PHYSIOLOGICAL BIOMETRICS Palm Prints FEATURES OF PALM OR

PHYSIOLOGICAL BIOMETRICS Palm Prints

FEATURES OF PALM OR PALM PRINT • Palm contains • Three flexion creases (principal lines : heart line, head line, life line) • Secondary creases (wrinkles) • Ridges • Regions : Finger root (I), inside region (II) and outside region (III) • Delta point features ( center of delta – like region) • Datum(end points across the palm and its mid point ) • Minutiae points • Geometry features : length, width and area of palm.

PALM PRINT AS BIOMETRICS • Palm lines and wrinkles are formed during third and fifth month of development. • Palm features are unique and also rich in information that can be used for feature extraction. • A region of interest (ROI) is extracted from the palm area for processing.

PALM RECOGNITION SYSTEM • Palm recognition process includes: • Region of Interest (ROI) is selected Image acquisition Feature Extraction • Features • Vectors • input query feature template is matched with stored template Matching Decision making • accept or reject the query feature template based on match score.

IMAGE ACQUISITION • Image of palm is captured for person identification. • Offline : • Inked palm images • Area of the palm (Region of interest) is “cropped” manually. • Online : • Palm scanners, • Digital Camera (no contact)

PRE - PROCESSING • The principal lines, minutiae and textures are used as unique information. • The pre-processing steps involve : Converting the Image to Binary Key point detection and Establishing coordinating system Extraction ROI and Segmenting

• Centre of palm is used as it covers most of the palm features. • To extract the centre of palm image first it has to be aligned and oriented to crop the centre portion. • Many methods are used for orientation, • Elliptical method : ellipse that’s fit the boundary of palm is obtained and orientation of palm is obtained by major axis of ellipse. • Key Point Extraction : Valley points from middle finger, ring finger, little finger and the line joining these are taken as orientation and a centre portion of palm image is found a circular or a squared portion of defined size is cropped.

(a) Acquired image (b) Binary Conversion of Palm Image. (c) Boundary tracking (d) Establishing coordinates (e) Extracting the central part (f) Preprocessed image (ROI)

FEATURE EXTRACTION • Performed after pre-processing. • Extract some stable and unique features such as principal lines, minutiae, singular points, density map, orientation field, texture etc. • These extracted features can be stored in database for future verification and matching purpose. • Stack filter : can extract the principal lines. • Gabor filter : Effective for texture analysis.

FEATURE EXTRACTION • Two types of recognition algorithms : verification and identification. • Matching methods : • Line Based • Sub-space Based • Statistical Based • Coding Based

LINE BASED APPROACH • The line-based approach utilises edge detectors to extract palm lines. • The palm lines are either matched directly or represented in other format for matching. • The magnitude are projected along the x and y axis.

STATISTICAL APPROACHES • Categorized into local and global statistical approaches. • Local Statistical : transforms images into another domain and divide the transform into several small regions. Local statistics such as means and variances of each small region are calculated and regarded as features. • Global statistical : features like moments, centre of gravity and density directly from the whole transformed images.

MATCHING • Decide whether two palm prints are from the same person or not. • Palm matching techniques • Minutiae-based matching : location, direction, and orientation of each minutia. • Correlation-based matching : lining up the palm images and subtracting them to determine if the ridges in the two palm images correspond. • Ridge-based matching : ridge pattern landmark features such as sweat pores, spatial attributes, and geometric characteristics of the ridges, and/or local texture analysis, all of which are alternates to minutiae characteristic extraction.

PALM PRINT : FEATURES