Ear Biometrics

• First of all, curvilinear features is extracted from 2D ear images, using a filter bank which was inspired by a lankmark pattern recognition task in a remort sensing application. We claim this the most efficient method to extract curvilinear feature for the ear detection surpassing other edge detection algorithms.
• The extracted cuvilinear features are then mapped to the corresponding 3D ear image.
• At this point, we got the key-points on the 3D ear, now we can use methods of part-1 effectively!

[Part-3] Unconstrained Ear Detection using Ensemble based Convolutional Neural Network Model

This work presents a technique for ear detection from 2D profile face images that is capable of significantly reducing the false positives. In an ear biometrics system, recognition performance highly depends on the performance of the ear detection module. The trade-off between the complexity and the false positive detection is one of the essential component, where the complexity of a system increases proportionally to achieve a zero false positive rate detection. In literature, available ear detection techniques based on handcrafted features face challenges with low quality acquired images affected by illumination, occlusion and pose variations. We propose an ear detection technique using ensemble of convolutional neural network (CNN). The first part of the technique trains three models of CNN on a given dataset whereas in later part, weighted average of the outputs of trained models is utilized to detect the ear regions. The use ensemble models shows better performance as compared to the case when each individual model is used standalone. The proposed technique is being evaluated on two databases viz. IIT Indore- Collection A (IIT-Col A) database and annotated web ear (AWE) database. Experimental results of ear detection demonstrate the superior performance of the proposed technique over other state-of-the-art techniques in handling illumination, occlusion and pose variations.

Some results of our algorithm in various challenging environment:

Related Publication

1. [Submitted] I. Iyyapan, S. Prakash, I. Dave, and S. Ali "3D Ear in Human Recognition Using Binarized 3D Descriptor", IEEE Transactions on Emerging Topics in Computing, 2018. (Impact 3.636)
2. I. Iyyapan, S. Prakash, I. Dave "Unconstrained Ear Detection using Ensemble based Convolutional Neural Network Model", Concurrency and Computation: Practice & Exp., John Wiley & Sons Ltd, 2018. (DOI: 10.1002/cpe.5197) (Accepted) (SCI Indexed IF 1.11) (Full-text will be available soon!)
3. I. Dave, I. Iyyapan, and S. Prakash "3D ear biometrics: acquisition and recognition", 15th Annual IEEE India Conference (INDICON), 2018. (Accepted) (Full-text will be available soon!)
4. I. Iyyapan, S. Prakash, and I. Dave, "Ear recognition in 3D using 2D curvilinear features", IET Journal of Biometics, 2018. (DOI: 10.1049/iet-bmt.2018.5064) (SCI Indexed IF 1.936) (Full-text available)