CN115660477A - Mutton quality evaluation method and system based on multiple evaluation indexes - Google Patents
Mutton quality evaluation method and system based on multiple evaluation indexes Download PDFInfo
- Publication number
- CN115660477A CN115660477A CN202211307167.3A CN202211307167A CN115660477A CN 115660477 A CN115660477 A CN 115660477A CN 202211307167 A CN202211307167 A CN 202211307167A CN 115660477 A CN115660477 A CN 115660477A
- Authority
- CN
- China
- Prior art keywords
- mutton
- information
- video information
- key frame
- preset
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a mutton quality evaluation method and a mutton quality evaluation system based on multiple evaluation indexes, which relate to the technical field of food evaluation and comprise the steps of obtaining video information of slaughtered sheep, mutton processing video information and vibration signal information received by knocking the teeth of sheep; extracting key frame images from all the video information, and performing anomaly detection based on the extracted key frame images to obtain video information corresponding to the key frame images which are judged to be normal; then, carrying out image recognition on video information corresponding to the normal key frame image to obtain texture features and color features of a mutton color image in the video information; and determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and evaluating the quality of mutton based on the texture characteristics, the color characteristics and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the quality information of the mutton.
Description
Technical Field
The invention relates to the technical field of food evaluation, in particular to a mutton quality evaluation method and system based on multiple evaluation indexes.
Background
Nowadays, with the improvement of the quality of life level, the requirements of people on the quality of food materials are higher and higher. For mutton, a certain mutton quality grade standard exists, but mutton is graded differently by different people, and mutton quality evaluation indexes are different. The simple method for manually evaluating the mutton quality hardly avoids individual subjective influence, the evaluation result is different from person to person, is not uniform, is not objective and is not scientific, a large amount of manpower and material resources are wasted, and the requirement on accuracy cannot be met. There is a need for a method and system for evaluating mutton quality from multiple indexes to reduce the subjectivity of mutton quality evaluation and improve the evaluation efficiency and accuracy.
Disclosure of Invention
The invention aims to provide a mutton quality evaluation method and system based on multiple evaluation indexes so as to improve the problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
on the one hand, the application provides a mutton quality evaluation method based on multiple evaluation indexes, which comprises the following steps:
acquiring first video information and vibration signal information, wherein the first video information comprises video information of slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information which is received by a detection system when a tooth of a goat is knocked;
extracting key frame images from the first video information, and performing anomaly detection based on the extracted key frame images to obtain second video information, wherein the second video information is the first video information corresponding to the key frame images which are judged to be normal;
carrying out image recognition on the second video information to obtain texture features and color features of a mutton color image in the second video information;
and determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and evaluating the quality of mutton based on the texture characteristics, the color characteristics and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the quality information of the mutton.
On the other hand, this application still provides a mutton quality evaluation system based on multiple evaluation index, includes:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first video information and vibration signal information, the first video information comprises video information of slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information which is received by a detection system after the detection system knocks the teeth of the sheep;
the detection unit is used for extracting key frame images from the first video information and performing abnormity detection on the basis of the extracted key frame images to obtain second video information, wherein the second video information is the first video information corresponding to the key frame images which are judged to be normal;
the identification unit is used for carrying out image identification on the second video information to obtain texture characteristics and color characteristics of a mutton color image in the second video information;
and the evaluation unit is used for determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and evaluating the mutton quality based on the texture feature, the color feature and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the mutton quality information.
The beneficial effects of the invention are as follows:
the method comprises the steps of identifying and judging video information of slaughtered sheep and mutton processing video information shot on a mutton production line, judging whether key steps of the slaughtered sheep and the mutton processing key steps are accurate, carrying out feature identification on accurate video information, determining texture features and color features of mutton, judging the physiological maturity of the sheep based on the teeth of the sheep, and further rapidly determining the mutton quality from three evaluation indexes.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a mutton quality evaluation method based on multiple evaluation indexes in the embodiment of the invention;
fig. 2 is a table of preset mutton quality evaluations in the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a mutton quality evaluation system based on multiple evaluation indexes in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a mutton quality evaluation method based on multiple evaluation indexes.
Referring to fig. 1, it is shown that the method comprises step S1, step S2, step S3 and step S4.
S1, acquiring first video information and vibration signal information, wherein the first video information comprises video information of slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information which is received by a detection system when a goat tooth is knocked;
it can be understood that this step is through carrying out the video recording to slaughtering flow and the process flow on the mutton production line of mill, when preventing to appear unexpected, also judge the slaughtering flow and the process flow of mutton, because the slaughtering flow and the process flow of mutton also belong to a part of mutton quality rating, for example the process of deacidification, if the time of deacidification can not reach the requirement or temperature environment is unsatisfactory, the flavor of mutton can not be improved, the quality will descend, and this step gathers and judges whether the age of sheep meets the requirements through judging based on the sheep tooth, can judge whether qualified through these indexes like this.
S2, extracting key frame images from the first video information, and performing anomaly detection based on the extracted key frame images to obtain second video information, wherein the second video information is the first video information corresponding to the key frame images which are judged to be normal;
it can be understood that the step judges which mutton is qualified processed mutton by judging whether the slaughtering process of sheep and the processing process of mutton are qualified. In this step, step S2 includes step S21, step S22, step S23, and step S24.
S21, comparing a preset key frame image in the first video information to obtain the key frame image, wherein the key frame image is an image containing slaughtering action and processing action, and the key frame image is image information containing the key frame image;
it can be understood that the step is performed by comparing a preset key frame image with the first video information, wherein the key frame image may be a historical slaughter action image or a historical processing action image, and comparing the preset key frame image with the first video information to determine the frame image containing the action in the first video information, thereby determining the operation flow sequence and steps of the worker.
S22, sequentially extracting video contents in a preset time period before and after the key frame image to obtain at least two video clips;
it is understood that the preset time period in this step is preferably a time period including 5 seconds before and after the key frame image, so that whether the action operates correctly can be completely judged.
S23, marking each video clip, and sequencing the marked videos according to the acquisition time to obtain sequenced video clips;
and S24, traversing the sequenced video clips, judging whether the sequenced video clips are the same as a preset processing flow video clip sequence, if not, marking the first video information and the key frame images corresponding to the sequenced video clips as abnormal, and if so, marking the first video information and the key frame images corresponding to the sequenced video clips as normal.
It will be appreciated that this step determines whether the worker's operational flow meets operational specifications by sequencing each video clip. If the operation flow does not meet the specification, judging that the mutton produced by the operation flow is unqualified, and marking the mutton quality as abnormal; and if the operation flow conforms to the regulations, marking the quality of the mutton as normal, and sending the first video information corresponding to the mutton marked as normal to the subsequent processing steps to prepare for the subsequent rating.
S3, carrying out image recognition on the second video information to obtain texture features and color features of the mutton color image in the second video information;
it will be appreciated that this step provides a basis for rating by processing the second video information to obtain image features within the second video information. In this step, step S3 includes step S31, step S32, step S33, and step S34.
S31, performing image recognition on the second video information, and extracting each frame of image containing a mutton image to obtain at least two frames of mutton color images;
it can be understood that in this step, the images in the second video information are subjected to mutton identification, and the images containing mutton are all extracted, so as to obtain all color images containing mutton.
Step S32, carrying out gray level conversion on all mutton color images to obtain gray level images corresponding to the mutton color images, and connecting pixel points with the same gray level value in the gray level images, wherein a linear interpolation method is adopted to carry out interpolation processing on the connecting lines to obtain mutton texture images in the mutton color images;
it can be understood that the step rapidly determines the texture of the mutton by performing texture extraction on the mutton color image, and provides for judging the quality of the mutton later. According to the step, the texture image is extracted, manual judgment is reduced, and errors are reduced.
S33, carrying out edge detection on the mutton color image to obtain a mutton contour edge in the mutton color image, and converting an image outside the mutton contour edge into white;
and S34, respectively clustering the R, G, B three components of all pixel points in the mutton outline edge, carrying out average calculation on the central points of all the obtained cluster clusters to obtain the average value of the central points of all the cluster clusters, and taking the average value as the color characteristic of the mutton color image.
It can be understood that the step converts all backgrounds except mutton into white by detecting the mutton contour edge, wherein the backgrounds can also be converted into other colors in the invention to prevent errors in extracting the color characteristics of the mutton color image. This step is still through clustering to all pixel points in the mutton profile edge, confirms the central point of the cluster of clustering of all pixel points fast, then regards the average value of all central points as the color characteristic of mutton color image, can judge the tender degree of mutton to different color characteristics like this, evaluates the quality of mutton.
And S4, determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and evaluating the quality of the mutton based on the texture characteristics, the color characteristics and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the quality information of the mutton.
It can be understood that in the step, whether the sheep is at the best slaughter age is judged by judging the physiological maturity of the sheep based on the vibration signal information, the quality of the sheep of different ages is determined based on the slaughter ages of different sheep, and then the mutton quality of different sheep is evaluated. In this step, step S4 includes step S41, step S42, and step S43.
S41, fitting the vibration signal information by adopting a least square method to obtain each order of harmonic amplitude signal and each order of harmonic phase signal in an initial state and any vibration time;
step S42, calculating the amplitude difference between the harmonic amplitude signal in the initial state and each order of harmonic amplitude signal in each vibration time based on a preset amplitude difference calculation formula, and calculating the phase difference between the harmonic phase signal in the initial state and each order of harmonic phase signal in each vibration time based on a preset phase difference calculation formula;
and S43, comparing the amplitude difference and the phase difference with preset threshold values respectively, and judging the physiological maturity of the sheep corresponding to the vibration signal based on the comparison result.
It can be understood that the harmonic amplitude signal and the phase signal of the teeth of the sheep before knocking are determined by fitting the vibration signals, the harmonic amplitude signal and the phase signal of the teeth of the sheep at each time period after knocking are determined, the age of the sheep is determined based on the phase difference before and after knocking, wherein the preset threshold is the phase difference calculated by knocking the teeth of the sheep with different physiological maturity through history, and the threshold is determined according to the phase difference range. Therefore, the physiological maturity of the sheep can be directly judged only by judging the relation with the threshold value in the step.
The preset amplitude difference calculation formula in the step is shown as follows;
wherein, delta α Is the amplitude difference, T is an arbitrary time,
is an amplitude signal of each harmonic in the initial state, alpha n (t) is the harmonic amplitude of each order within any vibration timeA value signal.
The phase difference calculation formula preset in this step is as follows;
wherein, delta β For the phase difference, T is an arbitrary time,
is a phase signal of each harmonic in an initial state, beta n And (t) is a harmonic phase signal of each order in any vibration time.
It is understood that in this step, step S4 further includes step S44, step S45 and step S46.
S44, performing mean value calculation on all pixel points contained in the preset historical texture features, performing initialization processing on the average value of the pixel points of the historical texture features obtained through the mean value calculation, the preset historical color features and the physiological maturity of the sheep corresponding to the preset historical vibration signal information, and calculating the fitness of the particles in each particle swarm based on a preset fitness function to obtain the individual optimal position and the global optimal position of the particles;
step S45, continuously updating the speed and the position of all particles based on a particle updating speed formula and a particle updating position formula in the particle swarm optimization algorithm until the particle swarm optimization algorithm reaches a preset iteration number to obtain parameter information after iteration, wherein the parameter information comprises a pixel point average value of historical texture characteristics, preset historical color characteristics and physiological maturity of the sheep corresponding to preset historical vibration signal information;
in the step, the optimal average value of the pixel points of the historical texture features, the optimal historical color features and the optimal physiological maturity are selected through a particle swarm optimization algorithm, so that preparation is made for later mutton quality evaluation, wherein fitness functions are as follows:
wherein, ET 1 For the actual value of the a-th history parameter information, ET 2 The parameter information is an average value of preset historical parameter information, and N is the total quantity of the parameter information.
It can be understood that this step updates its location by two formulas:
V a+1 ＝V a ×ω+c 1 ×rand(0，1)×(pbest a -x a )+c 2 ×rand(0，1)×(gbest a -x a )
wherein, V a+1 For updated speed, V a As the current speed, c 1 And c 2 In order to learn the factors, the learning device is provided with a plurality of learning units,
typically 2,x is taken a Is the current position of the particle, a is the total number of particles, rand (0,1) is a random number between 0 and 1, pbest a For the best position found by the present particles so far, gbest a ω is the inertial factor for the best position found by all particles to the current position.
x a ＝x a-1 +v a-1
Wherein x is a For updated positions of particles, x a-1 Is the position of the particle before update, v a-1 The position before particle update.
And S46, comparing the physiological maturity of the sheep corresponding to the texture feature, the color feature and the vibration signal information with the parameter information respectively, and comparing the comparison result with a preset mutton quality evaluation table to obtain mutton quality information in the first video information.
It can be understood that in the step, after the optimal parameter information is obtained through calculation, the physiological maturity of the sheep corresponding to the texture feature, the color feature and the vibration signal information obtained through calculation is divided by the optimal parameter information obtained through calculation to obtain corresponding ratios, and the corresponding ratios are compared with a preset mutton quality evaluation table to determine the corresponding mutton quality grades under each ratio.
Example 2:
as shown in fig. 3, the present embodiment provides a mutton quality evaluation system based on multiple evaluation indexes, which includes an acquisition unit 701, a detection unit 702, a recognition unit 703 and an evaluation unit 704.
The acquiring unit 701 is configured to acquire first video information and vibration signal information, where the first video information includes video information of a slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information that a detection system knocks a tooth of a goat and is received;
a detecting unit 702, configured to extract a key frame image from the first video information, and perform anomaly detection based on the extracted key frame image to obtain second video information, where the second video information is first video information corresponding to the key frame image that is determined to be normal;
the identifying unit 703 is configured to perform image identification on the second video information to obtain texture features and color features of a mutton color image in the second video information;
and the evaluation unit 704 is configured to determine the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and perform mutton quality evaluation based on the texture feature, the color feature and the physiological maturity of the sheep corresponding to the vibration signal information to obtain mutton quality information.
In a specific embodiment of the present disclosure, the detecting unit 702 includes a first processing subunit 7021, a second processing subunit 7022, a first marking subunit 7023, and a second marking subunit 7024.
A first processing subunit 7021, configured to compare a preset key frame image in the first video information to obtain the key frame image, where the key frame image is an image including a slaughter action and a processing action, and the key frame image is image information including the key frame image;
a second processing subunit 7022, configured to sequentially extract video contents in a preset time period before and after the key frame image, so as to obtain at least two video segments;
the first marking subunit 7023 is configured to mark each video segment, and sort the marked videos according to the acquisition time to obtain sorted video segments;
a second marking subunit 7024, configured to traverse the sorted video segments, determine whether the sorted video segments are the same as a preset sequence of the process flow video segments, mark, if the sorted video segments are different, the first video information and the key frame image corresponding to the sorted video segments as abnormal, and mark, if the sorted video segments are the same, the first video information and the key frame image corresponding to the sorted video segments as normal.
In a specific embodiment of the present disclosure, the identifying unit 703 includes a third processing subunit 7031, a fourth processing subunit 7032, a fifth processing subunit 7033, and a sixth processing subunit 7034.
A third processing subunit 7031, configured to perform image recognition on the second video information, and extract each frame of image including a mutton image to obtain at least two frames of mutton color images;
a fourth processing subunit 7032, configured to perform gray-scale conversion on all the mutton color images to obtain gray-scale images corresponding to the mutton color images, and connect pixel points of the same gray-scale value in the gray-scale images, where a linear interpolation method is used to perform interpolation processing on the connected lines to obtain mutton texture images in the mutton color images;
a fifth processing subunit 7033, configured to perform edge detection on the mutton color image to obtain a mutton contour edge in the mutton color image, and convert an image outside the mutton contour edge into white;
a sixth processing subunit 7034, configured to perform clustering on the R, G, B three components of all pixel points in the edge of the mutton profile, perform average calculation on the center points of all obtained clusters, obtain an average value of the center points of all clusters, and use the average value as the color feature of the mutton color image.
In a specific embodiment of the present disclosure, the evaluation unit 704 includes a seventh processing subunit 7041, a first calculating subunit 7042, and a first comparing subunit 7043.
A seventh processing subunit 7041, configured to fit the vibration signal information by using a least square method to obtain an amplitude signal of each order of harmonic and a phase signal of each order of harmonic in an initial state and in any vibration time;
a first calculating subunit 7042, configured to calculate an amplitude difference between the harmonic amplitude signal in the initial state and each order of harmonic amplitude signal in each vibration time based on a preset amplitude difference calculation formula, and calculate a phase difference between the harmonic phase signal in the initial state and each order of harmonic phase signal in each vibration time based on a preset phase difference calculation formula;
the first comparison subunit 7043 is configured to compare the amplitude difference and the phase difference with preset thresholds, respectively, and determine, based on the comparison result, the physiological maturity of the sheep corresponding to the vibration signal.
In a specific embodiment of the present disclosure, the evaluation unit 704 further includes a second calculation subunit 7044, a third calculation subunit 7045, and a second comparison subunit 7046.
A second calculating subunit 7044, configured to perform mean value calculation on all pixel points included in the preset historical texture feature, perform initialization processing on the average value of the pixel points of the historical texture feature obtained by the mean value calculation, the preset historical color feature, and the physiological maturity of the sheep corresponding to the preset historical vibration signal information, and calculate the fitness of the particles in each particle swarm based on a preset fitness function, so as to obtain an individual optimal position and a global optimal position of the particles;
a third computing subunit 7045, configured to continuously update the speed and the position of all the particles based on a particle update speed formula and a particle update position formula in the particle swarm optimization algorithm until the particle swarm optimization algorithm reaches a preset iteration number, so as to obtain parameter information after iteration, where the parameter information includes a pixel point average value of a historical texture feature, a preset historical color feature, and a physiological maturity of the sheep corresponding to preset historical vibration signal information;
and the second comparing subunit 7046 is configured to compare the physiological maturity of the sheep corresponding to the texture feature, the color feature, and the vibration signal information with the parameter information, and compare the comparison result with a preset mutton quality evaluation table to obtain mutton quality information in the first video information.
It should be noted that, with regard to the system in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A mutton quality evaluation method based on multiple evaluation indexes is characterized by comprising the following steps:
acquiring first video information and vibration signal information, wherein the first video information comprises video information of slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information which is received by a detection system when a tooth of a goat is knocked;
extracting key frame images from the first video information, and performing anomaly detection based on the extracted key frame images to obtain second video information, wherein the second video information is the first video information corresponding to the key frame images which are judged to be normal;
carrying out image recognition on the second video information to obtain texture features and color features of a mutton color image in the second video information;
and determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and evaluating the quality of mutton based on the texture characteristics, the color characteristics and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the quality information of the mutton.
2. The mutton quality evaluation method based on multiple evaluation indexes according to claim 1, wherein the steps of extracting key frame images from the first video information and performing anomaly detection based on the extracted key frame images comprise:
comparing preset key frame images in the first video information to obtain the key frame images, wherein the key frame images are images containing slaughtering actions and processing actions, and the key frame images are image information containing the key frame images;
sequentially extracting video contents in a preset time period before and after the key frame image to obtain at least two video clips;
marking each video clip, and sequencing the marked videos according to the acquisition time to obtain sequenced video clips;
traversing the sequenced video clips, judging whether the sequenced video clips are the same as a preset processing flow video clip sequence, if not, marking the first video information and the key frame image corresponding to the sequenced video clips as abnormal, and if so, marking the first video information and the key frame image corresponding to the sequenced video clips as normal.
3. The mutton quality evaluation method based on multiple evaluation indexes according to claim 1, wherein the image recognition of the second video information is performed to obtain the texture feature and the color feature of the mutton color image in the second video information, and the method comprises the following steps:
carrying out image recognition on the second video information, and extracting each frame of image containing the mutton image to obtain at least two frames of mutton color images;
carrying out gray level conversion on all mutton color images to obtain gray level images corresponding to the mutton color images, and connecting pixel points with the same gray level value in the gray level images, wherein a linear interpolation method is adopted to carry out interpolation processing on the connecting lines to obtain mutton texture images in the mutton color images;
carrying out edge detection on the mutton color image to obtain a mutton contour edge in the mutton color image, and converting an image outside the mutton contour edge into white;
and respectively clustering the R, G, B three components of all pixel points in the mutton profile edge, carrying out average calculation on the central points of all the obtained cluster clusters to obtain the average value of the central points of all the cluster clusters, and taking the average value as the color characteristic of the mutton color image.
4. The mutton quality evaluation method based on multiple evaluation indexes according to claim 1, wherein the step of determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information comprises the following steps:
fitting the vibration signal information by adopting a least square method to obtain each order of harmonic amplitude signal and each order of harmonic phase signal in an initial state and any vibration time;
calculating the amplitude difference between the harmonic amplitude signal in the initial state and each order of harmonic amplitude signal in each vibration time based on a preset amplitude difference calculation formula, and calculating the phase difference between the harmonic phase signal in the initial state and each order of harmonic phase signal in each vibration time based on a preset phase difference calculation formula;
and comparing the amplitude difference and the phase difference with preset threshold values respectively, and judging the physiological maturity of the sheep corresponding to the vibration signal based on the comparison result.
5. The mutton quality evaluation method based on multiple evaluation indexes according to claim 1, wherein the mutton quality evaluation is performed based on the texture feature, the color feature and the physiological maturity of sheep corresponding to the vibration signal information to obtain mutton quality information, and the method comprises the following steps:
carrying out mean value calculation on all pixel points contained in the preset historical textural features, carrying out initialization processing on the average value of the pixel points of the historical textural features obtained by the mean value calculation, the preset historical color features and the physiological maturity of the sheep corresponding to the preset historical vibration signal information, and calculating the fitness of the particles in each particle swarm based on a preset fitness function to obtain the individual optimal position and the global optimal position of the particles;
continuously updating the speed and the position of all particles based on a particle updating speed formula and a particle updating position formula in a particle swarm optimization algorithm until the particle swarm optimization algorithm reaches a preset iteration number to obtain parameter information after iteration, wherein the parameter information comprises a pixel point average value of historical texture characteristics, a preset historical color characteristic and a physiological maturity of the sheep corresponding to preset historical vibration signal information;
and comparing the physiological maturity of the sheep corresponding to the texture characteristic, the color characteristic and the vibration signal information with the parameter information respectively, and comparing the comparison result with a preset mutton quality evaluation table to obtain mutton quality information in the first video information.
6. A mutton quality evaluation system based on multiple evaluation indexes is characterized by comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first video information and vibration signal information, the first video information comprises video information of slaughtered sheep and mutton processing video information, and the vibration signal information is vibration signal information which is received by a detection system when a tooth of a goat is knocked;
the detection unit is used for extracting a key frame image from the first video information and performing abnormity detection based on the extracted key frame image to obtain second video information, wherein the second video information is the first video information corresponding to the key frame image which is judged to be normal;
the identification unit is used for carrying out image identification on the second video information to obtain texture characteristics and color characteristics of a mutton color image in the second video information;
and the evaluation unit is used for determining the physiological maturity of the sheep corresponding to the vibration signal information based on the vibration signal information, and performing mutton quality evaluation based on the texture feature, the color feature and the physiological maturity of the sheep corresponding to the vibration signal information to obtain the mutton quality information.
7. The system for evaluating mutton quality based on multiple evaluation indexes according to claim 6, wherein the system comprises:
the first processing subunit is configured to compare a preset key frame image in the first video information to obtain the key frame image, where the key frame image is an image including slaughter actions and processing actions, and the key frame image is image information including the key frame image;
the second processing subunit is used for sequentially extracting video contents in a preset time period before and after the key frame image to obtain at least two video clips;
the first marking subunit is used for marking each video clip and sequencing the marked videos according to the acquisition time to obtain sequenced video clips;
and the second marking subunit is used for traversing the sequenced video clips, judging whether the sequenced video clips are the same as a preset processing flow video clip sequence, marking the first video information and the key frame images corresponding to the sequenced video clips as abnormal if the sequenced video clips are different from the preset processing flow video clip sequence, and marking the first video information and the key frame images corresponding to the sequenced video clips as normal if the sequenced video clips are the same.
8. The system for evaluating mutton quality based on multiple evaluation indexes according to claim 6, wherein the system comprises:
the third processing subunit is used for carrying out image recognition on the second video information and extracting each frame of image containing the mutton image to obtain at least two frames of mutton color images;
the fourth processing subunit is used for performing gray level conversion on all the mutton color images to obtain gray level images corresponding to the mutton color images, and connecting pixel points with the same gray level value in the gray level images, wherein a linear interpolation method is adopted to perform interpolation processing on the connecting lines to obtain mutton texture images in the mutton color images;
the fifth processing subunit is used for carrying out edge detection on the mutton color image to obtain a mutton contour edge in the mutton color image and converting an image outside the mutton contour edge into white;
and the sixth processing subunit is used for respectively carrying out clustering processing on the R, G, B three components of all pixel points in the mutton profile edge, carrying out average calculation on the central points of all the obtained clustering clusters to obtain an average value of the central points of all the clustering clusters, and taking the average value as the color characteristic of the mutton color image.
9. The system for evaluating mutton quality based on multiple evaluation indexes according to claim 6, wherein the system comprises:
the seventh processing subunit is used for fitting the vibration signal information by adopting a least square method to obtain amplitude signals and phase signals of each order of harmonic in an initial state and any vibration time;
the first calculating subunit is used for calculating the amplitude difference between the harmonic amplitude signal in the initial state and each order of harmonic amplitude signal in each vibration time based on a preset amplitude difference calculating formula, and calculating the phase difference between the harmonic phase signal in the initial state and each order of harmonic phase signal in each vibration time based on a preset phase difference calculating formula;
and the first comparison subunit is used for comparing the amplitude difference and the phase difference with preset threshold values respectively, and judging the physiological maturity of the sheep corresponding to the vibration signal based on the comparison result.
10. The system for evaluating mutton quality based on multiple evaluation indexes according to claim 6, wherein the system comprises:
the second calculation subunit is used for performing mean value calculation on all pixel points contained in the preset historical texture features, performing initialization processing on the average value of the pixel points of the historical texture features obtained through the mean value calculation, the preset historical color features and the physiological maturity of the sheep corresponding to the preset historical vibration signal information, and calculating the fitness of the particles in each particle swarm based on a preset fitness function to obtain the individual optimal position and the global optimal position of the particles;
the third calculation subunit is used for continuously updating the speed and the position of all the particles based on a particle updating speed formula and a particle updating position formula in the particle swarm optimization algorithm until the particle swarm optimization algorithm reaches a preset iteration number to obtain parameter information after iteration, wherein the parameter information comprises a pixel point average value of historical texture characteristics, preset historical color characteristics and physiological maturity of the sheep corresponding to preset historical vibration signal information;
and the second comparison subunit is used for comparing the physiological maturity of the sheep corresponding to the texture features, the color features and the vibration signal information with the parameter information respectively, and comparing the comparison result with a preset mutton quality evaluation table to obtain mutton quality information in the first video information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307167.3A CN115660477A (en) | 2022-10-25 | 2022-10-25 | Mutton quality evaluation method and system based on multiple evaluation indexes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307167.3A CN115660477A (en) | 2022-10-25 | 2022-10-25 | Mutton quality evaluation method and system based on multiple evaluation indexes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660477A true CN115660477A (en) | 2023-01-31 |
Family
ID=84990510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211307167.3A Pending CN115660477A (en) | 2022-10-25 | 2022-10-25 | Mutton quality evaluation method and system based on multiple evaluation indexes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660477A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359142A (en) * | 2023-03-27 | 2023-06-30 | 山东千禧农牧发展有限公司 | Evaluation method for chicken quality |
| CN116503768A (en) * | 2023-06-29 | 2023-07-28 | 中国科学院心理研究所 | Aerial docking method and device for flight equipment |
-
2022
- 2022-10-25 CN CN202211307167.3A patent/CN115660477A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359142A (en) * | 2023-03-27 | 2023-06-30 | 山东千禧农牧发展有限公司 | Evaluation method for chicken quality |
| CN116359142B (en) * | 2023-03-27 | 2024-03-22 | 山东千禧农牧发展有限公司 | Evaluation method for chicken quality |
| CN116503768A (en) * | 2023-06-29 | 2023-07-28 | 中国科学院心理研究所 | Aerial docking method and device for flight equipment |
| CN116503768B (en) * | 2023-06-29 | 2023-11-07 | 中国科学院心理研究所 | Aerial docking method and device for flight equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115660477A (en) | Mutton quality evaluation method and system based on multiple evaluation indexes | |
| CN105138953B (en) | A method of action recognition in the video based on continuous more case-based learnings | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| CN109215010B (en) | Image quality judgment method and robot face recognition system | |
| CN114723704A (en) | Textile quality evaluation method based on image processing | |
| CN111652395A (en) | Health assessment method for high-speed railway contact network equipment | |
| CN105303200B (en) | Face identification method for handheld device | |
| CN113064796B (en) | Unsupervised index abnormality detection method | |
| CN109297534B (en) | Environmental parameter weight determination method and system for evaluating indoor environmental quality | |
| CN107564000A (en) | Hericium erinaceus Non-Destructive Testing stage division based on computer vision | |
| CN111984442A (en) | Method and device for detecting abnormality of computer cluster system, and storage medium | |
| CN108470194B (en) | Feature screening method and device | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN111753794A (en) | Fruit quality classification method and device, electronic equipment and readable storage medium | |
| CN116308300A (en) | Power equipment state monitoring evaluation and command method and system | |
| CN104298993A (en) | Pole number positioning and identification method suitable for railway line in complex scene | |
| TWI591545B (en) | Fingerprint image detecting device and method thereof | |
| AU2013321855B2 (en) | Method for estimating meat marbling | |
| CN105426926B (en) | A kind of couple of AMOLED carries out the method and device of detection classification | |
| US20210019656A1 (en) | Information processing device, information processing method, and computer program | |
| CN112232206B (en) | Face recognition method and face recognition platform based on big data and artificial intelligence | |
| CN106023208B (en) | The method for objectively evaluating of picture quality | |
| CN113160166B (en) | Medical image data mining working method through convolutional neural network model | |
| CN113034403B (en) | Working method for denoising medical image data through Gaussian filtering | |
| CN108764131A (en) | It is a kind of based on video processing adaptive threshold multiple target fall down detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |