Pritee Khanna

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

This work is directed toward the development of a computer-aided diagnosis (CAD) system to detect abnormalities or suspicious areas in digital mammograms and classify them as malignant or nonmalignant. Original mammogram is preprocessed to separate the breast region from its background. To work on the suspicious area of the breast, region of interest (ROI) patches of a fixed size of 128×128 are extracted from the original large-sized digital mammograms. For training, patches are extracted manually from a preprocessed mammogram. For testing, patches are extracted from a highly dense area identified by clustering technique. For all extracted patches corresponding to a mammogram, Zernike moments of different orders are computed and stored as a feature vector. A support vector machine (SVM) is used to classify extracted ROI patches. The experimental study shows that the use of Zernike moments with order 20 and SVM classifier gives better results among other studies. The proposed system is tested on Image Retrieval In Medical Application (IRMA) reference dataset and Digital Database for Screening Mammography (DDSM) mammogram database. On IRMA reference dataset, it attains 99 % sensitivity and 99 % specificity, and on DDSM mammogram database, it obtained 97 % sensitivity and 96 % specificity. To verify the applicability of Zernike moments as a fitting texture descriptor, the performance of the proposed CAD system is compared with the other well-known texture descriptors namely gray-level co-occurrence matrix (GLCM) and discrete cosine transform (DCT).

A gender classification system robust to occlusion using Gabor features based (2D)2PCA

Abstract Recognizing gender of a person from occluded face image is a recent challenge in gender classification research. This work investigates the issue and proposes a gender classification system that works for non-occluded face images to face images occluded up to 60%. Local information of the face, which carries the most discriminative features to find the gender, is gathered by dividing the face image into M × N sub-images. Subsequently, features are calculated for every sub-image by applying ( 2 D ) 2 PCA on each illumination invariant real Gabor space generated using Gabor filter. Support Vector Machine is used for classification. Experiments are performed on five databases. In case of non-occluded face images, the proposed approach gives 98.4% classification rate on FERET database. For occluded face images, occlusions ranging from 10% to 60%, results are quite competitive with accuracies around 90%. Present work also analyzes the impact of various face components in the context of gender classification.

Gender classification using Radon and Wavelet Transforms

In this paper a new approach is proposed to recognize gender from the face image. This approach will detect the face from the given image. Radon and Wavelet Transforms are combined to extract key facial features for each face images of male and female. These features will be used to classify the face images of each pattern. We have compared the DCT extracted face feature with our face feature extracted by Radon and Wavelet Transforms. The experimental result shows that the proposed approach (combination of face detector, radon and wavelet transforms, KNN classifier) achieves better performance.

Analysis of Palmprint Verification Using Wavelet Filter and Competitive Code

This paper presents an algorithm to extract the region of interest (ROI) from the palm print image of the Hong Kong PolyU large-scale palm print database (version 2). Competitive coding method is used for feature extraction. Coding based methods are among the most promising palm print recognition methods because of their small feature size, fast matching speed, and high verification accuracy. Competitive Coding Scheme (CCS), first convolves the palm print image from real part of six Gabor filters with different orientations and then encodes the dominant orientation into its bit wise representation. Palm print image is decomposed into two levels using discrete wavelet transform. Approximation details give compress and denoised image of the original image. The competitive scheme is applied in the approximation details of decomposed image for feature extraction. KNN Classifier is used for palm print verification. In this experiment, Genuine Acceptance Rate is calculated for four different wavelet filters (Db1, Db4, Sym4, and Coif4) with different values of K (number of nearest neighbors).

Biometric template protection using cancelable biometrics and visual cryptography techniques

Wide spread use of biometric based authentication implies the need to secure biometric reference data. Various template protection schemes have been introduced to prevent biometric forgery and identity thefts. Cancelable biometrics and visual cryptography are two recent technologies introduced to address the concerns regarding privacy of biometric data, and to improve public confidence and acceptance of biometric systems. Cancelable biometrics is an important technique that allows generation of revocable biometric templates. As the number of biometric instances are limited and once compromised they are lost forever. Cancelable biometrics allows templates to be cancelled and revoked like passwords innumerable times. Recently, various approaches that utilize visual cryptography to secure the stored template and impart privacy to the central databases have been introduced. This work attempts to summarize the existing approaches in literature making use of these two technologies to protect biometric templates.

Noise and rotation invariant RDF descriptor for palmprint identification

Rotation and noise invariant feature extraction is a challenge in palmprint recognition. This work presents a novel RDF descriptor based on Radon, Dual tree complex wavelet, and Fourier transforms. Combined properties of these transforms help to explore efficiency and robustness of RDF descriptor for palmprint identification. Radon transform can capture directional features of the palmprint and is robust to additive white Gaussian noise also. It converts rotation into translation. 1D Dual tree complex wavelet transform (DTCWT) applied on Radon coefficients in angle direction removes translation in Radon coefficients due to palmprint rotation. The magnitude of 2D Fourier transform performed on resultant coefficients helps to extract rotation and illumination invariant features. The performance of the proposed RDF descriptor is evaluated on noisy and rotated palmprints upto 10∘. Trained with normal palmprints only, the proposed system gives good results for rotated and noisy palmprints. Experiments are performed on PolyU 2D, CASIA, and IIITDMJ databases. Theoretical foundations and experimental results show the robustness of RDF descriptor against additive white noise and rotation.

Kernel discriminant analysis of Block-wise Gaussian Derivative Phase Pattern Histogram for palmprint recognition

The proposed palmprint recognition system is able to recognize palmprints captured in unconstrained environment with any imaging system.Kernel discriminant analysis of BGDPPH achieves 100% GAR and 0% EER as well as invariant to blur and noise.Experiments are performed on six different palmprint databases. This paper presents an efficient palmprint recognition technique for palmprints collected with visible as well as multispectral imaging system. ROI extraction is a challenging task for palmprint captured in unconstrained environment. ROI extracted by gaps between fingers and width of palm makes system rotation and translation invariant. Approximation ROI obtained by First-level decomposition of ROI using Haar wavelet reduces computational overhead as well as noise. Phase quantization of AROI by Gaussian derivative filter gives Gaussian derivative phase pattern image and its block-wise histograms are concatenated to form a single vector referred as BGDPPH descriptor. Dimension reduction is performed by increasing discrimination between genuine and impostor scores using chi-RBF kernel discriminant analysis (KDA). Weighted score level fusion of spectral palmprints on Fisher criterion improves recognition rate. Robustness of the proposed BGDPPH descriptor against blur and noise is evaluated on four gray-scale and two multispectral palmprint databases collected through touch-based and touch-less acquisition devices.

Gender Classification Techniques: A Review

Face is one of the most important biometric traits. By analyzing the face we get a lot of information such as age, gender, ethnicity, identity, expression, etc. A gender classification system uses face of a person from a given image to tell the gender (male/female) of the given person. A successful gender classification approach can boost the performance of many other applications including face recognition and smart human-computer interface. This paper illustrates the general processing steps for gender classification based on frontal face images. In this study, several techniques used in various steps of gender classification, i.e. feature extraction and classification, are also presented and compared.

A fast and efficient computer aided diagnostic system to detect tumor from brain magnetic resonance imaging

In this work, a simple and efficient CAD (computer‐aided diagnostic) system is proposed for tumor detection from brain magnetic resonance imaging (MRI). Poor contrast MR images are preprocessed by using morphological operations and DSR (dynamic stochastic resonance) technique. The appropriate segmentation of MR images plays an important role in yielding the correct detection of tumor. On examination of three views of brain MRI, it was visible that the region of interest (ROI) lies in the middle and its size ranges from 240 × 240 mm2 to 280 × 280 mm2. The proposed system makes effective use of this information and identifies four blocks from the desired ROI through block‐based segmentation. Texture and shape features are extracted for each block of all MRIs in the training set. The range of these feature values defines the threshold to distinguish tumorous and nontumorous MRIs. Features of each block of an MRI view are checked against the threshold. For a particular feature, if a block is found tumorous in a view, then the other views are also checked for the presence of tumor. If corresponding blocks in all the views are found to be tumorous, then the MRI is classified as tumorous. This selective block processing technique improves computational efficiency of the system. The proposed technique is well adaptive and fast, and it is compared with well‐known existing techniques, like k‐means, fuzzy c‐means, etc. The performance analysis based on accuracy and precision parameters emphasizes the effectiveness and efficiency of the proposed work.

ROI segmentation using Local Binary Image

Segmentation of ROI is an important and challenging task in the development of CAD system for the detection of breast cancer. This work proposes a Local Binary Image (LBI) to segment the ROI from the mammogram patches. The key idea is to use textural properties of mammogram patches for representing salient micro-patterns of the masses and preserving the spatial information at the same time. Corresponding to the patch, LBI is the binary image where the value 1 represents the presence of texture in the patch. Using LBI the threshold value is identified which is used to extract the mask image. Once the mask image is generated boundary is plotted to trace suspicious area in the patch. The efficiency of the proposed method is tested on a dataset of 819 suspicious patches from the IRMA reference database. The experimental results achieved that the proposed LBI method has successfully attained the value 0.934 for Quality measure.