Image Semantic Recognition and Segmentation Algorithm of Colorimetric Sensor Array Based on Deep Convolutional Neural Network

Table 5

Comparative analysis for features.

Metrics	SCN	SOSD-Net	CBF	SFASM
Accuracy	0.7843	0.8206	0.8642	0.9196
Precision	0.8271	0.8598	0.9084	0.9472
F1-score	0.691	0.755	0.842	0.9191
Error ratio	15.66	13.78	10.51	7.198
Analysis time (s)	4.12	3.43	2.59	1.706

The proposed method achieves 9.66% high accuracy, 8.21% high precision, 15.64% high F1-score, 6.12% less error ratio and 8.25% less analysis time.