Study 2-2 Research Papers

[ErSKS]

• https://ieeexplore.ieee.org/document/6779474/
• https://ieeexplore.ieee.org/document/6388514/
• https://pdfs.semanticscholar.org/9a04/395e93d04c7ed51722c09f7f7f0b76aef0c6.pdf

[Schandboy]

1. Strategy to Extract Reliable Minutia Points for Fingerprint Recognition (2014 IEEE) Link: https://ieeexplore.ieee.org/document/6779474/ Major Points: a) The image is first enhanced using multiple thresholding method. Then after binarization, minutia points are extracted using a 3*3 window. b) The algorithm used has 6 steps as i) Image Enhancement ii) Image Binarization iii) Extract ROI iv) Ridge Thinning v) Minutiae Marking vi) False Minutiae Removal c) Histogram may sometimes produce desired results but sometimes can degrade the image quality. First obtain the threshold of an image and then based on the threshold decide whether to adjust intensity or not. If the intensity is to be adjusted, by how much it should be adjusted. The intensity adjustment on the same image using imadjust() function of MATLAB. Clearly the manual adjustment produces better quality image and is recommended for the enhancement. d) The major challenge in fingerprint recognition lies in the pre-processing of the bad quality of fingerprint images which also add to the low verification rate. e) Future work will include addressing the scalable issue of fingerprint recognition.

[Schandboy]

2. Invariant and reduced features for Fingerprint Characterization (2012 IEEE) Link: https://ieeexplore.ieee.org/document/6388514/ Major Points: a) A new method for fingerprint identification based on the Euclidian distance between the center point and their nearest neighbor bifurcation minutiae's. b) This new method avoids the problem of geometric rotation and translation over the acquisition phase of image fingerprints. Whatever the degree of fingerprint rotation, the extraction features used to characterize the fingerprint remains the same. c) Fingerprint Characterization based on the Euclidean distance between the center point and their nearest neighbor bifurcation minutiae's gives better results in fingerprint classification than several other features. d) Algorithm for the proposed method: Step 1: Input fingerprint images Step 2: Determination for center point Step 3: Segmentation, Binarisation, Enhancement, Thinning Step 4: Feature extraction Extract Bifurcation Minutiae Step 5: Compute Euclidian distance between center point and bifurcation minutiae Step 6: Sort Euclidian distance vector Step 7: Store the informations in database. e) It is based on the Euclidian distance between the center point and their nearest neighbor bifurcation minutiae points. It overcomes problem of geometric rotation and translation over the acquisition of geometric rotation and translation over the acquisition phase of image fingerprints.

[PujanChangubhari]

Fingerprint Image Enhancement Algorithm and Performance Evaluation (International Journal of Innovative Research in Computer and Communication Engineering, Vol-3, Issue 1, January 2015) **Link:**- https://pdfs.semanticscholar.org/9a04/395e93d04c7ed51722c09f7f7f0b76aef0c6.pdf

Gist from every sub-chapters. Abstract: -Enhancement techniques are employed prior to minutiae extraction. -The uniqueness of fingerprint depends upon the local ridges characteristics and their relationships. -Performance of a minutiae extraction algorithm depends upon the quality of input fingerprint images.

Introduction: -Fingerprint is combination of ridges and valleys. -Ridge is single curved agent and valley is the region between two adjacent ridges. -Minutiae types are restricted to ridge endings and bifurcations. -Good quality fingerprint contains about 40-100 minutiae. -Region of Interest (ROI) is divided to 3 categories They are: i) Well-defined region ii) Recoverable corrupted region iii) Unrecoverable corrupted region

Related work: -Ridge structure in poor quality fingerprint images are not well-defined. It leads to following problems. i)A significant spurious minutiae may be created. ii)A large percent of real minutiae may be ignored. iii)Large errors in position and orientation may be introduced.

Fingerprint Enhancement Algorithm: -Fingerprint enhancement can be conducted on either
i) Binary images ii) Gray level images

Fingerprint Enhancement Algorithm includes the following in sequential manner. i) Normalization: -An input fingerprint image is normalized so that it has a prespecified mean and variance. -used to standardize intensity values by adjusting range of grey-level values.

-where, I(i; j) represent the grey-level value at pixel (i; j), and N(i; j) represent the normalized grey-level value at pixel (i; j). similarly, M and V are the estimated mean and variance of I(i; j), and M0 and V0 are the desired mean and variance values, respectively.

• Normalization does not change the ridge structures in a fingerprint.

ii) Segmentation: -The process of separating the foreground regions in the image from the background regions. -The foreground regions correspond to the clear fingerprint area containing the ridges and valleys. -The background corresponds to the regions outside the borders of the fingerprint area, which do not contain any valid information.

iii) Orientation Estimation: -The orientation field of a fingerprint image defines the local orientation of the ridges contained in the fingerprint. -The orientation estimation is a fundamental step in the enhancement process as the Gabor filtering stage relies on the local orientation in order to enhance the fingerprint image. -The least mean square (LMS) estimation method employed by Hong [2] et al. is used to compute the orientation image.

iv)Ridge frequency estimation and Gabor Filtering: -Local ridge frequency is used to construct gabor filter. -The first step in the frequency estimation stage is to divide the image into blocks of size W * W. -The next step is to project the grey-level values of all the pixels located inside each block along a direction orthogonal to the local ridge orientation. -The parameter ridge orientation and ridge frequency are used to construct the even-symmetric Gabor filter. -Gabor filters are employed because they have frequency selective and orientation-selective properties and reduces noise preserving ridge structures.

v)Binarization and Thinning: - Binarization converts a grey level image into a binary image. -This improves the contrast between the ridges and valleys in a fingerprint image, and facilitates the extraction of minutiae. -The binarization process involves examining the grey level value of each pixel in the enhanced image, and, if the value is greater than the global threshold, then the pixel value is set to a binary value one otherwise it is set to zero. -Thinning is a morphological operation that successively erodes away the foreground pixels until they are one pixel wide.

Performance evaluation: i)Evaluation using Goodness Index(GI): ii)Evaluation using Verification Performance:-

Conclusion: -Experimental results show that the enhancement algorithm is capable of improving both the goodness index and the verification performance.

[ErSKS]

Post/Upload pdf of prev. completed projects.

[Schandboy]

1. Strategy to Extract Reliable Minutia Points for Fingerprint Recognition (2014 IEEE) Link: https://drive.google.com/open?id=1TfiH8XIrkV0WFrnWfcHKTPCUNgCq5TGU

[Schandboy]

**2. Invariant and reduced features for Fingerprint Characterization (2012 IEEE) Link:** https://drive.google.com/open?id=1QXQuzuC9qQxYdYDDUGshtA2hjE3CJBeQ

[Schandboy]

3. A Fingerprint Recognition Algorithm Based On Principal Component Analysis Link: https://drive.google.com/open?id=1-ROsNOmnP9693z73AQ2Rqk6FOR6v2Tdc

[Schandboy]

4. A New Algorithm for Minutiae Extraction and Matching in Fingerprint Link: https://drive.google.com/open?id=1P8sZaMlEz4cWbWsHMHToaLdNk11i4seb

[Schandboy]

5. Fingerprint Image Enhancement Algorithm and Performance Evaluation Link: https://drive.google.com/open?id=1KF-QgE-FGSkSQmoVflqT9CAoDZVsyZ9e

[Schandboy]

6. Fingerprint Image Enhancement Algorithm and Performance Evaluation Link: https://drive.google.com/open?id=1AyEXEVvuXXTgibk9mlzw07afQYKf7N1l

[Schandboy]

7. Fingerprint Matching using Gabor Filters Link: https://drive.google.com/open?id=1JGzhJ_PkUUUWKiuRh4GWUBJ4A1aunRqP

[Schandboy]

8. Fingerprint Recognition Link : https://drive.google.com/open?id=1SBCOkOfIuGb1xEsjx_L-6vakMjs3waHn

[Schandboy]

9. Student Attendance System Based On Fingerprnt Recognition and One to Many Matching Link: https://drive.google.com/open?id=1CpywWtkeSoLBkcfdtmx6J___Q6YpbedN

[Schandboy]

10. Fingerprint Classification Based on Depth Neural Network [2014] Link: https://drive.google.com/open?id=1M2d8xnTalmBoWxiAnPNMxXu8AOArFKct

[Schandboy]

11. Neural Network-based Minutiae Extraction for Fingerprint Verification System [ICIT 2017] Link: https://drive.google.com/open?id=11uyslc3XjvfBwA-bvG1XGJuGAv5C99x2

[Schandboy]

12. Fingerprint Classification using a Deep Convolutional Neural Network [IEEE 2018] Link: https://drive.google.com/open?id=1T5tXfpJIOn9yNqyJc8pEun63Dn3u8D0Y

[ErSKS]

Project Board for your group:

https://github.com/orgs/KhEC/projects/2

Post all related Notes & Issues