Image Recognition amphibian identification app

Image Recognition

Amphibian Pattern Recognition

In a groundbreaking initiative, a leading US-based environmental research organization partnered with Uniwebb Software to transform amphibian lifecycle studies using state-of-the-art image recognition technology.


US-based environmental research organization


Academic Research


Java, Kotlin, OpenCV (for image processing), PostgreSQL, Spring Boot 2, and Spring Data


1 Project Manager, 2 Analysts, 4 Developers, 1 QA Specialist focused on machine learning algorithms and computer vision techniques.


Android Mobile App

Amphibian Research with Advanced Image Recognition Technology


Uniwebb Software was tasked with developing an Android application, the project leveraged cutting-edge advancements in computer vision, machine learning, and AI image analysis to create a non-invasive, efficient solution for amphibian identification.

Revolutionizing Amphibian Tracking

Traditional methods of tracking amphibians were proving inefficient and potentially harmful, prompting the need for an innovative solution. The project’s challenge was to harness the power of image recognition and pattern recognition technologies to accurately identify amphibian species from images, facilitating non-invasive research methods.


Uniwebb Software’s team developed a sophisticated machine learning algorithm optimized for image recognition, capable of accurately identifying amphibians through unique pattern recognition. This was supported by a custom middleware solution ensuring seamless communication between the app and a comprehensive species database, highlighting our expertise in computer vision and AI image analysis.

  • Unified Development with React Native: Ensured a consistent and efficient user interface across Android devices, showcasing our capability in cross-platform IoT development.
  • Agile and Cross-Functional Approach: Our agile methodology and the formation of cross-functional teams accelerated the development process, enabling rapid adaptation to new insights and technical challenges.

A Transformative Tool for Nature Scientists

The application has become an invaluable asset for scientists, offering:

  • Advanced Image Recognition: Facilitates the capture, identification, and classification of amphibians using smartphone cameras.
  • Data Analysis and Storage: Empowers researchers to add descriptions, store observations, and conduct population analysis through an intuitive interface.
  • Innovative Image Processing: Enables detailed analysis of captured images for comprehensive research findings.


This case study showcases Uniwebb Software’s expertise across a spectrum of technologies and disciplines:

  • Deep learning for images and AI-powered image analysis for accurate species identification.
  • Integration of Google Maps for geolocation data.
  • Utilization of Camera API for high-quality image capture and processing.


The project also highlighted our proficiency in:

  • Dependency injection with Dagger for maintainable code.
  • Retrofit for efficient network communication.
  • Ktor for scalable server-side applications.



Uniwebb Software’s successful development of this image recognition application marks a significant advancement in environmental research technology. By leveraging our expertise in machine learning, computer vision, and agile project management, we delivered a solution that not only meets the client’s needs but also contributes to the global understanding of amphibian life cycles.

This case study exemplifies how Uniwebb Software is at the forefront of developing innovative solutions that combine technology with environmental conservation, emphasizing our commitment to using image recognition and AI for the greater good.


What is the primary goal of the amphibian research app developed by Uniwebb Software?

The main objective is to provide environmental scientists with a powerful tool that uses advanced image recognition and machine learning technologies to accurately identify and track amphibian species, facilitating non-invasive research and data collection.

How does the app identify different amphibian species?

The app employs a sophisticated machine learning algorithm optimized for image recognition, which analyzes images captured by users. It utilizes pattern recognition to compare these images against a comprehensive database of amphibian species to identify the subject accurately.

Can the app be used in any environment or only in specific locations?

The app is designed to be used in various environments where amphibians are found. It integrates Google Maps for geolocation data, allowing scientists to capture and record amphibian sightings accurately across different locations worldwide.

What technologies were used in the development of the app?

The development team used a range of technologies, including Java, Kotlin, OpenCV for image processing, PostgreSQL, Spring Boot 2, Spring Data, and Vaadin 10, to create a robust and user-friendly Android application.

How does the app ensure the privacy and security of the data collected?

Data privacy and security are paramount. The app incorporates robust encryption methods, secure authentication mechanisms, and comprehensive data protection measures to safeguard sensitive user information and research data against potential threats.

What makes this app different from other wildlife identification apps?

This app is specifically tailored to the needs of environmental scientists studying amphibians. It not only provides advanced image recognition capabilities but also offers tools for detailed data analysis, storage, and population analysis, supported by a user-friendly interface designed for scientific research.

How can scientists or researchers access the app?

Scientists and researchers interested in utilizing the app for their studies can contact Uniwebb Software directly for more information on accessing and integrating this technology into their research projects.