CN105320955A - Meal quality management detection module and meal quality management detection method applying same - Google Patents
Meal quality management detection module and meal quality management detection method applying same Download PDFInfo
- Publication number
- CN105320955A CN105320955A CN201410826078.9A CN201410826078A CN105320955A CN 105320955 A CN105320955 A CN 105320955A CN 201410826078 A CN201410826078 A CN 201410826078A CN 105320955 A CN105320955 A CN 105320955A
- Authority
- CN
- China
- Prior art keywords
- cutlery box
- pantry
- content
- image
- bidimensional image
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 235000012054 meals Nutrition 0.000 title claims abstract description 58
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 235000013305 food Nutrition 0.000 claims description 93
- 238000004458 analytical method Methods 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 14
- 241000251468 Actinopterygii Species 0.000 description 6
- 238000000034 method Methods 0.000 description 5
- 235000013311 vegetables Nutrition 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 2
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 2
- 240000003768 Solanum lycopersicum Species 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 235000021183 entrée Nutrition 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 235000011299 Brassica oleracea var botrytis Nutrition 0.000 description 1
- 240000003259 Brassica oleracea var. botrytis Species 0.000 description 1
- 240000008436 Ipomoea aquatica Species 0.000 description 1
- 235000019004 Ipomoea aquatica Nutrition 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 240000001085 Trapa natans Species 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 235000009165 saligot Nutrition 0.000 description 1
Abstract
The invention discloses a meal quality management detection module and a meal quality management detection method using the same. The meal quality management detection module comprises two-dimensional image capturing equipment, three-dimensional image capturing equipment and an analysis unit. The two-dimensional image capturing device is used for obtaining a two-dimensional image of a meal box filled with meal preparation contents, and the two-dimensional image of the meal box has the two-dimensional image of the meal preparation contents. The three-dimensional image capturing device is used for acquiring depth information of dish variety styles of catering contents. The analyzing unit is used for analyzing the two-dimensional image of the meal box to identify the type of the meal box, analyzing the two-dimensional image of the meal distribution content to obtain the texture feature and the color feature of the two-dimensional image of the meal distribution content, analyzing the variety pattern of the meal distribution content according to the texture feature and the color feature, and calculating the weight of the meal distribution content according to the depth information of the two-dimensional image of the meal distribution content and the dish variety pattern.
Description
Technical field
The present invention relates to a kind of food quality management detection module and apply its food quality management detection method, relate more particularly to a kind of image application and confirm the food quality management detection module of cutlery box quality and apply its food quality management detection method.
Background technology
Medical system has huge cutlery box demand, to be supplied to patient or to need the people of special diet.The dish of each cutlery box and consumption can be different according to the demand of diner.On food production line, after cutlery box dress dish completes, usually whether meet a food specification by nutritionist's visual confirmation cutlery box quality.But, with visual type easily cause erroneous judgement and quite inefficent.Therefore, how to confirm that cutlery box quality is that the art dealer makes great efforts one of target efficiently.
Summary of the invention
The invention relates to a kind of food quality management detection module and apply its food quality management detection method, cutlery box pantry content and quality can be confirmed efficiently.
According to one embodiment of present invention, a kind of food quality management detection module is proposed.Food quality management detection module comprises a bidimensional image capture device, a 3-dimensional image capture device and an analytic unit.Bidimensional image capture device is in order to obtain the cutlery box bidimensional image that is filled with the cutlery box of a pantry content, and cutlery box bidimensional image has a pantry content bidimensional image of pantry content.3-dimensional image capture device is in order to obtain the depth information of a dish kind pattern of pantry content.Analytic unit is for performing following steps: analyze cutlery box bidimensional image, with a kind of identification cutlery box, analyze pantry content bidimensional image, to obtain a textural characteristics and a color character of pantry content bidimensional image, according to textural characteristics and color character, analyze a kind pattern of pantry content, and the depth information of foundation pantry content bidimensional image and dish kind pattern, calculate the deal of pantry content.
According to another embodiment of the invention, a kind of food quality management detection method is proposed.Food quality management detection method comprises the following steps: obtain the cutlery box bidimensional image that is filled with the cutlery box of a pantry content, cutlery box bidimensional image has a pantry content bidimensional image of pantry content; Obtain the depth information of a dish kind pattern of pantry content; Analyze cutlery box bidimensional image, with a kind of identification cutlery box; Analyze pantry content bidimensional image, to obtain a textural characteristics and a color character of pantry content bidimensional image; The depth information of foundation pantry content bidimensional image and dish kind pattern, calculates the deal of pantry content; And, according to textural characteristics and color character, analyze the kind pattern of pantry content.
In order to have a better understanding to above-mentioned and other aspect of the present invention, preferred embodiment cited below particularly, and coordinate appended accompanying drawing, be described in detail below:
Accompanying drawing explanation
Fig. 1 represents the schematic diagram of the food quality management detection module system according to one embodiment of the present of invention;
Fig. 2 represents the functional module block scheme of food quality management detection module;
Fig. 3 represents the process flow diagram of the food quality management detection method according to one embodiment of the present of invention;
Fig. 4 represents the schematic diagram that cutlery box transmits on the conveying belt of the food quality management detection system of Fig. 1;
Fig. 5 represents the change resolution schematic diagram of the cutlery box bidimensional image of Fig. 4;
Fig. 6 represents the schematic diagram of the cutlery box characteristic image stored by database of Fig. 2;
Fig. 7 represents the change resolution schematic diagram of the cutlery box bidimensional image of Fig. 5;
Fig. 8 represents the schematic diagram of the cutlery box bidimensional image of the whole cutlery box of Fig. 4;
Fig. 9 represents the corresponding relation figure of the cutlery box bidimensional image of Fig. 8 and the cutlery box characteristic image of Fig. 6;
Figure 10 represents the cut-open view of the cutlery box of Fig. 4 along direction 10-10 '.
Description of reference numerals:
100: food quality management detection module system;
110: conveying belt;
120: cutlery box corrective rail;
130: food quality management detection module;
131: bidimensional image capture device;
132: 3-dimensional image capture device;
133: analytic unit;
134: database;
140: display panel;
10: cutlery box;
17e: hypotenuse;
18: broken line;
A1: angle of inclination;
H11, h12: the depth information of dish kind pattern;
M1, M2, M3, M4, M5: pantry content;
P31, P32, P33, P34, P35: pantry content image;
P11, P12, P13, P22, P21: cutlery box bidimensional image;
P3: cutlery box bidimensional image;
PM1, PM2, PM3, PM4, PM5: concentrate food bidimensional image;
R: cog region;
S1, S2: cutlery box characteristic image;
S11, S12, S13, S14, S15: meal lattice region.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in further detail.
Please refer to Fig. 1 and Fig. 2, Fig. 1 represents the schematic diagram of the food quality management detection module system according to one embodiment of the present of invention, and Fig. 2 represents the functional module block scheme of food quality management detection module.
Food quality management detection module system 100 comprises conveying belt 110, cutlery box corrective rail 120, food quality management detection module 130 and display panel 140.Whether conveying belt 110, in order to carry cutlery box 10 (shown in Figure 4) through food quality management detection module 130, meets a food specification with the pantry content detecting cutlery box 10.Food specification can be recorded in a meal card.Cutlery box corrective rail 20 can the attitude of cutlery box 10 passed through of correcting, to reduce the angle excursion of cutlery box 10, and then increases the correctness detected.
As shown in Figure 2, food quality management detection module 130 comprises bidimensional image capture device 131,3-dimensional image capture device 132, analytic unit 133 and database 134.
Bidimensional image capture device 131 can obtain the image of pantry content M1 to M5 (as shown in Figure 4) in cutlery box 10, with kind pattern (the i.e. kind of pantry content M1 to M5 in identification cutlery box 10, the dish such as such as fish, chicken leg, vegetables), in addition, one meal card (not shown on figure) can be transmitted on conveying belt 110 along with cutlery box 10, meal card shows word, symbol or bar code, to represent the food specification of cutlery box 10.Bidimensional image capture device 131 can obtain the meal card image of meal card, as word image or bar code image.Analytic unit 133 can analyze meal card image, to obtain the food specification of corresponding cutlery box 10.
3-dimensional image capture device 132 can obtain the depth information of the dish kind pattern of the pantry content M1 to M5 (as shown in Figure 4) of cutlery box 10.Analytic unit 133 can analyze the image of pantry content and the depth information of dish kind pattern, to calculate the deal of pantry content, and judges whether the deal of pantry content meets food specification further.That is, whether the food quality management detection module 130 of the embodiment of the present invention pantry content deal of automatic decision cutlery box 10 can meet food specification, to promote the efficiency confirming cutlery box quality.It is below further instruction.
Fig. 3 represents the process flow diagram of the food quality management detection method according to one embodiment of the present of invention.
In step s 110, referring to Fig. 4, it represents the schematic diagram that cutlery box transmits on the conveying belt of the food quality management detection system of Fig. 1.Cutlery box 10, after completing filling pantry content M1 to M5, continues to be carried by conveying belt 110, to enter in food quality management detection module 130, then judges whether pantry content M1 to M5 meets food specification by food quality management detection module 130.
In the present embodiment, pantry content M1 is entree, and pantry content M2 to M5 is vegetables, wherein pantry content M1 is such as fish, row's formula sumptuous meal, chicken leg or other type entree, and pantry content M2 to M5 is water caltrop, cauliflower, water spinach and Scrambled Egg with Tomato or other type vegetables respectively.As shown in Figure 4, pantry content M1 can be layed in staple food, as on rice, so also can omit staple food in another embodiment.When cutlery box 10 enters the cog region R of food quality management detection module 130, bidimensional image capture device 131 can get the cutlery box bidimensional image P11 (as shown in Figure 5) of cutlery box 10, with the kind of identification cutlery box 10.
In the step s 120, as shown in Figure 5, it represents the schematic diagram of the change resolution of the cutlery box bidimensional image of Fig. 4.Obtain after cutlery box 10 enters the cutlery box bidimensional image P11 of cog region R at bidimensional image capture device 131, start to analyze cutlery box bidimensional image P11, and with the several cutlery box characteristic image comparison in database 134, with the kind of identification cutlery box 10.
Say further, as shown in Figure 6, it represents the schematic diagram of the cutlery box characteristic image stored by database of Fig. 2.Database 134 stores two cutlery box characteristic image S1 and S2.In another embodiment, the quantity of cutlery box characteristic image can more than 2.Each cutlery box characteristic image S1 and S2 has different recognition features, and whether analytic unit 133 can have recognition feature, to pick out the kind of cutlery box 10 by identification cutlery box bidimensional image P11.With cutlery box characteristic image S1, the recognition feature of cutlery box characteristic image S1 is the hypotenuse 17e of meal lid, if analytic unit 133 analyzes the feature that cutlery box bidimensional image P11 has hypotenuse 17e, represents the kind of the kind corresponding cutlery box characteristic image S1 of cutlery box 10.With cutlery box characteristic image S2, the recognition feature of cutlery box characteristic image S2 (being such as bowl) is arc limit.If analytic unit 133 analyzes the feature that cutlery box bidimensional image P11 has the hypotenuse 17e of cutlery box characteristic image S2, represent the kind of the kind corresponding cutlery box characteristic image S2 of cutlery box 10.
In addition, the specification of each cutlery box characteristic image is different.With cutlery box characteristic image S1, cutlery box characteristic image S1 is the image of packed meal box, and it only has five eat lattice region S11 to S15, its Chinese meal lattice region S11 to S15 to be the image of five foods meal lattice 11 to 15 (as shown in Figure 4) of cutlery box 10 respectively.
In addition, database 134 more stores cutlery box specification.Such as, with cutlery box characteristic image S1, database 134 stores meal lattice area and/or the meal lattice volume of food meal lattice 11 to 15.With cutlery box characteristic image S2, database 134 stores aperture area and/or the volume of bowl.When analytic unit 133 picks out the kind belonging to cutlery box bidimensional image P11, namely obtain the cutlery box specification of this cutlery box kind simultaneously.
In addition, analytic unit 133 can pass through following methods and accelerates identification speed.As shown in Figure 5, analytic unit 133 can reduce the resolution of cutlery box bidimensional image P11 at least one times, and then carries out image analysing computer, to accelerate identification speed under low-res.For example, the resolution of the cutlery box bidimensional image P11 of Fig. 5 can be reduced to 1/4th of former image resolution, and obtains cutlery box bidimensional image P12.Compared to analysis cutlery box bidimensional image P11, analytic unit 133 analyzes the speed of cutlery box bidimensional image P12, therefore can reduce many analysis times.Similarly, the resolution of cutlery box bidimensional image P12 can be reduced to 1/4th of former image resolution, and obtains cutlery box bidimensional image P13.Compared to analysis cutlery box bidimensional image P12, analytic unit 133 analyzes the speed of cutlery box bidimensional image P13, therefore can reduce more analysis times.Analytic unit 133 can analyze cutlery box bidimensional image P11, P12 and P13, and obtains three analysis results.These analysis results can with the analysis result comparison of bidimensional image P13, P22 and P21 of three of a Fig. 7 cutlery box, to verify that whether identification correct.
Fig. 7 represents the schematic diagram of the change resolution of the cutlery box bidimensional image of Fig. 5.In order to confirm that identification is whether correct, the resolution that analytic unit 133 can increase cutlery box bidimensional image P13 to four times of former image resolution, and obtains cutlery box bidimensional image P22; Then, analytic unit 133 can analyze cutlery box bidimensional image P22, the kind of identification cutlery box 10.If the identification result of cutlery box bidimensional image P22 is identical with the identification result analyzing cutlery box bidimensional image P12 (as shown in Figure 5), represent that identification correctness is very large.Similarly, the resolution that analytic unit 133 can increase cutlery box bidimensional image P22 to four times of former image resolution, and obtains cutlery box bidimensional image P21; Then, analytic unit 133 analyzes cutlery box bidimensional image P21, with the kind of identification cutlery box 10.If the identification result of cutlery box bidimensional image P21 with analyze cutlery box bidimensional image P11 (as shown in Figure 5) identification result identical, represent identification entirely true or have at least more than 80% fiduciary level.
In step s 130, which, analytic unit 133 can judge the attitude of cutlery box 10 from cutlery box bidimensional image P11.For example, analytic unit 133 can pick out the angle of inclination A1 of the broken line 18 (as shown in Figure 5) of cutlery box 10 from cutlery box bidimensional image P11 (as shown in Figure 5).According to the attitude of cutlery box 10, the corresponding relation of multiple meal lattice region S11 to S15 (as shown in Figure 9) of cutlery box characteristic image S1 and several pantry content bidimensional images P11 to P15 (as shown in Figure 9) of cutlery box bidimensional image P11 can be obtained.
In step S140, please refer to shown in Fig. 8 and Fig. 9, Fig. 8 represents the schematic diagram of the cutlery box bidimensional image of the whole cutlery box of Fig. 4, and Fig. 9 represents the relativeness figure of the cutlery box bidimensional image of Fig. 8 and the cutlery box characteristic image of Fig. 6.As shown in Figure 8, at whole cutlery box 10 after cog region R (as shown in Figure 4), bidimensional image capture device 131 can get the cutlery box bidimensional image P3 of whole cutlery box 10.Analytic unit 133 is according to the shape difference of angle of inclination A1 and cutlery box bidimensional image P3 and cutlery box characteristic image S1, through the angle and the size that change cutlery box bidimensional image P3 and/or cutlery box characteristic image S1, cutlery box bidimensional image P3 (as shown in the solid line of Fig. 9) and cutlery box characteristic image S1 (as shown in the dotted line of Fig. 9) are matched in sample comparison.Thus, as shown in Figure 9, analytic unit 133 can obtain the relativeness of several pantry content bidimensional image P31 to P35 of cutlery box bidimensional image P3 and several meal lattice region S11 to S15 of cutlery box characteristic image S1, and then can obtain pantry content bidimensional image P31 to P35 other regional extent.With pantry content bidimensional image P31 for example, meal lattice region S11 defining under, can learn pantry content bidimensional image P31 regional extent (by meal lattice region S11 around scope).
As from the foregoing, in the present embodiment, analytic unit 133 can not the meal lattice border image of Direct Analysis cutlery box bidimensional image P3, and is through cutlery box characteristic image P3 and cutlery box characteristic image S1 coincideing and obtaining the regional extent of these pantry content bidimensional images P31 on contour feature.
In step S150, due to the region of known each pantry content bidimensional image P31, analytic unit 133 can obtain the bidimensional image P31 to P35 of each pantry content of cutlery box bidimensional image P3.The bidimensional image P31 to P35 of these pantry contents can store into independent image respectively.These independent images are optionally presented on display panel 140, for operator or nutritionist's reference.
In step S160, analytic unit 133 analyzes the bidimensional image P31 to P35 of each pantry content, to obtain textural characteristics and the color character of the bidimensional image P31 to P35 of each pantry content.In the present embodiment, it is such as the color character that color polar coordinates histogram method (ColorPolorHistogram) obtains the bidimensional image P31 to P35 of each pantry content that analytic unit 133 can adopt, and analytic unit 133 can to adopt be such as that ((LocalBinaryPattern-FourierHistogram, LBP-HF) obtains the textural characteristics of each pantry content bidimensional image P31 to P35 to local binary Fourier histogram.
Then, in step S170, analytic unit 133, according to the textural characteristics of each pantry content bidimensional image P31 to P35 and color character, is compared with several concentrated food bidimensional image, to pick out the kind pattern of pantry content bidimensional image P31 to P35.
Say further, before step S110, bidimensional image capture device 131 can obtain each concentrated food bidimensional image PM1 to PM5 (concentrating food bidimensional image PM1 to PM5 to show in fig. 2) of several concentrated food (not shown) in advance, wherein concentrates food to be pantry content concentrated kenel before dispensing.Such as, the concentrated food of pantry content M1 is several fishes, and the concentrated food of pantry content M5 is a whole pot (or saying it is several parts) Scrambled Egg with Tomato.Analytic unit 133 can adopt textural characteristics and the color character of each concentrated food bidimensional image PM1 to PM5 of the analytical of similar steps S160, and be stored in database 134, using the comparison of the kind pattern recognition (step S170) as embodiment of the present invention basis.
In step S170, with pantry content bidimensional image P31 for example, the textural characteristics of the textural characteristics of pantry content bidimensional image P31 and several concentrated food bidimensional image is compared by analytic unit 133, to pick out the concentrated food bidimensional image corresponding to pantry content bidimensional image P31.Further, the color character of the color character of pantry content bidimensional image P31 and several concentrated food image is compared by analytic unit 133, to pick out the concentrated food bidimensional image corresponding to pantry content bidimensional image P31.When the textural characteristics of pantry content bidimensional image P31 and the textural characteristics of color character and same concentrated food bidimensional image and color character similar or identical time, side determines that pantry content bidimensional image P31 belongs to this same concentrated food bidimensional image, i.e. fish.The kind Pattern analysis of the kind Pattern analysis similar pantry content bidimensional image P31 of remaining pantry content bidimensional image P32 to P35, does not repeat them here.
In step S180, as shown in Figure 10, it represents the cut-open view of cutlery box along direction 10-10 ' of Fig. 4.3-dimensional image capture device 132 can obtain the depth information of the dish kind pattern of the pantry content M1 to M5 being positioned at cutlery box 10, as the depth information h12 of the depth information h11 of the dish kind pattern of pantry content M1 and the dish kind pattern of pantry content M2.Because section only cuts open pantry content M1 and M2, therefore Figure 10 only represents the depth information h12 of the depth information h11 of the dish kind pattern of pantry content M1 and the dish kind pattern of pantry content M2.
In step S190, analytic unit 133 according to the depth information of the kind of cutlery box 10 and dish kind pattern, can calculate the deal of pantry content.With pantry content M1 for example, analytic unit 133 can be analyzed pantry content bidimensional image P31 (as shown in Figure 9) and obtains the area (in the present embodiment, being the area of fish) of pantry content M1 and the depth information h11 (as shown in Figure 10) of the dish kind pattern of pantry content M1 be multiplied by the area of pantry content M1 and obtain the food volume (V1) of pantry content M1.Due to the kind (step S120) of known cutlery box 10, therefore analytic unit 133 can obtain the meal lattice volume (V11) of the food meal lattice 11 corresponding to pantry content M1 from database 134, therefore analytic unit 133 can calculate the ratio (i.e. V11/V1) of food volume (V1) and meal lattice volume (V1), and this ratio is as the deal of pantry content M1.In another embodiment, analytic unit 133 can analyze pantry content bidimensional image P31, picks out pantry content bidimensional image P31 and is fish and quantity is one, therefore can judge that the deal of pantry content M1 is a.
With pantry content M2 for example, the depth information h11 (as shown in Figure 10) of the dish kind pattern of pantry content M2 can be obtained through 3-dimensional image capture device 132.Owing to storing the meal lattice area (A12) of the food meal lattice 12 corresponding to pantry content M2 in database 134, therefore the depth information h12 (as shown in Figure 10) of the dish kind pattern of pantry content M2 can be multiplied by the meal lattice area (A12) of food meal lattice 12 and obtain the food volume (V2) of pantry content M2 by analytic unit 133.Owing to storing the meal lattice volume (V12) of the food meal lattice 12 corresponding to pantry content M2 in database 134, analytic unit 133 can calculate the ratio (i.e. V2/V12) of food volume (V2) and meal lattice volume (V12), and this ratio can be used as the deal of pantry content M2.In addition, analytic unit 133 can adopt the method for similar analysis pantry content M2, obtains the deal of other pantry content M3 to M5.
In step S195, analytic unit 133 can judge whether the deal of the pantry content M1 to M5 of cutlery box 10 and kind pattern meet food specification; If so, analytic unit 133 exports a qualifying signal, and display panel 140 shows a qualified information accordingly, as word, symbol, color etc.; If NO, analytic unit 133 exports an alarm signal, and display panel 140 shows an information warning accordingly, as word, symbol, color etc.In another embodiment, if analytic unit 133 judges that the deal of the pantry content M1 to M5 of cutlery box 10 and kind pattern do not meet food specification, also exportable alarm signal to sound producer (not shown), sound producer exports a warning sound accordingly.
In sum, although the present invention is with preferred embodiment openly as above, so itself and be not used to limit the present invention.Persond having ordinary knowledge in the technical field of the present invention, without departing from the spirit and scope of the present invention, still various modifications may be made and retouching.Therefore, the scope that protection scope of the present invention should define with accompanying claims is as the criterion.
Claims (14)
1. a food quality management detection module, comprising:
One bidimensional image capture device, being used for acquisition one is filled with a cutlery box bidimensional image of the cutlery box of a pantry content, and this cutlery box bidimensional image has a pantry content bidimensional image of this pantry content;
One 3-dimensional image capture device, is used for the depth information of the dish kind pattern obtaining this pantry content; And
One analytic unit, for performing following steps:
Analyze this cutlery box bidimensional image, with the kind of this cutlery box of identification;
Analyze this pantry content bidimensional image, to obtain textural characteristics and the color character of this pantry content bidimensional image;
According to this textural characteristics and this color character, analyze the kind pattern of this pantry content; And
According to this pantry content bidimensional image and this dish kind pattern depth information, calculate the deal of this pantry content.
2. food quality management detection module as claimed in claim 1, wherein this analytic unit is also for performing following steps:
Judge whether this kind pattern and this deal of this pantry content meet a food specification;
If this kind pattern of this pantry content and this deal do not meet this food specification, export an alarm signal; And
If this kind pattern of this pantry content and this deal meet this food specification, export a qualifying signal.
3. food quality management detection module as claimed in claim 1, also comprises:
One database, stores multiple cutlery box characteristic image;
This analytic unit is also for performing following steps:
The bidimensional image of this cutlery box of comparison and the characteristic image of these cutlery boxs, to pick out the cutlery box characteristic image belonging to this cutlery box.
4. food quality management detection module as claimed in claim 3, wherein this cutlery box has a hypotenuse; This analytic unit is also for performing following steps:
Analyze this cutlery box bidimensional image, to pick out this hypotenuse; And
This hypotenuse of comparison and these cutlery box characteristic images, to pick out this cutlery box characteristic image with this hypotenuse.
5. food quality management detection module as claimed in claim 1, also comprises:
One database, stores a cutlery box characteristic image;
This analytic unit is also for performing following steps:
Analyze this cutlery box bidimensional image, to judge an attitude of this cutlery box; And
According to this attitude, obtain this pantry content bidimensional image of this cutlery box bidimensional image and of this cutlery box characteristic image and to eat the corresponding relation in lattice region.
6. food quality management detection module as claimed in claim 5, wherein this cutlery box characteristic image has this meal lattice region multiple, and this cutlery box bidimensional image has this pantry content bidimensional image multiple, and this cutlery box has a broken line; This analytic unit is also for performing following steps:
Analyze this cutlery box bidimensional image, to pick out an angle of inclination of this broken line; And
According to the size difference of this angle of inclination and this cutlery box bidimensional image and this cutlery box characteristic image, this cutlery box bidimensional image and this cutlery box characteristic image are matched on contour feature, with the corresponding relation in the meal lattice region of the pantry content bidimensional image and this cutlery box characteristic image that obtain this cutlery box bidimensional image.
7. food quality management detection module as claimed in claim 1, wherein this pantry content fills in food meal lattice of this cutlery box, and this food quality management detection module also comprises:
One database, stores meal lattice area and the meal lattice volume of this food meal lattice;
This analytic unit is also for performing following steps:
According to the depth information of this meal lattice area and this dish kind pattern, calculate a pantry content volume of this pantry content; And
Calculate a ratio of this pantry content volume and this meal lattice volume, this ratio is as the deal of this pantry content.
8. a food quality management detection method, comprising:
Obtain the cutlery box bidimensional image that is filled with the cutlery box of a pantry content, this cutlery box bidimensional image has a pantry content bidimensional image of this pantry content;
Obtain the depth information of a dish kind pattern of this pantry content;
Analyze this cutlery box bidimensional image, with a kind of this cutlery box of identification;
Analyze this pantry content bidimensional image, to obtain a textural characteristics and a color character of this pantry content bidimensional image;
According to the depth information of this pantry content bidimensional image and this dish kind pattern, calculate a deal of this pantry content; And
According to this textural characteristics and this color character, analyze a kind pattern of this pantry content.
9. food quality management detection method as claimed in claim 8, also comprises:
Judge whether this kind pattern and this deal of this pantry content meet a food specification;
If this kind pattern of this pantry content and this deal do not meet this food specification, export an alarm signal; And
If this kind pattern of this pantry content and this deal meet this food specification, export a qualifying signal.
10. food quality management detection method as claimed in claim 8, also comprises:
This cutlery box bidimensional image of comparison and multiple cutlery box characteristic image, to pick out this cutlery box characteristic image belonging to this cutlery box.
11. food quality management detection methods as claimed in claim 10, wherein this cutlery box has a hypotenuse; This food quality management detection method also comprises:
Analyze this cutlery box bidimensional image, to pick out this hypotenuse; And
The characteristic image of this hypotenuse of comparison and these cutlery boxs, to pick out this cutlery box characteristic image with this hypotenuse.
12. food quality management detection methods as claimed in claim 8, also comprise:
Analyze this cutlery box bidimensional image, to judge an attitude of this cutlery box; And
According to this attitude, obtain this pantry content bidimensional image of this cutlery box bidimensional image and of a cutlery box characteristic image and to eat the corresponding relation in lattice region.
13. food quality management detection methods as claimed in claim 12, wherein this cutlery box characteristic image has this meal lattice region multiple, and this cutlery box bidimensional image has this pantry content bidimensional image multiple, and this cutlery box has a broken line; This food quality management detection method also comprises:
Analyze this cutlery box bidimensional image, to pick out an angle of inclination of this broken line; And
According to the size difference of this angle of inclination and this cutlery box bidimensional image and this cutlery box characteristic image, this cutlery box bidimensional image and this cutlery box characteristic image are matched on contour feature, with the corresponding relation in the meal lattice region of the pantry content bidimensional image and this cutlery box characteristic image that obtain this cutlery box bidimensional image.
14. food quality management detection methods as claimed in claim 8, also comprise:
The depth information of foundation one meal lattice area and this dish kind pattern, calculates a pantry content volume of this pantry content; And
Calculate a ratio of this pantry content volume and this meal lattice volume, this ratio is as the deal of this pantry content.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US201462028806P | 2014-07-25 | 2014-07-25 | |
| US62/028,806 | 2014-07-25 | ||
| TW103143666A TWI569011B (en) | 2014-07-25 | 2014-12-15 | Inspection module for meal quality and inspection method for meal quality using the same |
| TW103143666 | 2014-12-15 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105320955A true CN105320955A (en) | 2016-02-10 |
Family
ID=55248309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410826078.9A Pending CN105320955A (en) | 2014-07-25 | 2014-12-26 | Meal quality management detection module and meal quality management detection method applying same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105320955A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543687A (en) * | 2018-11-13 | 2019-03-29 | 南京赤狐智能科技有限公司 | A kind of assembly line mess-tin automatic identifying method |
| JP2021503147A (en) * | 2017-11-14 | 2021-02-04 | キム, デ フンKIM, Dae Hoon | School lunch management system and its operation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040181302A1 (en) * | 2002-01-03 | 2004-09-16 | Fmc Technologies, Inc. | Method of removing food product defects from a food product slurry |
| CN101477729A (en) * | 2008-12-30 | 2009-07-08 | 于忠清 | Self-help meal sale system and information processing method of the system |
| CN102326187A (en) * | 2008-12-23 | 2012-01-18 | 数据逻辑扫描公司 | Method and system for identifying and tallying objects |
| CN102982310A (en) * | 2011-09-05 | 2013-03-20 | 索尼公司 | Information processor, information processing method, and program |
| CN103034839A (en) * | 2012-12-04 | 2013-04-10 | 南京航空航天大学 | Canteen payment system and method based on image recognition technology |
-
2014
- 2014-12-26 CN CN201410826078.9A patent/CN105320955A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040181302A1 (en) * | 2002-01-03 | 2004-09-16 | Fmc Technologies, Inc. | Method of removing food product defects from a food product slurry |
| CN102326187A (en) * | 2008-12-23 | 2012-01-18 | 数据逻辑扫描公司 | Method and system for identifying and tallying objects |
| CN101477729A (en) * | 2008-12-30 | 2009-07-08 | 于忠清 | Self-help meal sale system and information processing method of the system |
| CN102982310A (en) * | 2011-09-05 | 2013-03-20 | 索尼公司 | Information processor, information processing method, and program |
| CN103034839A (en) * | 2012-12-04 | 2013-04-10 | 南京航空航天大学 | Canteen payment system and method based on image recognition technology |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2021503147A (en) * | 2017-11-14 | 2021-02-04 | キム, デ フンKIM, Dae Hoon | School lunch management system and its operation method |
| JP7159331B2 (en) | 2017-11-14 | 2022-10-24 | フン キム，デ | School lunch management system and its operation method |
| US11562817B2 (en) | 2017-11-14 | 2023-01-24 | Nuvi Labs Co., Ltd. | Meal service management system and operating method therefor |
| CN109543687A (en) * | 2018-11-13 | 2019-03-29 | 南京赤狐智能科技有限公司 | A kind of assembly line mess-tin automatic identifying method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2672389C1 (en) | System of follow-up inspection of orders | |
| Oo et al. | A simple and efficient method for automatic strawberry shape and size estimation and classification | |
| Nguyen et al. | Apple detection algorithm for robotic harvesting using a RGB-D camera | |
| CN109844807A (en) | For the mthods, systems and devices of size to be split and determined to object | |
| EP3459033A1 (en) | Method for automatically generating a planogram that assigns products to shelving structures within a store | |
| CN114127805A (en) | Deep network training method | |
| CN102982332A (en) | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method | |
| CN107609483B (en) | Dangerous target detection method and device for driving assistance system | |
| CN105389581B (en) | A kind of rice germ plumule integrity degree intelligent identifying system and its recognition methods | |
| CN104772289A (en) | Target product detection system, detection method thereof, and target product processing system | |
| CN103150631A (en) | Image-matching-based automatic article management method and system | |
| CN109034694B (en) | Production raw material intelligent storage method and system based on intelligent manufacturing | |
| CN112329587A (en) | Beverage bottle classification method and device and electronic equipment | |
| Chen et al. | A practical solution for ripe tomato recognition and localisation | |
| CN105320955A (en) | Meal quality management detection module and meal quality management detection method applying same | |
| CN106887006A (en) | The recognition methods of stacked objects, equipment and machine sort system | |
| Yoshida et al. | A tomato recognition method for harvesting with robots using point clouds | |
| CN115752683A (en) | Weight estimation method, system and terminal based on depth camera | |
| JP2021012692A (en) | Object identification method, system, and electronic apparatus | |
| CN109743497B (en) | Data set acquisition method and system and electronic device | |
| CN109215075A (en) | The positioning identification system and method for workpiece in the crawl of industrial robot material | |
| Zhao et al. | Automatic sweet pepper detection based on point cloud images using subtractive clustering | |
| CN113033286A (en) | Method and device for identifying commodities in container | |
| CN116087195B (en) | Fish freshness evaluation method and system | |
| JP7125929B2 (en) | nutrition calculator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160210 |
|
| WD01 | Invention patent application deemed withdrawn after publication |