WO2023092647A1 - 炒饭食味特性的快速定量评价方法 - Google Patents

炒饭食味特性的快速定量评价方法 Download PDF

Info

Publication number
WO2023092647A1
WO2023092647A1 PCT/CN2021/135904 CN2021135904W WO2023092647A1 WO 2023092647 A1 WO2023092647 A1 WO 2023092647A1 CN 2021135904 W CN2021135904 W CN 2021135904W WO 2023092647 A1 WO2023092647 A1 WO 2023092647A1
Authority
WO
WIPO (PCT)
Prior art keywords
seasoning
fried rice
rice
fried
particle
Prior art date
Application number
PCT/CN2021/135904
Other languages
English (en)
French (fr)
Inventor
石吉勇
刘梦雪
邹小波
黄晓玮
李志华
申婷婷
李信
崔鹏景
肖建波
张新爱
张迪
周晨光
张钖
Original Assignee
江苏大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 江苏大学 filed Critical 江苏大学
Priority to US17/907,963 priority Critical patent/US20230187030A1/en
Priority to JP2022514241A priority patent/JP7498982B2/ja
Publication of WO2023092647A1 publication Critical patent/WO2023092647A1/zh

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02—Food
    • G01N33/10—Starch-containing substances, e.g. dough
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F2101/00—Mixing characterised by the nature of the mixed materials or by the application field
    • B01F2101/06—Mixing of food ingredients

Definitions

  • the invention belongs to the technical field of food processing, and in particular relates to a fast and nondestructive quantitative method for the taste characteristics of fried rice.
  • Fried rice is a kind of delicacy made of rice, side dishes and seasonings. It is nutritious and delicious, with various styles and convenient preparation.
  • a common fried rice cooking process involves frying rice with a specific degree of doneness with different kinds of side dishes, and adding different flavors of seasonings for seasoning.
  • High-quality fried rice and special fried rice have higher requirements in terms of color, aroma, and shape. Among them, taste has the greatest impact on consumers' feelings when tasting fried rice, and is the key to determining the grade of fried rice and giving fried rice its characteristics.
  • fried rice not only has complex ingredients, but also has small particle size and various shapes. Therefore, how to quantitatively detect the eating characteristics of fried rice is the key to judge and make high-quality fried rice.
  • the existing evaluation methods of eating characteristics mainly include artificial sensory method, physical and chemical analysis method and non-destructive testing method.
  • the artificial sensory method mainly uses human senses to perceive product characteristics or properties, and can realize the evaluation of eating characteristics.
  • the invention patent CN112986506A discloses a method for evaluating the eating quality of rice by sensory.
  • the artificial sensory method has the disadvantages of strong subjectivity and low detection accuracy, and it is difficult to achieve an objective and accurate evaluation of the eating characteristics of fried rice.
  • Physicochemical analysis is to carry out qualitative and quantitative analysis to food taste and flavor related components by means of analysis such as physics and chemistry, so as to judge the eating characteristics of food (such as patent CN113138257A).
  • the non-destructive testing method can establish a qualitative and quantitative detection model of food flavor components by using the correlation between photoelectric and other non-destructive testing signals and food flavor components without destroying the original state of the sample.
  • Non-destructive and rapid detection of eating characteristics such as the evaluation method of eating characteristics based on spectroscopic method (CN111007040A) and electrochemical method (CN108037256B).
  • the existing non-destructive testing methods are mainly used for the detection of the taste characteristic components of samples, and it is difficult to accurately analyze the taste ability and distribution of seasoning components in complex foods such as fried rice.
  • the conventional non-destructive testing model of food components The corresponding modeling process requires a large number of physical and chemical experiments to provide modeling reference values, which is not conducive to the rapid construction and efficient maintenance of the model.
  • the present invention based on the characteristic that the hyperspectral image signal is sensitive to the seasoning content of fried rice, quickly senses the taste of the rice grains and side dish particles in the finished fried rice in a non-destructive way, and proposes a fried rice taste Fast and nondestructive quantification of properties.
  • the object of the present invention is to provide a fast and non-destructive quantitative method for the taste characteristics of fried rice, which is characterized in that it includes three steps: building a quantitative model of fried rice seasoning, building a model for identifying the types of raw materials for fried rice, and quantitatively characterizing the taste characteristics of fried rice:
  • Step 1 described fried rice seasoning quantitative model construction comprises the following processes:
  • Process 1 use m kinds of seasoning liquids A_1, A_2,..., A_(m-1), A_m as seasonings for cooking fried rice, and use n kinds of side dishes B_1, B_2,..., B_(n-1) , B_n, and rice D are used as ingredients for cooking fried rice;
  • the standard concentration of the i-th seasoning liquid A_i is C_A_i
  • the average surface area of a single particle of the j-th side dish B_j is S_B_j
  • the average surface area of a single particle of rice D is S_D
  • C_A_i, S_B_j, and S_D are all positive numbers
  • m and n are both integers greater than 0, i ⁇ [1,m], j ⁇ [1,n];
  • Process 3 according to the order of seasoning liquid concentration from low to high, cook fried rice with e portions of fried rice seasoning liquid combination and e portion of fried rice ingredient combination in a way of 1 type of fried rice seasoning liquid combination and 1 type of fried rice ingredient combination to obtain e portion of finished product Fried rice, and the kth finished fried rice includes cooked fried rice components B_j&A_0&C_k of side dish B_j and m kinds of seasoning solutions A_i with concentrations of C_k_A_i, and fried rice cooked with rice D and m kinds of seasoning solutions A_i with concentrations of C_k_A_i Component D&A_0&C_k;
  • the extraction process of G1_A_i described in step 1 is: taking each fried rice ingredient particle as a region of interest, and using the average spectrum of each region of interest as the spectral data of the sample to obtain the full-band spectral information of fried rice; Using the principal component analysis algorithm (PCA) to extract the spectral feature variable, the feature variable G1_A_i of the i-th seasoning A_i in the fried rice after cooking is obtained;
  • PCA principal component analysis algorithm
  • Step 2 the construction of the identification model of the fried rice raw material type includes the following process:
  • Process 1 take i ⁇ [1, m], j ⁇ [1, n], take f2 fried rice ingredients B_j&A_0&C_e, D&A_0&C_e from the e-th fried rice cooked in step 1 and process 3, and divide them randomly according to the ratio of d:1
  • the calibration set and prediction set are used to collect hyperspectral images and extract the spectral characteristic variable G2_B&D of the raw material type. According to the spectral characteristic variable G2_B&D, the spectral characteristic value g2_B_j_cal corresponding to the side dish B_j in the calibration set and the spectral characteristic corresponding to rice D are respectively extracted.
  • the extraction method of G2_B&D described in step 2 take each fried rice component B_j&A_0&C_e, D&A_0&C_e particle as a region of interest, and use the average spectrum of each region of interest as the spectral data of the sample to obtain the full band of the fried rice sample Spectral information; use the continuous projection algorithm (SPA) to screen and obtain the reflection intensities corresponding to t characteristic wavelengths ⁇ that characterize the raw material species as the characteristic variable G2_B&D.
  • SPA continuous projection algorithm
  • g2_B_j_cal described in step 2 is a spectral eigenvalue matrix of h1 ⁇ t formed by the reflection intensity of h1 particles B_j&A_0&C_e in the calibration set at the characteristic wavelength ⁇ (the number of characteristic wavelengths is t);
  • the g2_D_cal is the h1 ⁇ t spectral eigenvalue matrix formed by the reflection intensity of h1 rice grains D&A_0&C_e in the calibration set at the characteristic wavelength ⁇ (the number of characteristic wavelengths is t).
  • g2_B_j_pre and g2_D_pre are the corresponding fried rice sample particles in the prediction set The h1*1/d ⁇ t spectral eigenvalue matrix formed by the reflection intensity at the characteristic wavelength ⁇ .
  • chemometric method described in step 2 is support vector machine (SVM).
  • Step 3 the quantitative characterization of the eating characteristics of the fried rice includes the following process:
  • Process 1 using m kinds of seasoning liquids A_1, A_2, ..., A_(m-1), A_m described in step 1 as seasonings for cooking fried rice, and n kinds of side dishes B_1, B_j, B_2, ..., B_(n-1), B_n, and rice D are used as ingredients for cooking fried rice;
  • the concentration of the i-th seasoning liquid A_i is C'_A_i
  • the surface area of a single particle of the j-th side dish B_j is S'_B_j
  • the surface area of a single grain of rice D is S'_D, where C'_A_i, S'_B_j, and S'_D are all positive numbers;
  • Process 2 Cook m types of seasonings A_i with volumes V'_A_i, n types of side dishes B_j with particle numbers N'_B_j, and rice D with particle numbers N'_D according to the cooking process in step 1 and process 3.
  • Fried rice the cooked fried rice is broken up and spread into a state where the particles are separated from each other to obtain the fried rice particles; collect hyperspectral images according to the method in step one process four, and obtain the spectral characteristic value g1'_A_i_p of seasoning A_i corresponding to the pth particle in fried rice according to the characteristic variable G1_A_i of seasoning A_i; according to step two in process one Spectral characteristic variable G2_B&D of the raw material type, to obtain the spectral characteristic value g2'_B&D_p corresponding to the pth particle in the fried rice; where p ⁇ [1, N'];
  • variable R_B_j is set to record the number of particles of the side dish B_j successfully identified in this step
  • variable R_D is used to record the number of particles of the rice D successfully identified in this step
  • initial values of R_B_j and R_D are set to 0; p The value of is sequentially taken as 1, 2, ..., N'-1, N';
  • Process 4 Calculate the relative taste characteristic evaluation index, absolute taste characteristic evaluation index, and uniform taste characteristic evaluation index of fried rice eating characteristics. The specific calculation process is as follows:
  • the relative taste evaluation index of the i-th seasoning A_i on the j-th side dish B_j It is used to indicate the absorption ability of side dish B_j to seasoning A_i;
  • the relative taste evaluation index of the i-th seasoning A_i on the rice D Used to indicate the absorption capacity of rice D to seasoning A_i;
  • the absolute taste evaluation index of the i-th seasoning A_i on the j-th side dish B_j It is used to represent the total absorption of seasoning A_i by single particle side dish B_j;
  • Absolute taste evaluation index of the i-th seasoning A_i on rice D Used to represent the total amount of seasoning A_i absorbed by single-grain rice D;
  • Evaluation index of flavor uniformity of the i-th seasoning A_i on the j-th side dish B_j Indicates the degree of difference in the content of seasoning A_i among different particles of side dish B_j;
  • the evaluation index of the taste uniformity of the i-th seasoning A_i on the rice D Indicates the degree of difference in the content of seasoning A_i among different grains of rice D;
  • the evaluation index of the taste uniformity of the i-th seasoning A_i in different types of fried rice ingredients Indicates the degree of difference in the average content of seasoning A_i among different food types, where
  • the taste characteristic evaluation index obtained in process four is compared with the standard index of the standard sample, so as to realize the evaluation of the taste quality of fried rice.
  • the standard sample refers to the high-quality fried rice with complete color, aroma and taste identified by sensory evaluation and physical and chemical analysis methods; at the same time, the standard sample can be adjusted accordingly according to the taste of different places, and subdivided into different local standard samples to suit local taste habits.
  • the present invention utilizes the sensitivity of spectral signals to the change of seasoning liquid content to establish a seasoning quantitative model, and according to the characteristic that the total amount of seasoning in the finished fried rice is equal to the total amount of seasoning added in the frying process of fried rice, the quantitative model of seasoning is constructed
  • the analytical equation of key parameters realizes the rapid construction of the seasoning quantitative model by solving the equation.
  • the present invention obtains the spectral characteristics of fried rice particles one by one, combines the constructed seasoning quantitative model and fried rice raw material type identification model to quickly detect the content of different types of seasoning on single grain fried rice raw materials, and accordingly proposes a quantitative evaluation of fried rice eating characteristics
  • the index and its calculation method provide a new technical means for studying and optimizing the taste characteristics of fried rice.
  • a fast and non-destructive quantitative method for the taste characteristics of fried rice characterized in that it comprises three steps: construction of a quantitative model for fried rice seasoning, construction of a recognition model for types of raw materials for fried rice, and quantitative characterization of the taste characteristics of fried rice:
  • Step 1 described fried rice seasoning quantitative model construction comprises the following processes:
  • Step 2 the construction of the identification model of the fried rice raw material type includes the following process:
  • Process 1 take 40 fried rice ingredients B_1&A_0&C_3, B_2&A_0&C_3, D&A_0&C_3 from the third fried rice cooked in step 1 and process 3, and randomly divide them into a correction set and a prediction set according to the ratio of 3:1, so that the correction set contains 30 sausages B_1&A_0&C_3, 30 carrots B_2&A_0&C_3 and 30 grains of rice D&A_0&C_3, the prediction set contains 10 sausages B_1&A_0&C_3, 10 carrots B_2&A_0&C_3 and 10 grains of rice D&A_0&C_3, and hyperspectral image acquisition is performed on them, and each fried rice component B_1&A_0&C_3, B_2 &A_0&C_3, D&A_0&C_3 particles As a region of interest, the average spectrum of each region of interest is used as the spectral data of the sample to obtain the full-band spectral information of
  • Step 3 the quantitative characterization of the eating characteristics of the fried rice includes the following process:
  • Seasoning liquid A_1 and curry seasoning liquid A_2 are used as seasonings for cooking fried rice, and sausage B_1, carrot B_2, and rice D are used as ingredients for cooking fried rice;
  • the concentration of soy sauce seasoning liquid A_1 is 50%, and the concentration of curry seasoning liquid A_2 It is 40%; use the color sorter to select sausage B_1, carrot B_2 and rice D with a single particle surface area of 0.6cm2 with a single particle surface area of 5cm2 ;
  • the method in process 4 collects hyperspectral images, and according to the characteristic variable G1_A_1 of soy sauce seasoning A_1, the spectral characteristic value g1'_A_1_p of soy sauce seasoning A_1 corresponding to the pth particle in fried rice is obtained, and according to the characteristic variable of curry seasoning A_2 G1_A_2, to obtain the spectral characteristic value g1'_A_2_p of curry
  • Process 3 set the variable R_B_1 to record the number of successfully recognized particles of sausage B_1 in this step, set the variable R_B_2 to record the number of successfully recognized particles of carrot B_2 in this step, and set the variable R_D to record the successful recognition of rice D in this step
  • the number of particles, and the initial value of R_B_1, R_B_2, R_D is set to 0; the value of p is 1, 2, ..., 919, 920 in turn;
  • the relative content of the corresponding seasoning A_i on the fried rice particles is the concentration of the corresponding seasoning A_i on the fried rice particles (i.e. the amount of seasoning A_i contained per unit surface area), and the absolute content is the total amount of the corresponding seasoning A_i on the fried rice particles;
  • Process 4 Calculate the relative taste characteristic evaluation index, absolute taste characteristic evaluation index, and uniform taste characteristic evaluation index of fried rice eating characteristics. The specific calculation process is as follows:
  • Relative taste evaluation index of soy sauce seasoning A_1 on carrot B_2 It is used to indicate the absorption capacity of carrot B_2 to soy sauce seasoning A_1;
  • Relative taste evaluation index of soy sauce seasoning A_1 on rice D It is used to indicate the absorption capacity of rice D to soy sauce seasoning A_1;
  • Relative taste evaluation index of curry seasoning A_2 on rice D It is used to indicate the absorption capacity of rice D to curry seasoning A_2;
  • Absolute taste evaluation index of soy sauce seasoning A_1 on sausage B_1 It is used to represent the total amount of absorption of sausage B_1 particles to soy sauce seasoning A_1;
  • Absolute taste evaluation index of curry seasoning A_2 on sausage B_1 Used to represent the total amount of curry seasoning A2 absorbed by sausage B_1 particles;
  • Absolute Taste Evaluation Index of Soy Sauce Seasoning A_1 on Carrot B_2 It is used to represent the total amount of absorption of carrot B_2 particles to soy sauce seasoning A_1;
  • Absolute taste evaluation index of curry seasoning A_2 on carrot B_2 It is used to represent the total amount of curry seasoning A2 absorbed by carrot B_2 particles;
  • Absolute taste evaluation index of soy sauce seasoning A_1 on rice D It is used to represent the total absorption of rice D particles to soy sauce seasoning A_1;
  • Absolute taste evaluation index of curry seasoning A_2 on rice D Used to represent the total amount of curry seasoning A_2 absorbed by rice D particles;
  • Evaluation index of flavor uniformity of soy sauce seasoning A_1 on sausage B_1 Indicates the degree of difference in the content of soy sauce seasoning A_1 among different particles of sausage B_1;
  • Evaluation index of taste uniformity of curry seasoning A_2 on sausage B_1 Indicates the degree of difference in the content of curry seasoning A_2 among different particles of sausage B_1;
  • Evaluation index of flavor uniformity of soy sauce seasoning A_1 on carrot B_2 Indicates the degree of difference in the content of soy sauce seasoning A_1 among different particles of carrot B_2;
  • Evaluation index of taste uniformity of curry seasoning A_2 on carrot B_2 Indicates the degree of difference in the content of curry seasoning A_2 among different particles of carrot B_2;
  • Evaluation index of flavor uniformity of soy sauce seasoning A_1 on rice D Indicates the degree of difference in the content of soy sauce seasoning A_1 among different grains of rice D;
  • Evaluation index of taste uniformity of curry seasoning A_2 on rice D Indicates the degree of difference in the content of curry seasoning A_2 among different grains of rice D;
  • Evaluation index of flavor uniformity of soy sauce seasoning A_1 in different types of fried rice ingredients Indicates the degree of difference in the average content of soy sauce seasoning A_1 among different types of ingredients, where
  • Evaluation index of taste uniformity of curry seasoning A_2 in different types of fried rice ingredients Indicates the degree of difference in the average content of curry seasoning A_2 among different types of ingredients, where
  • Process 5 In the early stage, according to the standard sample, sensory evaluation is used to establish the evaluation standard index of fried rice taste, and the evaluation index of taste characteristics obtained in process 4 is compared with the standard index. The closer the evaluation index is to the standard index, the better the taste quality of fried rice is. Within ⁇ 10%, it is considered to be of good quality.
  • the standard sample refers to the high-quality fried rice with complete color, aroma and taste identified by sensory evaluation and physical and chemical analysis methods.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Cereal-Derived Products (AREA)
  • Image Analysis (AREA)

Abstract

本发明属于食品加工技术领域，具体涉及一种炒饭食味特性的快速无损定量方法；其包含炒饭调味料定量模型构建、炒饭原料种类识别模型构建、炒饭食味特性定量表征三个步骤；利用光谱信号对调料液含量变化的敏感性建立了调味料定量模型，根据成品炒饭中调味料总量与炒饭炒制过程中加入的调味料总量相等的特点，构建了调味料定量模型关键参数的解析方程，通过方程求解的方式实现了调味料定量模型的快速构建。同时，本发明通过逐一获取炒饭颗粒的光谱特征，结合构建的调味料定量模型及炒饭原料种类识别模型快速检测单颗粒炒饭原料上不同种类调味料的含量，提出了炒饭食味特性的定量评价指标及其计算方法，为研究、优化炒饭食味特性提供新的技术手段。

Description

炒饭食味特性的快速定量评价方法 技术领域
本发明属于食品加工技术领域，具体涉及一种炒饭食味特性的快速无损定量方法。
背景技术
炒饭是一类由米饭、配菜、调味料烹炒而成的美食，具有营养美味、款式多样、制作方便等特点。常见的炒饭烹制过程涉及将特定熟度的米饭与不同种类的配菜搭配炒制，同时添加不同风味的调料进行调味。高品质炒饭、特色炒饭在色香味形方面都有较高的要求，其中味道对消费者品尝炒饭时的感受影响最大，是决定炒饭品级、赋予炒饭特色的关键。然而，炒饭不仅成品成分复杂，而且颗粒度小、形态多样。因此，如何定量检测炒饭的食味特性是评判、制作高品质炒饭的关键。
现有的食味特性评价方法主要有人工感官法、理化分析法和无损检测法。人工感官法主要利用人的感官感知产品特性或性质，可实现对食味特性的评价。人工感官法评价食味特性方面，发明专利CN112986506A公开了一种利用感官评价稻米食味品质的方法。然而，人工感官法具有主观性强、检测精度低等缺点，难以实现对炒饭食味特性客观、准确评价。理化分析法是通过物理、化学等分析手段对食品滋味、风味相关的成分进行定性、定量分析，据此可判断食品的食味特性(如专利CN113138257A)。然而，理化分析法检测成本高、检测过程耗时、对操作人员的要求高，难以实现炒饭食味特性的快速、在线检测。无损检测法可在不破坏样品原有状态的前提下，利用光电等无损检测信号与食品食味特征组分之间的相关性，建立食品风味组分的定性、定量检测模型，据此可实现食品食味特征的无损、快速检测，如基于光谱法(CN111007040A)和电化学法(CN108037256B)的食味特性评价方法等。然而，现有的无损检测方法主要用于样品的食味特性成分含量检测，难以精确分析炒饭等复杂食品中不同食材的入味能力、调味组分的分布情况等；同时，常规食味组分无损检测模型对应的建模过程需要大量的理化实验提供建模参考值，不利于模型的快速构建及高效维护。
发明内容
为了克服现有技术方案的不足，本发明依据高光谱图像信号对炒饭调味料含量敏感的特性，通过无损的方式快速感知炒饭成品中米粒与配菜颗粒的调料入味情况，提出了一种炒饭食味特性的快速无损定量方法。
本发明的目的在于提供一种炒饭食味特性的快速无损定量方法，其特征在于包含炒饭调味料定量模型构建、炒饭原料种类识别模型构建、炒饭食味特性定量表征三个步骤：
步骤一，所述炒饭调味料定量模型构建包含以下过程：
过程一，将m种调料液A_1、A_2、……、A_(m-1)、A_m用作烹制炒饭的调味料，将n种配菜B_1、B_2、……、B_(n-1)、B_n，以及米饭D用作烹制炒饭的食材；第i种调料液A_i的标准浓度为C_A_i，第j种配菜B_j的单颗粒平均表面积为S_B_j，米饭D的单颗粒平均表面积为S_D，其中C_A_i、S_B_j、S_D均为正数，m和n均为大于0的整数，i∈[1，m]、j∈[1，n]；
过程二，分别取e份炒饭食材组合，每份炒饭食材组合包含N_B_j颗第j种配菜B_j以及N_D粒米饭D；分别取e份炒饭调料液组合，每份炒饭调料液组合包含体积为V_A_i ml第i种调料液A_i，且第k份炒饭调料液组合中A_i的浓度为C_k_A_i＝k*(C_A_i)/e，其中e为大于2的整数，k∈[1，e]，N_B_j、N_D均为正整数，V_A_i为正数；
过程三，按照调料液浓度由低到高的顺序，将e份炒饭调料液组合、e份炒饭食材组合以1种炒饭调料液组合搭配1种炒饭食材组合的方式烹制炒饭，得到e份成品炒饭，且第k份成品炒饭包含配菜B_j与m种浓度为C_k_A_i的调料液A_i经烹制后的炒饭成分B_j&A_0&C_k、以及米饭D与m种浓度为C_k_A_i的调料液A_i经烹制后的炒饭成分D&A_0&C_k；
过程四，高光谱图像采集与光谱特征提取；
取i∈[1，m]、j∈[1，n]、k∈[1，e]，分别取f1颗炒饭成分B_j&A_0&C_k、D&A_0&C_k进行高光谱图像采集及光谱特征变量提取，得到烹制后炒饭中第i种调味料A_i的特征变量G1_A_i；并根据特征变量G1_A_i分别提取第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k；其中f1为正整数；过程五，根据第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k以及调味料A_i的总用量(V_A_i)*k*(C_A_i)/e；利用未知数h_A_i、b_A_i假设调味料A_i的定量模型为y＝F1_i(x)＝x*h_A_i+b_A_i，根据利用模型结合调味料A_i的特征值之和Sum_g1_A_i_k计算得到的第k份成品炒饭调味料A_i的总用量等于本步骤过程二中第k份炒饭炒制时加入的A_i总用量(V_A_i)*k*(C_A_i)/e，可建立用于求解未知数h_A_i、b_A_i的方程(Sum_g1_A_i_k)*(h_A_i)+b_A_i＝(V_A_i)*k*(C_A_i)/e；当k依次取值为1、2……、e-1、e时，利用得到的方程组可求解出未知数h_A_i、b_A_i，从而得到不含未知数的调味料A_i的定量模型为y＝F1_i(x)＝x*h_A_i+b_A_i，其中模型y为调味料A_i的浓度(单位表面积所含调味料的量)、x为调味料A_i的特征变量G1_A_i；
进一步地，步骤一中所述G1_A_i的提取过程为：以每个炒饭成分颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭的全波段光谱信息；利用主成分分析算法(PCA)进行光谱特征变量提取，得到烹制后炒饭中第i种调味料A_i的特征变量G1_A_i；
进一步地，步骤一中所述第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k的提取过程为：(1)提取f1颗添加m种浓度为C_k_A_i＝k*(C_A_i)/e调料液A_i的炒饭成分B_j&A_0&C_k对应的平均光谱，根据调味料A_i的特征变量G1_A_i得到B_j&A_0&C_k对应的平均特征值g1_B_j&A_i&C_k；提取f1颗添加m种浓度为C_k_A_i＝k*(C_A_i)/e调料液A_i的炒饭成分D&A_0&C_k对应的平均光谱，根据调味料A_i的特征变量G1_A_i得到D&A_0&C_k对应的平均特征值g1_D&A_i&C_k；(2)根据第k份炒饭中配菜B_j的颗粒数N_B_j及单颗平均表面积S_B_j、米饭D的颗粒数N_D及单颗平均表面积S_D，得到第k份成品炒饭中调味料A_i的特征值之和
Figure PCTCN2021135904-appb-000001
Figure PCTCN2021135904-appb-000002
步骤二，所述炒饭原料种类识别模型构建包含以下过程：
过程一，取i∈[1，m]，j∈[1，n]，分别从步骤一过程三烹制的第e份炒饭中取f2颗炒饭成分B_j&A_0&C_e、D&A_0&C_e按照d:1的比例随机分为校正集和预测集，并对其进行高光谱图像采集及原料种类光谱特征变量G2_B&D的提取，根据光谱特征变量G2_B&D分别提取校正集中配菜B_j对应的光谱特征值g2_B_j_cal和米饭D对应的光谱特征值g2_D_cal，以及预测集中配菜B_j对应的光谱特征值g2_B_j_pre和米饭D对应的光谱特征值g2_D_pre；其中d、f2为正整数；
过程二，利用光谱特征变量G2_B&D作为自变量X，以炒饭原料种类作为因变量Y(以参考值0代表米饭D，以参考值j代表配菜B_j)，结合化学计量学方法建立炒饭原料种类识别模型Y＝F2(X)；
进一步地，步骤二中所述G2_B&D的提取方法：将每个炒饭成分B_j&A_0&C_e、D&A_0&C_e颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭样品的全波段光谱信息；利用连续投影算法(SPA)筛选得到t个表征原料种类的特征波长λ对应的反射强度作为特征变量G2_B&D。
进一步地，步骤二中所述g2_B_j_cal为校正集中h1个颗粒B_j&A_0&C_e在特征波长λ(特征波长个数为t)下的反射强度构成的h1×t的光谱特征值矩阵；
所述g2_D_cal为校正集中h1个颗粒米饭D&A_0&C_e在特征波长λ(特征波长个数为t)下的反射强度构成的h1×t的光谱特征值矩阵，同理g2_B_j_pre和g2_D_pre为预测集中相应炒饭样品颗粒在特征波长λ下的反射强度构成的h1*1/d×t的光谱特征值矩阵。
进一步地，步骤二中所述化学计量学方法为支持向量机(SVM)。
步骤三，所述炒饭食味特性定量表征包含以下过程：
过程一，将步骤一中过程一所述的m种调料液A_1、A_2、……、A_(m-1)、A_m用作烹制炒饭的调味料，n种配菜B_1、B_j、B_2、……、B_(n-1)、B_n，以及米饭D用作烹制炒饭的食材；第i种调料液A_i的浓度为C’_A_i，第j种配菜B_j的单颗粒表面积为S’_B_j，米饭D的单颗粒表面积为S’_D，其中C’_A_i、S’_B_j、S’_D均为正数；
过程二，将体积分别为V’_A_i的m种调料A_i、颗粒数分别为N’_B_j的n种配菜B_j、以及颗粒数为N’_D的米饭D按照步骤一过程三中的烹饪工艺烹制炒饭；将烹制的炒饭打散、平铺成颗粒彼此分离的状态从而得到炒饭的
Figure PCTCN2021135904-appb-000003
个颗粒；按照步骤一过程四中的方法采集高光谱图像，根据调味料A_i的特征变量G1_A_i得到炒饭中第p个颗粒对应的调味料A_i的光谱特征值g1’_A_i_p；根据步骤二过程一中的原料种类光谱特征变量G2_B&D，得到炒饭中第p个颗粒对应的种类识别光谱特征值g2’_B&D_p；其中p∈[1，N’]；
过程三，设置变量R_B_j用于记录本步骤配菜B_j被成功识别的颗粒数，设置变量R_D用于记录本步骤米饭D被成功识别的颗粒数，且R_B_j、R_D的初始值设为0；p的取值依次取1、2、……、N’-1、N’；
首先，将第p个颗粒的种类识别光谱特征值g2’_B&D_p代入炒饭原料种类识别模型Y＝F2(X)，得到第p个颗粒所属的炒饭原料种类Yp；
其次，i的值依次取1、2、……、m-1、m；当Yp＝0时，表示第p个颗粒被识别为米饭D，则米饭被成功识别的颗粒数R_D增加1个；将第p个颗粒对应的光谱特征值g1’_A_i_p代入调味料A_i定量模型为y＝F1_i(x)，得到第R_D个米饭颗粒对应的调味料A_i的相对含量y1&D&R_D&A_i，并根据米饭D的单颗粒表面积为S’_D得到该颗粒对应的调味料A_i的绝对含量y2&D&R_D&A_i＝(y1&D&R_D&A_i)*S’_D；
当Yp＝j时，表示第p个颗粒被识别为配菜B_j，则配菜B_j被成功识别的颗粒数R_B_j增加1个；将第p个颗粒对应的光谱特征值g1’_A_i_p代入调味料A_i定量模型为y＝F1_i(x)，得到第R_B_j个配菜B_j颗粒对应的调味料A_i的相对含量y1&B_j&R_B_j&A_i，并根据配菜B_j的单颗粒表面积为S’_B_j得到该颗粒对应的调味料A_i的绝对含量y2&B_j&R_B_j&A_i＝(y1&B_j&R_B_j&A_i)*S’_B_j；
最后，得到本步骤炒饭中N’_B_j颗配菜B_j颗粒Uj上对应的调味料A_i的相对含量y1&B_j&Uj&A_i及绝对含量y2&B_j&Uj&A_i、N’_D颗粒米饭D颗粒VD上对应的调料A_i的相对含量y1&D&VD&A_i及绝对含量y2&D&VD&A_i，其中Uj∈[1，N’_B_j]、VD∈[1，N’_D]；
过程四，计算炒饭食味特性的相对入味特性评价指标、绝对入味特性评价指标、均度入味特性评价指标，具体计算过程为：
(1)调味料A_i在配菜B_j、米饭D上的相对入味评价指标的计算方法为：
第i种调味料A_i在第j种配菜B_j上的相对入味评价指标
Figure PCTCN2021135904-appb-000004
用于表示配菜B_j对调味料A_i的吸收能力；
第i种调味料A_i在米饭D上的相对入味评价指标
Figure PCTCN2021135904-appb-000005
Figure PCTCN2021135904-appb-000006
用于表示米饭D对调味料A_i的吸收能力；
(2)调味料A_i在配菜B_j、米饭D上的绝对入味评价指标的计算方法为：
第i种调味料A_i在第j种配菜B_j上的绝对入味评价指标
Figure PCTCN2021135904-appb-000007
用于表示单颗粒配菜B_j对调味料A_i的吸收总量；
第i种调味料A_i在米饭D上的绝对入味评价指标
Figure PCTCN2021135904-appb-000008
Figure PCTCN2021135904-appb-000009
用于表示单颗粒米饭D对调味料A_i的吸收总量；
(3)调味料A_i在配菜B_j、米饭D颗粒间的入味均匀度评价指标的计算方法为：
第i种调味料A_i在第j种配菜B_j上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000010
表示配菜B_j不同颗粒间调料A_i含量的差异程度；
第i种调味料A_i在米饭D上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000011
表示米饭D不同颗粒间调料A_i含量的差异程度；
第i种调味料A_i在炒饭不同种类食材的入味均匀度评价指标
Figure PCTCN2021135904-appb-000012
表示不同食材种类间调料A_i平均含量的差异程度，其中
Figure PCTCN2021135904-appb-000013
过程五，将过程四获得的入味特性评价指标与标准样品的标准指标相对比，即可实现炒饭的入味品质的评价。
所述标准样品是指结合感官评价和理化分析方法鉴定色、香、味俱全的高品质炒饭；同时针对标准样品可根据不同地方的口味进行相应调整，细分为不同的地方标准样品，以适合当地的口味习惯。
本发明的有益效果：
本发明利用光谱信号对调料液含量变化的敏感性建立了调味料定量模型，根据成品炒饭 中调味料总量与炒饭炒制过程中加入的调味料总量相等的特点，构建了调味料定量模型关键参数的解析方程，通过方程求解的方式实现了调味料定量模型的快速构建。同时，本发明通过逐一获取炒饭颗粒的光谱特征，结合构建的调味料定量模型及炒饭原料种类识别模型快速检测单颗粒炒饭原料上不同种类调味料的含量，据此提出了炒饭食味特性的定量评价指标及其计算方法，为研究、优化炒饭食味特性提供新的技术手段。
具体实施方式
下面结合一些具体实施例为本发明进一步详细说明，但本发明的保护范围不仅限于这些实施例。
实施例1：
一种炒饭食味特性的快速无损定量方法，其特征在于包含炒饭调味料定量模型构建、炒饭原料种类识别模型构建、炒饭食味特性定量表征三个步骤：
步骤一，所述炒饭调味料定量模型构建包含以下过程：
过程一，取m＝2、n＝2、C_A_1＝90％、C_A_2＝60％、S_B_1＝6cm 2、S_B_2＝6cm 2、S_D＝0.5cm 2，将酱油调料液A_1、咖喱调料液A_2用作烹制炒饭的调味料，将香肠B_1、胡萝卜B_2、米饭D用作烹制炒饭的食材；酱油调料液A_1的标准浓度为90％(体积百分浓度)，咖喱调料液A_2的标准浓度为60％(体积百分浓度)，香肠B_1的单颗粒平均表面积为6cm 2，胡萝卜B_2的单颗粒平均表面积为6cm 2，米饭D的单颗粒平均表面积为0.5cm 2；
过程二，取e＝3、V_A_1＝10ml、V_A_2＝10ml、N_B_1＝50、N_B_2＝50、N_D＝1800，取3份炒饭食材组合，每份炒饭食材组合包含50颗的香肠B_1、50颗胡萝卜B_2以及1800粒的米饭D；取3份调料液组合，第一份调料液组合包含10ml浓度为C_1_A_1＝30％的酱油调料液A_1和10ml浓度为C_1_A_2＝20％的咖喱调料液A_2，第二份调料液组合包含10ml浓度为C_2_A_1＝60％的酱油调料液A_1和10ml浓度为C_2_A_2＝40％的咖喱调料液A_2，第三份调料液组合包含10ml浓度为C_3_A_1＝90％的酱油调料液A_1和10ml浓度为C_3_A_2＝60％的咖喱调料液A_2；
过程三，按照调料液浓度从低到高的顺序，将3份炒饭食材组合、3份炒饭调料液组合以1种炒饭食材组合搭配1种炒饭调料液组合的方式烹制炒饭，得到3份成品炒饭，第1份炒饭包含香肠B_1、胡萝卜B_2、米饭D与浓度C_1_A_1＝30％的酱油调料液A_1和浓度C_1_A_2＝20％的咖喱调料液A_2经烹制后的炒饭成分B_1&A_0&C_1、B_2&A_0&C_1、D&A_0&C_1；第2份炒饭包含香肠B_1、胡萝卜B_2、米饭D与浓度C_2_A_1＝60％的酱油调料液A_1和浓度C_2_A_2＝40％的咖喱调料液A_2经烹制后的炒饭成分B_1&A_0&C_2、B_2&A_0&C_2、D&A_0&C_2；第3份炒饭包含香肠B_1、胡萝卜B_2、米饭D与浓度 C_3_A_1＝90％的酱油调料液A_1和浓度C_3_A_2＝60％的咖喱调料液A_2经烹制后的炒饭成分B_1&A_0&C_3、B_2&A_0&C_3、D&A_0&C_3；
过程四，高光谱图像采集与光谱特征提取；
分别取20颗炒饭成分B_1&A_0&C_1、B_2&A_0&C_1、D&A_0&C_1、B_1&A_0&C_2、B_2&A_0&C_2、D&A_0&C_2、B_1&A_0&C_3、B_2&A_0&C_3、D&A_0&C_3进行高光谱图像采集，以每个炒饭成分颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭的全波段光谱信息；利用主成分分析算法(PCA)进行光谱特征变量提取，得到烹制后炒饭中酱油调味料A_1的特征变量G1_A_1、咖喱调味料A_2的特征变量G1_A_2；并根据特征变量G1_A_1分别提取3份成品炒饭中酱油调味料A_1在浓度30％、60％、90％下对应的特征值之和Sum_g1_A_1_1、Sum_g1_A_1_2、Sum_g1_A_1_3，根据特征变量G1_A_2分别提取3份成品炒饭中咖喱调味料A_2在浓度20％、40％、60％下对应的特征值之和Sum_g1_A_2_1、Sum_g1_A_2_2、Sum_g1_A_2_3；
所述第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k(i＝1，2；k＝1，2，3)的提取过程为：(1)根据过程四获取的光谱数据，取20颗香肠颗粒B_1&A_0&C_k的平均光谱、20颗胡萝卜B_2&A_0&C_k的平均光谱、20粒米饭D&A_0&C_k的平均光谱，根据过程四得到的烹制后炒饭中调味料A_i的特征变量G1_A_i，分别提取炒饭成分B_1&A_0&C_k、B_2&A_0&C_k、D&A_0&C_k特征变量G1_A_i相应的特征值g1_B_1&A_i&C_k、g1_B_2&A_i&C_k、g1_D&A_i&C_k；(2)将n＝2，S_B_1＝6cm 2，S_B_2＝6cm 2，S_D＝0.5cm 2，N_B_1＝50，N_B_2＝50，N_D＝1800，代入
Figure PCTCN2021135904-appb-000014
得到Sum_g1_A_i_k＝300*g1_B_1&A_i&C_k+300*g1_B_2&A_i&C_k+900*g1_D&A_i&C_k；
过程五，根据第k份成品炒饭中酱油调味料A_1的特征值之和Sum_g1_A_1_k以及酱油调味料A_1的总用量(V_A_1)*k*(C_A_1)/e＝3*k ml；利用未知数h_A_1、b_A_1假设酱油调味料A_1的定量模型为y＝F1_1(x)＝x*h_A_1+b_A_1，根据利用模型结合酱油调味料味料A_1的特征值之和Sum_g1_A_1_k计算得到的第k份炒饭酱油调味料A_1的总用量等于本步骤过程二中第k份炒饭炒制时加入酱油调味料A_1的总用量，可建立用于求解未知数h_A_1、b_A_1的方程(Sum_g1_A_1_k)*(h_A_1)+b_A_1＝3*k；当k依次取值为1、2、3时，利用得到的方程组可求解出未知数h_A_1、b_A_1，从而得到不含未知数的酱油调味料A_1的定量模型为y＝F1_1(x)＝x*h_A_1+b_A_1，其中模型y为酱油调味料A_1的浓度(单位表面积所含调味料的量)、x为酱油调味料A_1的特征变量G1_A_1；
根据第k份成品炒饭中咖喱调味料A_2的特征值之和Sum_g1_A_2_k以及调味料A_2的总用量(V_A_2)*k*(C_A_2)/e＝2*k ml；利用未知数h_A_2、b_A_2假设咖喱调味料A_2的定量模型为y＝F1_2(x)＝x*h_A_2+b_A_2，根据利用模型结合咖喱调味料A_2的特征值之和Sum_g1_A_2_k计算得到的第k份炒饭咖喱调味料A_2的总用量等于本步骤过程二中第k份炒饭炒制时加入咖喱调味料A_2的总用量，可建立用于求解未知数h_A_2、b_A_2的方程(Sum_g1_A_2_k)*(h_A_2)+b_A_2＝2*k；当k依次取值为1、2、3时，利用得到的方程组可求解出未知数h_A_2、b_A_2，从而得到不含未知数的咖喱调味料A_2的定量模型为y＝F1_2(x)＝x*h_A_2+b_A_2，其中模型y为咖喱调味料A_2的浓度(单位表面积所含调味料的量)、x为咖喱调味料A_2的特征变量G1_A_2；
步骤二，所述炒饭原料种类识别模型构建包含以下过程：
过程一，分别从步骤一过程三烹制的第三份炒饭中取40颗炒饭成分B_1&A_0&C_3、B_2&A_0&C_3、D&A_0&C_3，按照3:1的比例随机分为校正集和预测集，使得校正集包含30颗香肠B_1&A_0&C_3、30颗胡萝卜B_2&A_0&C_3和30粒米饭D&A_0&C_3，预测集包含10颗香肠B_1&A_0&C_3、10颗胡萝卜B_2&A_0&C_3和10粒米饭D&A_0&C_3，并对其进行高光谱图像采集，将每个炒饭成分B_1&A_0&C_3、B_2&A_0&C_3、D&A_0&C_3颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭样品的全波段光谱信息；
利用连续投影算法(SPA)筛选得到t个表征原料种类的特征波长λ对应的反射强度作为特征变量G2_B&D，提取校正集中香肠颗粒B_1&A_0&C_3在特征波长λ(特征个数为t)下的反射强度作为30×t的光谱特征值矩阵g2_B_1_cal、胡萝卜颗粒B_2&A_0&C_3在特征波长λ(特征个数为t)下的反射强度作为30×t的光谱特征值矩阵g2_B_2_cal、米饭D&A_0&C_3在特征波长λ(特征个数为t)下的反射强度作为30×t的光谱特征值矩阵g2_D_cal，同理提取预测集中相应炒饭样品颗粒在特征波长λ下的反射强度，获得10×t的光谱特征值矩阵g2_B_1_pre、g2_B_2_pre、g2_D_pre；
过程二，利用光谱特征变量G2_B&D作为自变量X，以炒饭原料种类作为因变量Y(以参考值0代表米饭D，以参考值1代表香肠B_1，以参考值2代表胡萝卜B_2)，结合支持向量机(SVM)建立炒饭原料种类识别模型Y＝F2(X)；
步骤三，所述炒饭食味特性定量表征包含以下过程：
过程一，取C’_A_1＝50％、C’_A_2＝40％、S’_B_1＝5cm 2、S’_B_2＝5cm 2、S’_D＝0.6cm 2，将步骤一中过程一所述的酱油调料液A_1、咖喱调料液A_2用作烹制炒饭的调味料，将香肠B_1、胡萝卜B_2、米饭D用作烹制炒饭的食材；酱油调料液A_1的浓度为50％，咖喱调料液A_2 的浓度为40％；利用色选机选出单颗粒表面积为5cm 2的香肠B_1、胡萝卜B_2和单颗粒表面积为0.6cm 2的米饭D；
过程二，取V’_A_1＝V’_A_2＝15ml、N’_B_1＝N’_B_2＝10、N’_D＝900，一次性加入15ml酱油调料液A_1、15ml咖喱调料液A_2和10颗香肠B_1、10颗胡萝卜以及900粒米饭D按照步骤一过程三中的烹饪工艺烹制炒饭；将烹制的炒饭打散、平铺成颗粒彼此分离的状态从而得到炒饭的N’＝920个颗粒；按照步骤一过程四中的方法采集高光谱图像，根据酱油调味料A_1的特征变量G1_A_1，得到炒饭中第p个颗粒对应的酱油调味料A_1的光谱特征值g1’_A_1_p，根据咖喱调味料A_2的特征变量G1_A_2，得到咖喱调味料A_2的光谱特征值g1’_A_2_p；按照步骤二过程一中的原料种类光谱特征变量G2_B&D，得到炒饭中第p个颗粒对应的种类识别光谱特征值g2’_B&D_p；其中p∈[1，920]；
过程三，设置变量R_B_1用于记录本步骤香肠B_1被成功识别的颗粒数，设置变量R_B_2用于记录本步骤胡萝卜B_2被成功识别的颗粒数，设置变量R_D用于记录本步骤米饭D被成功识别的颗粒数，且R_B_1、R_B_2、R_D的初始值设为0；p的取值依次取1、2、……、919、920；
首先，将第p个颗粒的种类识别光谱特征值g2’_B&D_p代入炒饭原料种类识别模型Y＝F2(X)，得到第p个颗粒所属的炒饭原料种类Yp；
其次，当Yp＝0时，表示第p个颗粒被识别为米饭D，则米饭被成功识别的颗粒数R_D增加1个；将第p个颗粒对应的光谱特征值g1’_A_1_p代入酱油调味料A_1定量模型y＝F1_1(x)，得到第R_D个米饭颗粒对应的酱油调味料A_1的相对含量y1&D&R_D&A_1，将第p个颗粒对应的光谱特征值g1’_A_2_p代入咖喱调味料A_2定量模型y＝F1_2(x)，得到第R_D个米饭颗粒对应的咖喱调味料A_2的相对含量y1&D&R_D&A_2，并根据米饭D的单颗粒表面积为S’_D＝0.6cm 2得到该颗粒对应的酱油调味料A_1的绝对含量y2&D&R_D&A_1＝(y1&D&R_D&A_1)*0.6、咖喱调味料A_2的绝对含量y2&D&R_D&A_2＝(y1&D&R_D&A_2)*0.6；
当Yp＝1时，表示第p个颗粒被识别为香肠B_1，则香肠被成功识别的颗粒数R_B_1增加1个；将第p个颗粒对应的光谱特征值g1’_A_1_p代入酱油调味料A_1定量模型y＝F1_1(x)，得到第R_B_1个香肠颗粒对应的酱油调味料A_1的相对含量y1&B_1&R_B_1&A_1，将第p个颗粒对应的光谱特征值g1’_A_2_p代入咖喱调味料A_2定量模型y＝F1_2(x)，得到第R_B_1个香肠颗粒对应的咖喱调味料A_2的相对含量y1&B_1&R_B_1&A_2，并根据香肠B_1的单颗粒表面积为S’_B_1＝5cm 2得到该颗粒对应的酱油调味料A_1的绝对含量 y2&B_1&R_B_1&A_1＝(y1&B_1&R_B_1&A_1)*5、咖喱调味料A_2的绝对含量y2&B_1&R_B_1&A_2＝(y1&B_1&R_B_1&A_2)*5；
当Yp＝2时，表示第p个颗粒被识别为胡萝卜B_2，则胡萝卜被成功识别的颗粒数R_B_2增加1个；将第p个颗粒对应的光谱特征值g1’_A_1_p代入酱油调味料A_1定量模型y＝F1_1(x)，得到第R_B_2个胡萝卜颗粒对应的酱油调味料A_1的相对含量y1&B_2&R_B_2&A_1，将第p个颗粒对应的光谱特征值g1’_A_2_p代入咖喱调味料A_2定量模型y＝F1_2(x)，得到第R_B_2个胡萝卜颗粒对应的咖喱调味料A_2的相对含量y1&B_2&R_B_2&A_2，并根据胡萝卜B_2的单颗粒表面积为S’_B_2＝5cm 2得到该颗粒对应的酱油调味料A_1的绝对含量y2&B_2&R_B_2&A_1＝(y1&B_2&R_B_2&A_1)*5、咖喱调味料A_2的绝对含量y2&B_2&R_B_2&A_2＝(y1&B_2&R_B_2&A_2)*5；
最后，得到本步骤炒饭中香肠B_1颗粒U1上对应的酱油调味料A_1的相对含量y1&B_1&U1&A_1及绝对含量y2&B_1&U1&A_1、咖喱调味料A_2的相对含量y1&B_1&U1&A_2及绝对含量y2&B_1&U1&A_2，1胡萝卜B_2颗粒U2上对应的酱油调味料A_1的相对含量y1&B_2&U2&A_1及绝对含量y2&B_2&U2&A_1、咖喱调味料A_2的相对含量y1&B_2&U2&A_2及绝对含量y2&B_2&U2&A_2，米饭D颗粒VD上对应的酱油调味料A_1的相对含量y1&D&VD&A_1及绝对含量y2&D&VD&A_1、咖喱调味料A_2的相对含量y1&D&VD&A_2及绝对含量y2&D&VD&A_2，其中U1、U2∈[1，10]，VD∈[1，900]；
所述炒饭颗粒上对应调味料A_i的相对含量为炒饭颗粒上对应调味料A_i的浓度(即单位表面积所含有的调味料A_i的量)，绝对含量为炒饭颗粒上对应调味料A_i的总量；
过程四，计算炒饭食味特性的相对入味特性评价指标、绝对入味特性评价指标、均度入味特性评价指标，具体计算过程为：
(1)调味料A_i在香肠B_1、胡萝卜B_2、米饭D上的相对入味评价指标的计算方法为：
酱油调味料A_1在香肠B_1上的相对入味评价指标
Figure PCTCN2021135904-appb-000015
用于表示香肠B_1对酱油调味料A_1的吸收能力；
咖喱调味料A_2在香肠B_1上的相对入味评价指标
Figure PCTCN2021135904-appb-000016
用于表示香肠B_1对咖喱调味料A_2的吸收能力；
酱油调味料A_1在胡萝卜B_2上的相对入味评价指标
Figure PCTCN2021135904-appb-000017
用于表示胡萝卜B_2对酱油调味料A_1的吸收能力；
咖喱调味料A_2在胡萝卜B_2上的相对入味评价指标
Figure PCTCN2021135904-appb-000018
用于表示胡萝卜B_2对咖喱调味料A_2的吸收能力；
酱油调味料A_1在米饭D上的相对入味评价指标
Figure PCTCN2021135904-appb-000019
Figure PCTCN2021135904-appb-000020
用于表示米饭D对酱油调味料A_1的吸收能力；
咖喱调味料A_2在米饭D上的相对入味评价指标
Figure PCTCN2021135904-appb-000021
Figure PCTCN2021135904-appb-000022
用于表示米饭D对咖喱调味料A_2的吸收能力；
(2)调味料A_i在香肠B_1、胡萝卜B_2、米饭D上的绝对入味评价指标的计算方法为：
酱油调味料A_1在香肠B_1上的绝对入味评价指标
Figure PCTCN2021135904-appb-000023
用于表示香肠B_1颗粒对酱油调味料A_1的吸收总量；
咖喱调味料A_2在香肠B_1上的绝对入味评价指标
Figure PCTCN2021135904-appb-000024
用于表示香肠B_1颗粒对咖喱调味料A_2的吸收总量；
酱油调味料A_1在胡萝卜B_2上的绝对入味评价指标
Figure PCTCN2021135904-appb-000025
用于表示胡萝卜B_2颗粒对酱油调味料A_1的吸收总量；
咖喱调味料A_2在胡萝卜B_2上的绝对入味评价指标
Figure PCTCN2021135904-appb-000026
用于表示胡萝卜B_2颗粒对咖喱调味料A_2的吸收总量；
酱油调味料A_1在米饭D上的绝对入味评价指标
Figure PCTCN2021135904-appb-000027
Figure PCTCN2021135904-appb-000028
用于表示米饭D颗粒对酱油调味料A_1的吸收总量；
咖喱调味料A_2在米饭D上的绝对入味评价指标
Figure PCTCN2021135904-appb-000029
Figure PCTCN2021135904-appb-000030
用于表示米饭D颗粒对咖喱调味料A_2的吸收总量；
(3)调味料A_i在香肠B_1、胡萝卜B_2、米饭D颗粒间的入味均匀度评价指标的计算方法为：
酱油调味料A_1在香肠B_1上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000031
表示香肠B_1不同颗粒间酱油调味料A_1含量的差异程度；
咖喱调味料A_2在香肠B_1上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000032
表示香肠B_1不同颗粒间咖喱调味料A_2含量的差异程度；
酱油调味料A_1在胡萝卜B_2上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000033
表示胡萝卜B_2不同颗粒间酱油调味料A_1含量的差异程度；
咖喱调味料A_2在胡萝卜B_2上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000034
表示胡萝卜B_2不同颗粒间咖喱调味料A_2含量的差异程度；
酱油调味料A_1在米饭D上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000035
表示米饭D不同颗粒间酱油调味料A_1含量的差异程度；
咖喱调味料A_2在米饭D上的入味均匀度评价指标
Figure PCTCN2021135904-appb-000036
表示米饭D不同颗粒间咖喱调味料A_2含量的差异程度；
酱油调味料A_1在炒饭不同种类食材的入味均匀度评价指标
Figure PCTCN2021135904-appb-000037
表示不同食材种类间酱油调味料A_1平均含量的差异程度，其中
Figure PCTCN2021135904-appb-000038
咖喱调味料A_2在炒饭不同种类食材的入味均匀度评价指标
Figure PCTCN2021135904-appb-000039
表示不同食材种类间咖喱调味料A_2平均含量的差异程度，其中
Figure PCTCN2021135904-appb-000040
过程五，前期根据标准样品利用感官评价建立炒饭入味评价标准指标，将过程四获得的入味特性评价指标与标准指标相对比，评价指标越接近标准指标，说明炒饭的入味品质越好，在标准指标的±10％内，认为其品质良好。
其中标准样品是指结合感官评价和理化分析方法鉴定色、香、味俱全的高品质炒饭。

Claims (6)

  1. 炒饭食味特性的快速定量评价方法，其特征在于，按照下述步骤进行：
    步骤一，所述炒饭调味料定量模型构建包含以下过程：
    过程一，将m种调料液A_1、A_2、……、A_(m-1)、A_m用作烹制炒饭的调味料，将n种配菜B_1、B_2、……、B_(n-1)、B_n，以及米饭D用作烹制炒饭的食材；第i种调料液A_i的标准浓度为C_A_i，第j种配菜B_j的单颗粒平均表面积为S_B_j，米饭D的单颗粒平均表面积为S_D，其中C_A_i、S_B_j、S_D均为正数，m和n均为大于0的整数，i∈[1，m]、j∈[1，n]；
    过程二，分别取e份炒饭食材组合，每份炒饭食材组合包含N_B_j颗第j种配菜B_j以及N_D粒米饭D；分别取e份炒饭调料液组合，每份炒饭调料液组合包含体积为V_A_i ml第i种调料液A_i，且第k份炒饭调料液组合中A_i的浓度为C_k_A_i＝k*(C_A_i)/e，其中e为大于2的整数，k∈[1，e]，N_B_j、N_D均为正整数，V_A_i为正数；
    过程三，按照调料液浓度由低到高的顺序，将e份炒饭调料液组合、e份炒饭食材组合以1种炒饭调料液组合搭配1种炒饭食材组合的方式烹制炒饭，得到e份成品炒饭，且第k份成品炒饭包含配菜B_j与m种浓度为C_k_A_i的调料液A_i经烹制后的炒饭成分B_j&A_0&C_k、以及米饭D与m种浓度为C_k_A_i的调料液A_i经烹制后的炒饭成分D&A_0&C_k；
    过程四，高光谱图像采集与光谱特征提取；
    取i∈[1，m]、j∈[1，n]、k∈[1，e]，分别取f1颗炒饭成分B_j&A_0&C_k、D&A_0&C_k进行高光谱图像采集及光谱特征变量提取，得到烹制后炒饭中第i种调味料A_i的特征变量G1_A_i；并根据特征变量G1_A_i分别提取第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k；其中f1为正整数；
    过程五，根据第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k以及调味料A_i的总用量(V_A_i)*k*(C_A_i)/e；利用未知数h_A_i、b_A_i假设调味料A_i的定量模型为y＝F1_i(x)＝x*h_A_i+b_A_i，根据利用模型结合调味料A_i的特征值之和Sum_g1_A_i_k计算得到的第k份成品炒饭调味料A_i的总用量等于本步骤过程二中第k份炒饭炒制时加入的A_i总用量(V_A_i)*k*(C_A_i)/e，可建立用于求解未知数h_A_i、b_A_i的方程(Sum_g1_A_i_k)*(h_A_i)+b_A_i＝(V_A_i)*k*(C_A_i)/e；当k依次取值为1、2……、e-1、e时，利用得到的方程组可求解出未知数h_A_i、b_A_i，从而得到不含未知数的调味料A_i的定量模型为y＝F1_i(x)＝x*h_A_i+b_A_i，其中模型y为调味料A_i的浓度、x为调味料A_i的特征变量G1_A_i；
    步骤二，所述炒饭原料种类识别模型构建包含以下过程：
    过程一，取i∈[1，m]，j∈[1，n]，分别从步骤一过程三烹制的第e份炒饭中取f2颗炒饭成分B_j&A_0&C_e、D&A_0&C_e按照d:1的比例随机分为校正集和预测集，并对其进行高光谱图像采集及原料种类光谱特征变量G2_B&D的提取，根据光谱特征变量G2_B&D分别提取校正集中配菜B_j对应的光谱特征值g2_B_j_cal和米饭D对应的光谱特征值g2_D_cal，以及预测集中配菜B_j对应的光谱特征值g2_B_j_pre和米饭D对应的光谱特征值g2_D_pre；其中d、f2为正整数；
    过程二，利用光谱特征变量G2_B&D作为自变量X，以炒饭原料种类作为因变量Y；以参考值0代表米饭D，以参考值j代表配菜B_j，结合化学计量学方法建立炒饭原料种类识别模型Y＝F2(X)；
    步骤三，所述炒饭食味特性定量表征包含以下过程：
    过程一，将步骤一中过程一所述的m种调料液A_1、A_2、……、A_(m-1)、A_m用作烹制炒饭的调味料，n种配菜B_1、B_j、B_2、……、B_(n-1)、B_n，以及米饭D用作烹制炒饭的食材；第i种调料液A_i的浓度为C’_A_i，第j种配菜B_j的单颗粒表面积为S’_B_j，米饭D的单颗粒表面积为S’_D，其中C’_A_i、S’_B_j、S’_D均为正数；
    过程二，将体积分别为V’_A_i的m种调料A_i、颗粒数分别为N’_B_j的n种配菜B_j、以及颗粒数为N’_D的米饭D按照步骤一过程三中的烹饪工艺烹制炒饭；将烹制的炒饭打散、平铺成颗粒彼此分离的状态从而得到炒饭的
    Figure PCTCN2021135904-appb-100001
    个颗粒；按照步骤一过程四中的方法采集高光谱图像，根据调味料A_i的特征变量G1_A_i得到炒饭中第p个颗粒对应的调味料A_i的光谱特征值g1’_A_i_p；根据步骤二过程一中的原料种类光谱特征变量G2_B&D，得到炒饭中第p个颗粒对应的种类识别光谱特征值g2’_B&D_p；其中p∈[1，N’]；
    过程三，设置变量R_B_j用于记录本步骤配菜B_j被成功识别的颗粒数，设置变量R_D用于记录本步骤米饭D被成功识别的颗粒数，且R_B_j、R_D的初始值设为0；p的取值依次取1、2、……、N’-1、N’；
    首先，将第p个颗粒的种类识别光谱特征值g2’_B&D_p代入炒饭原料种类识别模型Y＝F2(X)，得到第p个颗粒所属的炒饭原料种类Yp；
    其次，i的值依次取1、2、……、m-1、m；当Yp＝0时，表示第p个颗粒被识别为米饭D，则米饭被成功识别的颗粒数R_D增加1个；将第p个颗粒对应的光谱特征值g1’_A_i_p代入调味料A_i定量模型为y＝F1_i(x)，得到第R_D个米饭颗粒对应的调味料A_i的相对 含量y1&D&R_D&A_i，并根据米饭D的单颗粒表面积为S’_D得到该颗粒对应的调味料A_i的绝对含量y2&D&R_D&A_i＝(y1&D&R_D&A_i)*S’_D；
    当Yp＝j时，表示第p个颗粒被识别为配菜B_j，则配菜B_j被成功识别的颗粒数R_B_j增加1个；将第p个颗粒对应的光谱特征值g1’_A_i_p代入调味料A_i定量模型为y＝F1_i(x)，得到第R_B_j个配菜B_j颗粒对应的调味料A_i的相对含量y1&B_j&R_B_j&A_i，并根据配菜B_j的单颗粒表面积为S’_B_j得到该颗粒对应的调味料A_i的绝对含量y2&B_j&R_B_j&A_i＝(y1&B_j&R_B_j&A_i)*S’_B_j。
    最后，得到本步骤炒饭中N’_B_j颗配菜B_j颗粒Uj上对应的调味料A_i的相对含量y1&B_j&Uj&A_i及绝对含量y2&B_j&Uj&A_i、N’_D颗粒米饭D颗粒VD上对应的调料A_i的相对含量y1&D&VD&A_i及绝对含量y2&D&VD&A_i，其中Uj∈[1，N’_B_j]、VD∈[1，N’_D]；
    过程四，计算炒饭食味特性的相对入味特性评价指标、绝对入味特性评价指标、均度入味特性评价指标，具体计算过程为：
    (1)调味料A_i在配菜B_j、米饭D上的相对入味评价指标的计算方法为：
    第i种调味料A_i在第j种配菜B_j上的相对入味评价指标
    Figure PCTCN2021135904-appb-100002
    用于表示配菜B_j对调味料A_i的吸收能力；
    第i种调味料A_i在米饭D上的相对入味评价指标
    Figure PCTCN2021135904-appb-100003
    用于表示米饭D对调味料A_i的吸收能力；
    (2)调味料A_i在配菜B_j、米饭D上的绝对入味评价指标的计算方法为：
    第i种调味料A_i在第j种配菜B_j上的绝对入味评价指标
    Figure PCTCN2021135904-appb-100004
    用于表示单颗粒配菜B_j对调味料A_i的吸收总量；
    第i种调味料A_i在米饭D上的绝对入味评价指标
    Figure PCTCN2021135904-appb-100005
    用于表示单颗粒米饭D对调味料A_i的吸收总量；
    (3)调味料A_i在配菜B_j、米饭D颗粒间的入味均匀度评价指标的计算方法为：
    第i种调味料A_i在第j种配菜B_j上的入味均匀度评价指标
    Figure PCTCN2021135904-appb-100006
    Figure PCTCN2021135904-appb-100007
    表示配菜B_j不同颗粒间调料A_i含量的差异程度；
    第i种调味料A_i在米饭D上的入味均匀度评价指标
    Figure PCTCN2021135904-appb-100008
    表示米饭D不同颗粒间调料A_i含量的差异程度；
    第i种调味料A_i在炒饭不同种类食材的入味均匀度评价指标
    Figure PCTCN2021135904-appb-100009
    表示不同食材种类间调料A_i平均含量的差异程度，其中
    Figure PCTCN2021135904-appb-100010
    过程五，将过程四获得的入味特性评价指标与标准样品的标准指标相对比，即可实现炒饭的入味品质的评价。
  2. 根据权利要求1所述的炒饭食味特性的快速定量评价方法，其特征在于，步骤一中所述G1_A_i的提取过程为：以每个炒饭成分颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭的全波段光谱信息；利用主成分分析算法进行光谱特征变量提取，得到烹制后炒饭中第i种调味料A_i的特征变量G1_A_i。
  3. 根据权利要求1所述的炒饭食味特性的快速定量评价方法，其特征在于，步骤一中所述第k份成品炒饭中调味料A_i的特征值之和Sum_g1_A_i_k的提取过程为：
    (1)提取f1颗添加m种浓度为C_k_A_i＝k*(C_A_i)/e调料液A_i的炒饭成分B_j&A_0&C_k对应的平均光谱，根据调味料A_i的特征变量G1_A_i得到B_j&A_0&C_k对应的平均特征值g1_B_j&A_i&C_k；提取f1颗添加m种浓度为C_k_A_i＝k*(C_A_i)/e调料液A_i的炒饭成分D&A_0&C_k对应的平均光谱，根据调味料A_i的特征变量G1_A_i得到D&A_0&C_k对应的平均特征值g1_D&A_i&C_k；
    (2)根据第k份炒饭中配菜B_j的颗粒数N_B_j及单颗平均表面积S_B_j、米饭D的颗粒数N_D及单颗平均表面积S_D，得到第k份成品炒饭中调味料A_i的特征值之和
    Figure PCTCN2021135904-appb-100011
  4. 根据权利要求1炒饭食味特性的快速定量评价方法，其特征在于，步骤二中所述G2_B&D的提取方法：将每个炒饭成分B_j&A_0&C_e、D&A_0&C_e颗粒作为一个感兴趣区域，将每个感兴趣区域的平均光谱作为该样本的光谱数据，得到炒饭样品的全波段光谱信息；利用连续投影算法筛选得到t个表征原料种类的特征波长λ对应的反射强度作为特征变量G2_B&D。
  5. 根据权利要求1所述的炒饭食味特性的快速定量评价方法，其特征在于，步骤二中所述g2_B_j_cal为校正集中h1个颗粒B_j&A_0&C_e在特征波长λ下的反射强度构成 的h1×t的光谱特征值矩阵；其中t为特征波长个数为；
    所述g2_D_cal为校正集中h1个颗粒米饭D&A_0&C_e在特征波长λ下的反射强度构成的h1×t的光谱特征值矩阵，其中t为特征波长个数；同理g2_B_j_pre和g2_D_pre为预测集中相应炒饭样品颗粒在特征波长λ下的反射强度构成的h1*1/d×t的光谱特征值矩阵。
  6. 根据权利要求1所述的炒饭食味特性的快速定量评价方法，其特征在于，步骤二中所述化学计量学方法为支持向量机。
PCT/CN2021/135904 2021-11-24 2021-12-07 炒饭食味特性的快速定量评价方法 WO2023092647A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/907,963 US20230187030A1 (en) 2021-11-24 2021-12-07 Rapid quantitative evaluation method for taste characteristics of fried rice
JP2022514241A JP7498982B2 (ja) 2021-11-24 2021-12-07 炒飯の食味特性を速やかに定量評価する方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111403368.9 2021-11-24
CN202111403368.9A CN114220501A (zh) 2021-11-24 2021-11-24 炒饭食味特性的快速定量评价方法

Publications (1)

Publication Number Publication Date
WO2023092647A1 true WO2023092647A1 (zh) 2023-06-01

Family

ID=80698115

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/135904 WO2023092647A1 (zh) 2021-11-24 2021-12-07 炒饭食味特性的快速定量评价方法

Country Status (4)

Country Link
US (1) US20230187030A1 (zh)
JP (1) JP7498982B2 (zh)
CN (1) CN114220501A (zh)
WO (1) WO2023092647A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114220501A (zh) * 2021-11-24 2022-03-22 江苏大学 炒饭食味特性的快速定量评价方法
CN116804669B (zh) * 2023-06-16 2024-04-02 枣庄华宝牧业开发有限公司 一种肉制品加工用油炸监视系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02290537A (ja) * 1989-04-30 1990-11-30 Nireco Corp 近赤外線による食味値推定方法
WO2019102400A1 (en) * 2017-11-22 2019-05-31 Cti Srl System and process for the recognition, characterization and classification of foods and nutrients in foods
CN110179319A (zh) * 2019-05-20 2019-08-30 梁志鹏 一种智能烹饪的方法及装置
CN110366731A (zh) * 2017-03-07 2019-10-22 索尼公司 用于指导膳食的图像捕获的系统、方法和计算机程序
CN111007040A (zh) * 2019-12-27 2020-04-14 黑龙江八一农垦大学 大米食味品质近红外光谱快速评价方法

Family Cites Families (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5464981A (en) * 1993-05-17 1995-11-07 Simco/Ramic Corporation Methods of separating selected items from a mixture including raisins and the selected items
JPH07270312A (ja) * 1994-02-09 1995-10-20 Satake Eng Co Ltd 米飯の食味評価方法及び装置
JPH07260681A (ja) * 1995-03-07 1995-10-13 Iseki & Co Ltd 食物品質評価法
JP2000266742A (ja) * 1999-03-15 2000-09-29 Tokyo Gas Co Ltd 炊飯米の食味評価方法及び装置
US20040146615A1 (en) * 2001-04-13 2004-07-29 Mcdonald John Thomas Processes for evaluating agricultural and/or food materials; applications;and, products
CN1930474B (zh) * 2004-03-05 2012-07-04 普利玛食品株式会社 变应原的检测方法
US7805066B2 (en) * 2007-12-24 2010-09-28 Microsoft Corporation System for guided photography based on image capturing device rendered user recommendations according to embodiments
JP2011221637A (ja) * 2010-04-06 2011-11-04 Sony Corp 情報処理装置、情報出力方法及びプログラム
US20140220217A1 (en) * 2011-07-12 2014-08-07 Maraxi, Inc. Method and compositions for consumables
US10458845B2 (en) * 2012-06-14 2019-10-29 Medibotics Llc Mobile device for food identification an quantification using spectroscopy and imaging
US9442100B2 (en) * 2013-12-18 2016-09-13 Medibotics Llc Caloric intake measuring system using spectroscopic and 3D imaging analysis
US11754542B2 (en) * 2012-06-14 2023-09-12 Medibotics Llc System for nutritional monitoring and management
JP6142526B2 (ja) * 2012-12-27 2017-06-07 セイコーエプソン株式会社 食品分析装置
EP3022690A4 (en) * 2013-07-17 2017-01-25 Commonwealth Scientific & Industrial Research Organisation ( C.S.I.R.O. ) System and method for formulating a foodstuff
US9659225B2 (en) * 2014-02-12 2017-05-23 Microsoft Technology Licensing, Llc Restaurant-specific food logging from images
US20150302160A1 (en) * 2014-04-21 2015-10-22 The Board of Regents of the NV Sys of Higher Edu, Las Vegas NV on Behalf of the Univ of NV Las Vega Method and Apparatus for Monitoring Diet and Activity
US9916520B2 (en) * 2014-09-03 2018-03-13 Sri International Automated food recognition and nutritional estimation with a personal mobile electronic device
WO2016189536A1 (en) * 2015-05-26 2016-12-01 Aspect Ai Ltd. Apparatus and method for quality detection of a processed product
US10070661B2 (en) * 2015-09-24 2018-09-11 Frito-Lay North America, Inc. Feedback control of food texture system and method
US10969316B2 (en) * 2015-09-24 2021-04-06 Frito-Lay North America, Inc. Quantitative in-situ texture measurement apparatus and method
US10998087B2 (en) * 2016-08-25 2021-05-04 The Government of the United States of Amercia as represented by the Secretary of Homeland Security Systems and methodologies for desigining simulant compounds
US11808771B2 (en) * 2017-01-25 2023-11-07 Corteva Agriscience Llc Methods and systems for selective quantitation and detection of allergens including Gly m 7
EP3593282A1 (en) * 2017-03-07 2020-01-15 Sony Corporation System, method and computer program
KR102143700B1 (ko) * 2017-12-08 2020-08-12 한양대학교 에리카산학협력단 식품 정보 관리 장치 및 식품 정보 관리 방법
WO2019148019A1 (en) * 2018-01-25 2019-08-01 Kraft Foods Group Brands Llc Method and system for improving food-related personalization
EP3537119B1 (de) * 2018-03-06 2022-09-28 Vorwerk & Co. Interholding GmbH System mit einem speisenzubereitungsgerät und einem spektrometer
US20190295440A1 (en) * 2018-03-23 2019-09-26 Nutrino Health Ltd. Systems and methods for food analysis, personalized recommendations and health management
US10832094B2 (en) * 2018-04-10 2020-11-10 International Business Machines Corporation Generating hyperspectral image database by machine learning and mapping of color images to hyperspectral domain
JP2020181491A (ja) * 2019-04-26 2020-11-05 ソフトバンクグループ株式会社 システム、プログラム、及び方法
CN110320162B (zh) * 2019-05-20 2021-04-23 广东省智能制造研究所 一种基于生成对抗网络的半监督高光谱数据定量分析方法
WO2020237055A1 (en) * 2019-05-21 2020-11-26 Ohio State Innovation Foundation Portable spectrometer system and methods for determining nutritional and quality traits
CN114127674B (zh) * 2019-08-08 2023-08-22 诺特可特拉华州有限责任公司 对风味进行分类的方法
US10957424B1 (en) * 2020-08-10 2021-03-23 NotCo Delaware, LLC Neural network method of generating food formulas
TWI778789B (zh) * 2021-09-14 2022-09-21 華新麗華股份有限公司 配方建構系統、配方建構方法、內儲程式之電腦可讀取記錄媒體與非暫時性電腦程式產品
CN114220501A (zh) * 2021-11-24 2022-03-22 江苏大学 炒饭食味特性的快速定量评价方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02290537A (ja) * 1989-04-30 1990-11-30 Nireco Corp 近赤外線による食味値推定方法
CN110366731A (zh) * 2017-03-07 2019-10-22 索尼公司 用于指导膳食的图像捕获的系统、方法和计算机程序
WO2019102400A1 (en) * 2017-11-22 2019-05-31 Cti Srl System and process for the recognition, characterization and classification of foods and nutrients in foods
CN110179319A (zh) * 2019-05-20 2019-08-30 梁志鹏 一种智能烹饪的方法及装置
CN111007040A (zh) * 2019-12-27 2020-04-14 黑龙江八一农垦大学 大米食味品质近红外光谱快速评价方法

Also Published As

Publication number Publication date
CN114220501A (zh) 2022-03-22
US20230187030A1 (en) 2023-06-15
JP2023553222A (ja) 2023-12-21
JP7498982B2 (ja) 2024-06-13

Similar Documents

Publication Publication Date Title
Esteki et al. Use of spectroscopic methods in combination with linear discriminant analysis for authentication of food products
Li et al. Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems
Zhou et al. Information fusion of emerging non-destructive analytical techniques for food quality authentication: A survey
Pu et al. Hierarchical variable selection for predicting chemical constituents in lamb meats using hyperspectral imaging
Wang et al. Use of hyperspectral imaging to discriminate the variety and quality of rice
Manley Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials
Modupalli et al. Emerging non-destructive methods for quality and safety monitoring of spices
Barbin et al. Predicting quality and sensory attributes of pork using near-infrared hyperspectral imaging
Ding et al. NIR spectroscopy and chemometrics for the discrimination of pure, powdered, purple sweet potatoes and their samples adulterated with the white sweet potato flour
Liu et al. Feasibility of using hyperspectral imaging to predict moisture content of porcine meat during salting process
CN102435713B (zh) 中药品质自动检测系统
WO2023092647A1 (zh) 炒饭食味特性的快速定量评价方法
Baardseth et al. Multivariate techniques in the analysis of meat quality
Kiani et al. Hyperspectral imaging, a non-destructive technique in medicinal and aromatic plant products industry: Current status and potential future applications
Yuan et al. Selecting key wavelengths of hyperspectral imagine for nondestructive classification of moldy peanuts using ensemble classifier
Xiao et al. Prediction of soluble solid content of Agaricus bisporus during ultrasound-assisted osmotic dehydration based on hyperspectral imaging
Marshall et al. Hyperspectral imaging for food applications
Zhao et al. Integration of spectra and image features of Vis/NIR hyperspectral imaging for prediction of deoxynivalenol contamination in whole wheat flour
Posudin et al. Non-destructive detection of food adulteration to guarantee human health and safety
Tao et al. Rapid and non-destructive detection of cassava flour adulterants in wheat flour using a handheld MicroNIR spectrometer
Cheng et al. Developing a NIR multispectral imaging for prediction and visualization of peanut protein content using variable selection algorithms
Yijie et al. Rapid and non-destructive prediction of protein content in peanut varieties using near-infrared hyperspectral imaging method
Qin et al. Prediction of Peking duck intramuscle fat content by near-infrared spectroscopy
Kucha et al. Improving intramuscular fat assessment in pork by synergy between spectral and spatial features in hyperspectral image
Xu Electronic eye for food sensory evaluation

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2022514241

Country of ref document: JP

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21965375

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE