Cow face detection and cow face key point positioning method based on convolutional neural network
The invention discloses a cow face detection and cow face key point positioning method based on a convolutional neural network, and the method comprises the following steps: S1, collecting cow pictures of a cow farm, and constructing a cow image data set; s2, manually marking the dairy cow pictures...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a cow face detection and cow face key point positioning method based on a convolutional neural network, and the method comprises the following steps: S1, collecting cow pictures of a cow farm, and constructing a cow image data set; s2, manually marking the dairy cow pictures in the image data set by adopting LabelMe software, and marking face detection frames and key point information on the dairy cow pictures; s3, performing data transformation and enhancement on the labeled dairy cow image data set, and dividing the data set subjected to data transformation and enhancement into a training set and a test set; s4, constructing a convolutional neural network, inputting the training set data obtained in the step S3 into the constructed convolutional neural network for training, and obtaining a cattle face detection and key point recognition model; and S5, inputting the test set data obtained in the step S3 into the trained recognition model, and outputting a cattle face detection frame a |
---|