Intro fact: Each individual has unique ear! Ear can be used as a biometrics trait! like a fingerprint, face recognition, etc...
Title: 'Development of an Efficient Ear Biometric System and Investigation of Age Invariant Nature of Human Ear'
Sponsoring Agency: Department of Science & Technology (DST), Government of India
Period: 2015 - 2018 (I joined the project on Sept, 2017)
In this project we experimented with 2D ear data, 3D ear data, and a combination of both. The project consisted mainly of the following parts:
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:
Poor Lighting codition
Frontal Pose
Occlusion
High scale variance
(
Full-text will be available soon!)
(Full-text will be available soon!)
(
Full-text available
)