component ratio for each material from the material composition ratio using the light spectrum DB for each material and the light spectrum DB for each nutrient,

The content analysis step,

Method for analyzing food nutrient intake, characterized in that the nutrient content of the food is calculated using the weight information, the volume information, the nutrient component ratio, and the nutrient component ratio for each material.
The method of claim 10,

The prediction model is a food nutrient intake analysis method, characterized in that the neural network generated by learning the light spectrum information of the composite food.