|
Author | Dataset | Accuracy | Summary |
|
Emeršič et al. [3] | NA | 30 | It was a handcrafted feature extraction method, such as LBP and patterns of oriented edge magnitudes (POEM), and CNN-based feature extraction methods were used to obtain the ear identification |
|
Tian and Mu [4] | AMI, WPUT, IITD, and UERC | 70.58, 67.01, 81.98, and 57.75 | This system used deep convolutional neural network (CNN) to ear recognition. There were occlusions like no earrings, headsets, or similar occlusions |
|
Raveane et al. [5] | NA | 98 | This system used variable conditions, and this could also be because of the odd shape of the human ears and changing lighting conditions |
|
Zhang and Mu [6] | Notre Dame Biometrics database and University of Beira Interior Ear dataset | 100 and 98.22 | This system contained large occlusions, scale, and pose variation |
|
Kohlakala and Coetzer [7] | Mathematical Analysis of Images Ear database and Indian Institute of Technology Delhi Ear database | 99.2 and 96.06 | It is used to classify ears in either the foreground or background of the image. The binary contour image applied the matching for feature extraction, and this was done by implementing a Euclidean distance measure, which had a ranking to verify for authentication |
|
Tomczyk and Szczepaniak [8] | NA | NA | It shows the published experimental results that the approach did the rotation equivalence property to detect rotated structures |
|
Hammam et al. [9] | Three ear datasets but not stated | 22 | The paper took seven performing handcrafted descriptors to extract the discriminating ear image. They then took the extracted ear and trained it using support vector machines (SVM) to learn a suitable model |
|
Alkababji and Mohammed [10] | NA | 97.8 | It used the principal component analysis (PCA) and a genetic algorithm for feature reduction and selection |
|
Jamil et al. [11] | Very underexposed or overexposed database | 97 | They considered that their work was the first to test the performance of CNN on very underexposed or overexposed images |
|
Hansley et al. [12] | UERC challenge | NA | This was done using handcrafted descriptors, which were fused to improve recognition |
|