Technology2022년 09월 07일 2023-02-24 23:06
Automated Extraction & Recognition Technology of Pets Biometrics Information
Real-time detection and classification of pets
Various objects are scanned altogether while recording with a smartphone camera. While scanning dogs and cats, other animals or your family may be included.
Our in-house developed object detection technology can precisely seek and classify your pet. Currently, only dogs and cats can be recognized for registration.
Automated camera control
Based on data acquisition experience of biometric information,
Petnow has implemented the most optimal automated
camera control technology.
Our app automatically focuses on a dog's nose or cat’s face,
controls the camera with brightness and quality assessment
result accordingly for obtaining higher quality images.
Improvement of recognition performance
with AI-based quality assessment
Not all data is perfect, and the same goes for pet identification data. Blurry or dark images can affect the accuracy of pet identification, especially when pets tend to move continuously.
We utilize our proprietary machine learning technology to quickly assess the quality of a photographed nose print or face.
If the quality is insufficient, our technology automatically retries the acquisition process to obtain higher quality images. This allows us to provide more accurate pet identification and help protect pets and their owners.
Minimalization of user effort
Once our app's camera detects a pet, it is automatically categorized and the quality of their biometric information (nose print/face) is inspected. Our technology controls the camera accordingly to continually improve the quality of the acquired data.
All of these processes are done promptly and automatically with the help of machine learning and artificial intelligence technology.
To obtain high-quality nose print and face images, all a user needs to do is simply execute our app on their mobile phone and point it at a dog or cat.
Dogs Identification Technology
Artificial Intelligence Deep Neural Network
optimized for dogs identification
In the past, identification solutions based on biometrics have primarily focused on humans, utilizing methods such as tags, branding, and microchips for animals.
Thanks to our proprietary research and technical skills, as well as collaboration with universities, we have developed a new artificial intelligence neural network optimized for identifying dogs.
Our technology specializes in nose print identification, achieving over 99% accuracy, and has been successfully published in IEEE Access after approval from peer reviewers.
An AI neural network optimized for
cat’s facial recognition
We designed and trained the AI neural network reflecting cat’s
behavioral traits. Our unique research and development are
tailored just for cats, because their faces are different from humans.
We attained an impressive recognition rate for cat faces
of up to 99%. This result has been submitted for publication in
international journals as well as for registration as intellectual property.
Assessment of performance
*Same colored points are the same dogs, and performance of differentiation is higher when they are closer.
*Different colored points are different dogs, and performance of differentiation is higher when they are farther.
Google Inception Module shows approx. 90% recognition success rate.
Our deep neural networks shows approx. 98% of recognition success rate.
(as published on IEEE Access: Dog Nose-Print Identification Using Deep Neural Networks. DOI: 10.1109/ACCESS.2021.3068517)
High speed search function
with parallel processing
Millions of nose print information can be inquired instantly by adapting cutting edgy parallel distributed processing solution
and our neural network designed optimally for looking up identification information.
Advancing artificial intelligence deep neural networks
Our artificial intelligence does not stay as is. As more data is collected, its performance improves with recurred studies, and next-gen artificial intelligence neural network technology can be designed.
Our research has been continued to exceed accuracy and convenience of human biometrics identification technology.
Results of our artificial intelligence deep neural networks consist of random numbers that are irreversible, nor they can be understood by people.
Once nose print data is processed, it is safely encrypted before getting stored in a cloud storage.