A method for identifying individual animals, and a computer program for doing so.
The method uses deep distance learning to identify animals from back images, overcoming the challenge of high-resolution facial image requirements, ensuring accurate and efficient individual identification with confidence-based data management.
JP2026141822APending Publication Date: 2026-09-07SEIKO EPSON CORP
1 Cites 0 Cited by
Patent Information
- Application Number
- JP2025028504
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-26
- Publication Date
- 2026-09-07
AI Technical Summary
Technical Problem
Conventional animal identification techniques require high-resolution facial images, which are difficult to obtain, especially for continuously moving animals like cattle, limiting their effectiveness for individual identification.
Method used
A method using a deep distance learning model to extract embedding vectors from images of an animal's back, calculating distances between these vectors and registered embedding vectors to identify individuals, with confidence thresholds for accurate identification and data management.
Benefits of technology
Enables reliable individual animal identification using back images, reducing misrecognition due to dirt or movement, and enhances registration data reliability through confidence-based vector addition and data pruning.
✦ Generated by Eureka AI based on patent content.
Abstract
This technology provides a method for individual identification using features other than nose prints. [Solution] The disclosed method includes: (a) acquiring a target image relating to the back of the animal to be identified; (b) obtaining an embedding vector from the target image using a deep distance learning model; (c) calculating the distance between the registered embedding vectors using registration data that includes pre-generated registration embedding vectors for each of a plurality of registered individuals; (d) determining whether the animal to be identified is one of the multiple registered individuals that is a judgment registered individual, using the distance; and (e) adding the embedding vector relating to the animal to be identified to the registration data if the confidence level of the determination determined according to the distance is equal to or greater than a confidence threshold.
Need to check novelty before this filing date? Find Prior Art