Evidence-Based Complementary and Alternative Medicine / 2017 / Article / Tab 5

Research Article

Tongue Images Classification Based on Constrained High Dispersal Network

Table 5

Comparison of the proposed method with other feature extracting approaches.

LDAKNNCARTGBDTRFLIBSVMLIBLEAR SVM

HOG [20]Sensitivity%%%%%%
Specificity%%%%%%%
LBP
Sensitivity%%%%%%%
Specificity%%%%%%%
SIFTSensitivity%%%%%%%
Specificity%%%%%%%
HOG + LBPSensitivity%%%%%%%
Specificity%%%%%%
HOG + SIFTSensitivity%%%%%%%
Specificity%%%%%%%
LBP + SIFTSensitivity%%%%%%%
Specificity%%%%%%
HOG + LBP + SIFTSensitivity%%%%%%
Specificity%%%%%%%
Doublets [21] Sensitivity%
Specificity%%
Doublets + HOG [22] Sensitivity%%%%%%
Specificity%%%%%%
PCANet [23] Sensitivity%%%%%%%
Specificity%%%
Our methodSensitivity%%%%%%%
Specificity%%%%%%%

Note. The sum rule of feature combination is a cascade operation. Given two types of features and obtained by feature extraction methods and , respectively, then + is equal to . For example, HOG + LBP means, for each sample, we append LBP features just after HOG features. Besides, “our method” is short for the proposed CHDNet feature extraction method.

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.