Pig identity recognition system

Abstract

The invention relates to a pig identity recognition system which comprises an identity input module, a depth image acquisition module, an image preprocessing module, a feature extraction module and afeature matching recognition module. The identity input module is used for inputting pig face basic information of each pig and establishing a feature database according to the input basic information; the depth image acquisition module is used for continuously acquiring to-be-identified pig face depth image data; the image preprocessing module is used for carrying out image smoothing and filtering processing on the acquired pig face depth image data and intercepting a face area depth image; the feature extraction module is used for performing feature extraction on the intercepted face regiondepth image to obtain face features of the to-be-identified pig; and the image recognition module is used for matching and comparing the extracted facial features with the sample feature data in the feature database to obtain matching similarity and outputting a matching result. The method can be widely applied to the field of pig identity recognition.

Description

technical field [0001] The invention relates to the field of image recognition and software systems, in particular to a pig identity recognition system based on a depth image of a pig face. Background technique [0002] With the development of refined farming, it is more and more important to identify the identity of pigs. It is conducive to the control of epidemic diseases, improving the management level of farms, and it is also convenient for the country to supervise the safety of pork products. At present, the identification of pigs is mainly carried out by giving each pig a different electronic ear tag, and then reading the data of the electronic ear tag according to the RFID card reader to identify the identity of the pig. However, the process of putting electronic ear tags on pigs will inevitably cause stress to the pigs, which violates the requirements of animal welfare, and the electronic ear tags are also easily damaged by other pigs, and the RFID card reader signal...

AI Technical Summary

Problems solved by technology

[0004] However, pigs are different from humans, they will not actively cooperate with the image collection during the recognition process, and the fattening pigs grow rapidly, the model established before may not be applicable as the pigs grow; pig faces are also different from human faces, human faces, eyes, noses The mouth and mouth are almost on the same plane, so it is easy to obtain a full-face image from the front, while the pig's face organs are distributed in three-dimensional space, it is difficult to take a full picture of the pig's face from a fixed angle; at the same time, the pig's face is often stained with feces, feed and impact identification

Images