An interactive learning system for children that recognizes objects via the camera with YOLOv8, speaks their names, detects colors with HSV, and labels uploaded images.
An academic project carried out by a team of students with technical assistance from Techno Enjaz to develop an interactive learning system for children based on artificial intelligence and image processing. A child points the camera at an everyday object, such as a cup, a ball, or a book, and the system recognizes it, displays its name on screen, and speaks the name aloud. It also identifies the color of an object held in front of the camera and recognizes the objects in an image the user uploads from the device.
The working prototype was built in Python and uses YOLOv8 (through the ultralytics library) for object recognition, the HSV color model with OpenCV for color detection, and Tkinter for a three-button graphical interface. The prototype carried out all three of its tasks in the documented practical tests. The project reports no quantitative accuracy measurements, so its results are presented as a functional proof of a prototype.
| Item | Details |
|---|---|
| Project type | Interactive learning system based on computer vision |
| Field | Educational technology, artificial intelligence, image processing |
| Project status | Working desktop prototype, tested on a variety of objects, colors, and images |
| Techno Enjaz role | Technical support and assistance to the students during project development |
| Core technologies | Python, YOLOv8 (ultralytics), OpenCV, HSV, Tkinter, Anaconda |
| Outputs | Object recognition with spoken names, color detection, recognition of uploaded image content |
The project starts from the view that a child's early years have the greatest influence on intellectual and language development, and that traditional education often relies on rote learning, makes the teacher the only source of information, and offers few interactive methods that encourage children to explore and learn by doing.
Children naturally learn by observing and handling the things around them. The project therefore aimed at a tool that links the child directly to their surroundings: when a child points the camera at a ball or a flower and hears its name immediately, the word is tied to the real object, and color recognition adds a further dimension to visual learning.
The project was carried out academically by the students, with technical assistance and support from Techno Enjaz during development. It is presented among the office's work as an example of its support for educational projects that apply computer vision and AI in tools designed for children.
The system runs through a graphical interface with three buttons, each with its own task:
The HSV model separates hue, saturation, and value (brightness), which makes defining a range for each color less sensitive to lighting changes than the RGB model. The book explains the OpenCV-based HSV thresholding method in these steps:
cvtColor; hue runs from 0 to 179, and saturation and value from 0 to 255.inRange, then clean it with erosion and dilation.findContours, ignore small areas, and write the color name over the detected object.| Tool | Role in the project |
|---|---|
| Python | Main development language |
| Anaconda | Isolated environment with a specific Python version to avoid package conflicts |
| OpenCV | Video capture, image processing, and color analysis |
| YOLOv8 (ultralytics) | Object recognition in the live feed and uploaded images |
| Tkinter | The three-button graphical interface |
| Jupyter Notebook and VS Code | Environments for writing and testing code |
The three tasks were tested in practice, with the results described by the project as follows:
| Task | What was tested | Documented result |
|---|---|---|
| Recognizing objects and speaking their names | Various objects in front of the camera, such as a ball, a book, and a pen, under different lighting | Recognized objects well, especially in good lighting; the documented example shows "cup" displayed and spoken |
| Color detection | Basic colors such as red, green, and blue under different lighting | Identified the object's color and displayed it on screen |
| Recognizing uploaded image content | Images containing animals and household items | Recognized the objects and wrote their names, including a cat in the documented example |
The project concluded that the system performed all three tasks well and consistently and met its intended goals. However, the book reports no project-specific quantitative values such as precision, recall, mAP, or processing speed, nor the number of test samples, and while its conclusion mentions positive interaction from children, it gives no method or data for that evaluation. The accuracy figures in the theoretical chapter belong to other studies and are not results of this system.
According to the proposals set out in the project, the system could be developed by:
If you are working on a computer-vision-based learning app and need technical help developing the idea or building a prototype, you can contact the Techno Enjaz office to discuss your project's requirements and the appropriate scope of support.
It is a prototype interactive learning system built by a team of students with technical assistance from Techno Enjaz. The child points the camera at an everyday object and the system displays its name and speaks it aloud; it also identifies the object's color and recognizes objects in uploaded images, with the aim of expanding children's vocabulary and linking names to real objects.
The graphical interface has three buttons: the first starts the camera so that YOLOv8 recognizes the object in view and displays and speaks its name; the second uploads an image from the device and the system writes the names of the objects in it; the third identifies the color of an object held in front of the camera after converting the frame to the HSV color model.
The system was built in Python within an Anaconda environment. It uses YOLOv8 through the ultralytics library for object recognition, OpenCV for video capture and image processing, the HSV model for color analysis, and Tkinter for the interface. Jupyter Notebook and VS Code were used to write and test the code.
The system was tested on objects such as a ball, a book, a pen, and a cup under different lighting, on basic colors such as red, green, and blue, and on images containing animals and household items, and it succeeded at all three tasks, performing best in good lighting. The project reports no quantitative accuracy or speed values, so the results are a functional proof of a prototype.
Color detection is affected by lighting, reflections, and shadows; objects that look alike or are partly hidden can be confused; and performance drops on weak devices and with blurry images. The documented version is a desktop application, while a mobile app, multi-language support, and learning games remain proposed developments.
Reach out to Techno Enjaz engineering team to discuss technical feasibility, prototype hardware, and development scope.
Discover more engineering prototypes and academic implementations
A children's learning system that uses a camera to recognize animals with YOLO11, colors with HSV, and numbers with OCR, then shows and speaks the result in Arabic.
A computer vision system that detects knives and pistols in real time from a laptop or phone camera using two trained YOLOv8 models, Python, and OpenCV.
A gold-shop security system detecting weapons with YOLO, violence with an RNN and theft with MediaPipe, plus PIR and flame sensors on NodeMCU and Telegram alerts.