Research Article

Hybrid Deep Learning Algorithm-Based Food Recognition and Calorie Estimation

Table 4

Comparative analysis of the existing approaches with the proposed method.

Evaluation metricsMask RCNN+YOLO V5Mask RCNNYOLOCNN

Accuracy0.971250.962250.951250.92125
Sensitivity0.967540.953540.947540.93754
Specificity0.964520.951520.942520.93452
Precision0.964150.950150.941150.93415
-score0.965840.951840.944330.93584
MCC0.962410.950410.943410.93241
NPV0.945920.938920.926920.91592
FPR0.01540.02140.02940.0354
FDR0.01480.01980.02380.0348
FNR0.01610.02510.03210.0461