Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overview of pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.

/pdf/data-clustering-a-review-4c452f5cab.pdf

Data clustering: a review

A major new professional reference work on fingerprint security systems and technology from leading international researchers in the field Handbook provides authoritative and comprehensive coverage of all major topics, concepts, and methods for fingerprint security systems This unique reference work is an absolutely essential resource for all biometric security professionals, researchers, and systems administrators

/pdf/handbook-of-fingerprint-recognition-16mh887j24.pdf

Handbook of Fingerprint Recognition

In order to ensure that the performance of an automatic fingerprint identification/verification system will be robust with respect to the quality of input fingerprint images, it is essential to incorporate a fingerprint enhancement algorithm in the minutiae extraction module. We present a fast fingerprint enhancement algorithm, which can adaptively improve the clarity of ridge and valley structures of input fingerprint images based on the estimated local ridge orientation and frequency. We have evaluated the performance of the image enhancement algorithm using the goodness index of the extracted minutiae and the accuracy of an online fingerprint verification system. Experimental results show that incorporating the enhancement algorithm improves both the goodness index and the verification accuracy.

/pdf/fingerprint-image-enhancement-algorithm-and-performance-405diava9j.pdf

Fingerprint image enhancement: algorithm and performance evaluation

The objective of this paper is to give a comprehensive introduction to applied cryptography with an engineer or computer scientist in mind. The emphasis is on the knowledge needed to create practical systems which supports integrity, confidentiality, or authenticity. Topics covered includes an introduction to the concepts in cryptography, attacks against cryptographic systems, key use and handling, random bit generation, encryption modes, and message authentication codes. Recommendations on algorithms and further reading is given in the end of the paper. This paper should make the reader able to build, understand and evaluate system descriptions and designs based on the cryptographic components described in the paper.

[서평]「Applied Cryptography」

IEEE Transactions on Pattern Analysis and Machine Intelligence

In document understanding, one of the early stages involves extracting text strings from a scanned image of the document. Often, the text is printed on a repetitive background of design patterns for visual effects. For recognition purposes, the text strings need to be extracted eliminating the background. Image morphology based algorithms have been proposed for this purpose. However, image morphology operations are compute intensive. We describe the design and synthesis of a high-performance coprocessor to meet the compute load. The algorithm has been synthesized for Splash 2, an attached processor on Sun hosts. The Xilinx Field-Programmable Gate Array (FPGA) based PEs are programmed using VHDL behavioral modeling. The design can run at near-ASIC speeds of /spl ap/22 MHz clock rate with effective timing of 3 milliseconds per 128/spl times/128 image frame and 3/spl times/3 structuring element. Compared with a SPARC station 20 timings of 1.5 sees, the present implementation has a speed advantage of the order of 500 times.

FPGA-based coprocessor for text string extraction

Deep learning algorithms provide state-of-the-art results on a multitude of applications. However, it is also well established that they are highly vulnerable to adversarial perturbations. It is often believed that the solution to this vulnerability of deep learning systems must come from deep networks only. Contrary to this common understanding, in this article, we propose a non-deep learning approach that searches over a set of well-known image transforms such as Discrete Wavelet Transform and Discrete Sine Transform, and classifying the features with a support vector machine-based classifier. Existing deep networks-based defense have been proven ineffective against sophisticated adversaries, whereas image transformation-based solution makes a strong defense because of the non-differential nature, multiscale, and orientation filtering. The proposed approach, which combines the outputs of two transforms, efficiently generalizes across databases as well as different unseen attacks and combinations of both (i.e., cross-database and unseen noise generation CNN model). The proposed algorithm is evaluated on large scale databases, including object database (validation set of ImageNet) and face recognition (MBGC) database. The proposed detection algorithm yields at-least 84.2% and 80.1% detection accuracy under seen and unseen database test settings, respectively. Besides, we also show how the impact of the adversarial perturbation can be neutralized using a wavelet decomposition-based filtering method of denoising. The mitigation results with different perturbation methods on several image databases demonstrate the effectiveness of the proposed method.

Image Transformation-Based Defense Against Adversarial Perturbation on Deep Learning Models

Biometric Technology for Human Identification II

The invention is a system and method for constructing a rolled surface image from a set of partial surface images. A sequence of individual partial surface images is acquired as an object is progressively rolled across the surface of an imaging device. The imaging device is configured so that only that part of the object's surface which is in close proximity is imaged. To produce a complete rolled surface image, i.e. a composite image, the value of each pixel of the composite image is derived by performing a suitable pixel operation on the set of corresponding pixels in the input partial surface images. This is possible because each partial image is represented as a fixed size and each pixel in each of the partial images has a unique position in the partial image. The system can also directly produce a list of salient surface features. Localized features are extracted from each individual partial image whereas other specific attributes of each image are ignored. The features from different partial surface images are then matched up to generate clusters of observations associated with each unique surface feature. These clusters are analyzed to produce more accurate positional information as well as a confidence measure for each observed feature in the complete set covering the rolled surface of the object.

System and method for generating a rolled surface representation from a set of partial images

A majority of the existing fingerprint recognition algorithms are based on matching minutia features. Therefore, minutiae extraction is one of the critical steps in fingerprint verification algorithms. Poor quality fingerprint images lead to missing and spurious minutiae that degrade the performance of the matching system. We propose two new techniques for minutiae verification based on non-trivial gray level features. The proposed features intuitively represent the structural properties of the minutiae neighborhood leading to better classification. We use directionally selective steerable wedge filters to differentiate between minutiae and non-minutiae neighborhoods. We also propose a second technique based on Gabor expansion that results in even better discrimination. We present an objective evaluation of both the algorithms.

/pdf/novel-approaches-for-minutiae-verification-in-fingerprint-4xijdc01gt.pdf

Nalini K. Ratha

Papers

FPGA-based coprocessor for text string extraction

Image Transformation-Based Defense Against Adversarial Perturbation on Deep Learning Models

Biometric Technology for Human Identification II

System and method for generating a rolled surface representation from a set of partial images

Novel Approaches for Minutiae Verification in Fingerprint Images