Project Overview :
β Here we going to label the object from the images, so that we can use that data to training the ai model. Itβs called labelling or annotation.
Requirements :
β Raspberry Pi 3 Model B+ .
β Python3 .
Initial setup for RPI-TENSORFLOW :
π Click Here , for the initial setup
SPECIFICATION :
Raspberry Pi 3 Model B+
The Raspberry Pi 3 Model B+ is the latest product in the Raspberry Pi 3 range, boasting a 64-bit quad core processor running at 1.4GHz, dual-band 2.4GHz and 5GHz wireless LAN, Bluetooth 4.2/BLE, faster Ethernet, and PoE capability.
The dual-band wireless LAN comes with modular compliance certification, allowing the board to be designed into end products with significantly reduced wireless LAN compliance testing, improving both cost and time to market.
β Processor: Broadcom BCM2837B0, Cortex-A53 64-bit SoC @ 1.4GHz .
β Memory: 1GB LPDDR2 SDRAM.
β Connectivity: 2.4GHz and 5GHz IEEE 802.11.b/g/n/ac wireless LAN, Bluetooth 4.2, BLE Gigabit Ethernet over USB 2.0 (maximum throughput 300Mbps) 4 Γ USB 2.0 ports.
β Access: Extended 40-pin GPIO header.
β Video & Sound: 1 Γ full size HDMI, MIPI DSI display port, MIPI CSI camera port, 4 pole stereo output and composite video port.
β Multimedia: H.264, MPEG-4 decodes (1080p30); H.264 encode (1080p30) OpenGL ES 1.1, 2.0 graphics.
β SD card support: Micro SD format for loading operating system and data storage.
β Input Power: 5V/3.1A DC via micro USB connector, 5V DC via GPIO header, Power over Ethernet (PoE)βenabled.
Procedure :
β Here is the github link for LableImg python application,
https://github.com/heartexlabs/labelImg.git πClick This URL
β Download the repository from the website or just replace the path with your required path that folder should be empty and run the below commend from the terminal,
- git clone https://github.com/heartexlabs/labelImg πClick This URL
β Then we have to install the required libraries all listed in requirements/requirements-linux-python3.txt install those libraries.
β Run the below commends for install required libraries,
- sudo apt-get install pyqt5-dev-tools
- sudo pip3 install -r requirements/requirements-linux-python3.txt
βIf the pyqt5 version not found edit the requirements-linux-python3.txt file and remove β==
- make qt5py3
β And then run the labelImg.py file directly or running the commend below form terminal,
- python3 labelImg.py
βThe application will open,
β Select the folder where you kept the images and open that directory
β Select the image you want and press w key to create the border on your object you want to detect then give the name or id to that object then save it by using Ctrl+S then move on to next image.
β Then if you check the image folder each image have a XML file which has the data of that object border and id so we can use this for train our model.
OUTPUT :