Image-data-based classification of vacuum seal packages

1. A system comprising:

a transportation system configured to transport vacuum seal packages, wherein each of the vacuum seal packages includes a food product;

an image sensor system including an image data capture system, wherein the image data capture system is arranged to capture image data of individual vacuum seal packages as the vacuum seal packages are transported by the transportation system; and

one or more computing devices communicatively coupled to the image sensor system and configured to receive the image data from the image sensor system;

wherein the one or more computing devices include instructions that, in response to execution of the instructions by the one or more computing devices, cause the one or more computing devices to:

classify a state of one or more of the vacuum seal packages based on the image data using a trained classification model, wherein the state of one or more of the vacuum seal packages includes an indication of whether the food product is fully enclosed in a generally air-free environment in one of the one or more of the vacuum seal packages, and

output the state of the one or more of the vacuum seal packages after classification of the state of the one or more of the vacuum seal packages.

2. The system of claim 1 , wherein the trained classification model includes a decision-making process configured to receive an input that includes the image data and to output an output that includes the state of the one or more of the vacuum seal packages.

3. The system of claim 2 , wherein the decision-making process is a multilayer neural network, wherein the multilayer neural network includes an input layer comprising the input, an output layer comprising the output, and at least one hidden layer between the input layer and the output layer.

4. The system of claim 1 , wherein the image sensor system further comprises a presence detector system configured to detect one of the vacuum seal packages on the transport system.

5. The system of claim 4 , wherein:

the image sensor system further comprises a controller;

the controller is configured to receive a signal from the presence detector system indicating the detected one of the vacuum seal packages; and

the controller is further configured to control a timing of the image sensor system during at least a portion of a time that the image sensor system obtains the image data of the detected one of the vacuum seal packages.

6. The system of claim 5 , wherein the transportation system comprises a conveyor belt, and wherein the controller is further configured to control the timing of the image sensor system based in part on a speed of the conveyor belt.

7. The system of claim 1 , wherein the classified state of the one or more of the vacuum seal packages includes an indication of whether the one or more of the vacuum seal packages is defective, is non-defective, or has a particular defect.

8. The system of claim 7 , wherein the classified state of the one or more of the vacuum seal packages further includes a degree of certainty as to whether the vacuum seal package is defective, is non-defective, or has a particular defect.

9. The system of claim 1 , wherein the one or more computing devices are configured to output the state of the one or more of the vacuum seal packages via by at least one of providing an indication of the state to a user interface output device, communicating the state via a communication interface to an external device, or storing the state in a local database.

10. A computer-readable medium having instructions embodied thereon, wherein the computer-readable medium is a non-transitory computer-readable medium, and wherein the instructions comprise instructions that, in response to execution by one or more computing devices, cause the one or more computing devices to:

receive training image data, the training image data comprising image data about a plurality of first vacuum seal packages;

receive labels associated with the plurality of first vacuum seal packages, wherein each of the labels includes a state of one of the plurality of first vacuum seal packages;

develop a trained classification model based on the training image data and the received labels;

receive image data representative of a second vacuum seal package;

input the image data into the trained classification model, wherein the trained classification model is configured to classify a state of the second vacuum seal package based on the image data, wherein the state of the second vacuum seal package includes an indication of whether the food product is fully enclosed in a generally air-free environment in the second vacuum seal package; and

receive the state of the second vacuum seal package from the trained classification model.

11. The computer-readable medium of claim 10 , wherein the state of the second vacuum seal package includes an indication of whether the second vacuum seal package is defective, is non-defective, or has a particular defect.

12. The computer-readable medium of claim 11 , wherein the state of the second vacuum seal package further includes a degree of certainty as to whether the second vacuum seal package is defective, is non-defective, or has a particular defect.

13. The computer-readable medium of claim 12 , wherein the instructions further comprise instructions that, in response to execution by the one or more computing devices, further cause the one or more computing devices to:

determine, based on the degree of certainty, whether a confidence level of the state of the second vacuum seal package is low; and

in response to determining that the confidence level of the state of the second vacuum seal package is low, flag the second vacuum seal package for manual classification.

14. The computer-readable medium of claim 13 , wherein the instructions further comprise instructions that, in response to execution by the one or more computing devices, further cause the one or more computing devices to:

receive a user input of a manual classification of the second vacuum seal package; and

further develop the trained classification model based on the image data and the manual classification of the second vacuum seal package.

15. The computer-readable medium of claim 10 , wherein the trained classification model includes a detection decision-making process and a classification decision-making process.

16. The computer-readable medium of claim 15 , wherein the detection decision-making process is configured to process the image data to produce processed image data.

17. The computer-readable medium of claim 16 , wherein the detection decision-making process is configured to perform at least one of:

process the image data to produce processed image data at least by cropping an image in the image data so that the second vacuum seal package remains in the cropped image;

detect a presence of the second vacuum seal package in the image data; or

classify the state of the second vacuum seal package based on the processed image data.

18. The computer-readable medium of claim 10 , wherein the instruction that cause the one or more computing devices to develop a trained classification model include instructions that, in response to execution by the one or more computing devices, cause the one or more computing devices to:

train the classification model for a plurality of learning parameters; and

determine one or more model parameters based on the plurality of learning parameters.

19. The computer-readable medium of claim 18 , wherein the instruction that cause the one or more computing devices to develop a trained classification model further include instructions that, in response to execution by the one or more computing devices, cause the one or more computing devices to:

create the trained classification model based on the one or more model parameters.

20. The computer-readable medium of claim 10 , wherein:

the image data representative of the second vacuum seal package includes a plurality of forms of image data;

the plurality of forms of image data includes at least two images of the second vacuum seal package; and

the trained classification model is configured to classify the state of the second vacuum seal package based on the image data in part by separately classifying a state of each of the at least two images of the second vacuum seal package.