Underwater Algae Detection and Identification System Desktop Application Development

Project Background

The project primarily focuses on the detection of planktonic organisms in various water bodies. The system includes a built-in plankton database that automates the identification and counting of planktonic organisms through instruments. It can provide early warnings for the occurrence of algal blooms in large rivers and lakes, helping plankton monitoring workers to improve work efficiency and monitoring standards. It offers the best operational platform for environmental monitoring, water quality analysis, and algae research institutions, thereby ensuring the safety of drinking water for the public.

Project Introduction

1. Rich plankton image library, with expandable species and content in each library; plankton image collection camera connection, adjustable white balance and exposure time, with options for manual or automatic mode for image capture.
2. Customizable database, where users can add algae/zooplankton images to a user-defined database, creating a local database.
3. Deep learning technology for automatic comparison, utilizing cutting-edge deep learning techniques to solve the problem of blurry identification of biological images in complex environments. For the first time, it has implemented an intelligent search function for similarity without any conditional restrictions, helping laboratory personnel quickly search for possible species based on the images observed under a microscope.
4. Algae classification and counting, using color-coded and size-differentiated circles to mark various microalgae, with automatic accumulation of counts by category clicking, automatic sorting of dominant species, sorting by phylum (class), percentage analysis of dominant community composition, automatic calculation of evenness index, algal density, and zooplankton abundance.