Automated Diagnosis of Otitis Media: Vocabulary and Grammar

Table 4

Classification accuracies (in %) on the ground-truth set of 170 tympanic membrane images out of 181 images after rejection. Each row corresponds to the class-wise classification accuracies and columns correspond to classification by the following algorithms: correlation filter classification system (CFC), WND-CHRM (WCM), multiresolution classifier (MRC), SIFT and shape descriptors with SVM classifier (SSC), random forest classifier (RF), and otitis media classifier with rejection (OMCR).

	CFC	WCM	MRC	SSC	RF	OMCR
AOM	65.6	65.5	61.0	76.2	80.3	90.0
OME	56.7	58.2	65.3	72.8	79.1	89.1
NOE	71.4	69.0	83.9	58.3	69.4	93.2
Accuracy	63.6	63.6	68.2	70.0	77.1	89.9