A pH Detection System Based on Lightweight Convolutional Neural Network
FAN Wenxuan
MAO Yingji
Abstract：pH value is usually used to measure the degree of acidity and alkalinity of the substance,in view of the traditional manual colorimetric visual detection of pH test paper values are susceptible to the subjective factors of the detector,this paper de-signes and implementes a pH test paper value detection system based on the lightweight convolutional neural network EfficientNet Lite1,using Raspberry Pi 3B as the hardware master,through the camera to collect images and the methods of threshold segmenta-tion,median filtering and image cropping are used to preprocess the collected images.The cut pH test paper area is used as the net-work input,and finally the network output is used as the system test result.Experimental results show that the accuracy rate of the system for pH test paper detection is 99.72%,which has certain practical application value.
Keywords：pH test paperEfficientNet Lite1Raspberry Pi 3Bimage classification
Publication Date：2025-07-20
Online Publishing Date：2025-09-25(First online date of this platform, not the publication date of the document)
Pages：6( 1846-1851 )