Hand image recognition by the techniques of hand shape scaling and image weight scaling

Abstract

This research uses the object extracting technique to extract the – thumb, index, middle, ring, and small fingers from the hand images. The algorithm developed in this research can find the precise locations of the fingertips and the finger-to-finger-valleys. The extracted fingers contain many useful geometry features. One can use these features to do the person identification. The geometry descriptor is used to transfer geometry features of these finger images to another feature-domain for image-comparison. Image is scaled to make the finger image has more salient feature. Image is also magnifying by the basis of distance-multiplying-pixel-gray-level. After the image magnifying, the finger-image will possess more salient feature. Image subtraction is used to exam the difference of the two images.

Introduction

In the past 20 years, researchers invested a lot of effort to develop different techniques to identify the hand images. This past work includes – hand geometry (Editorial, 2003, Egiazarian and Gonzalez Pestana, 2002, Han et al., 2003; He, Qiu, & Sun, 2002; Mitome and Ishii, 2003, Su, 2003, Sun and Qiu, 2004, Xionga, Toha et al., 2005, Xiong, Xu et al., 2005), middle finger crease pattern matching (Joshi, Rao, Kar, & Kumar, 1998), various finger size measurements (Kumar et al., 2003, Sanchez-Reillo et al., 2000), various finger lateral view size measurements (Sanchez-Reillo et al., 2000), vein pattern (Lin & Fan, 2004), eigenpalm (Lua, Zhang, & Wanga, 2003), implicit polynomials (Oden, Ercil, & Buke, 2003), algebraic invariants (Oden et al., 2003), Karen invariant computation (Oden et al., 2003), line interception and slope comparisons (You, Li, & Zhang, 2002), control point selection (Lia et al., 2003, You et al., 2002), coarse to fine strategy (Han, 2004), B-Spline (Ma, Pollick, & Terry Hewitt, 2004), watershed transform (Lin & Fan, 2004), HMM (Sun & Qiu, 2004); however, some are very sensitive to the noise (Joshi et al., 1998, You et al., 2002); some have very complicated mathematical models (Oden et al., 2003) and some have very complicated neural training algorithms.

In the previous research, when performing the hand geometry matching (Editorial, 2003, Egiazarian and Gonzalez Pestana, 2002, Han et al., 2003, He et al., 2002, Mitome and Ishii, 2003, Su, 2003, Sun and Qiu, 2004, Xionga, Toha et al., 2005, Xiong, Xu et al., 2005), in order to recognize the hand image, every time the hand needs to place in a precise certain fixed position – thus the camera can capture the same hand image. In this research the hand needs not to place in a precise certain fixed position. Wavelet technique is used to find the finger-to-finger valley in the past research (Han, 2004, Han et al., 2003). In this research, the developed recognition algorithm automatically calculate and check the finger-edge energy response signals and selected the high energy response signals to find the finger-to-finger valleys of the hand image automatically. The algorithm developed in this research finds the finger-to-finger valleys more accurately and more efficiently. This research amputates the finger from the hand image automatically and calculates the feature and shape of each individual finger image separately. This research uses the amputated finger to generate more original finger features – which contain more opulent data than the finger crease pattern (Joshi et al., 1998) and rude finger shape matching methods (Han, 2004, Han et al., 2003, Sanchez-Reillo et al., 2000). Implicit polynomials are very difficult to describe the finger shape by the power of seven polynomial functions. In the previous research, the palm-print (Han, 2004, Han et al., 2003), iris, fingerprint, face, and vein pattern (Lin & Fan, 2004) are also used to identify the different persons.

In this research, the new technique is used to extract the – thumb, index, middle, ring, and small fingers and to perform the person’s identification. The geometry descriptor is used to transfer geometry features of the finger image to another feature-domain for image-comparison. For reducing the number of finger-image-files in the system, one person’s entire finger images are placed in one file. Image subtraction is used to exam the difference of the two images. The hand are fixed each time when a picture is taken and one can assume that each time when the hand image is taken, the acquired finger images are the same as the previous acquired ones. Since the pictures are the same, after the fingers are extracted from the hand image, one can use the acquired fingers to identify different persons.

This paper consists of four sections. Section 2 extracts the finger images. Section 3 describes the geometry descriptor and image subtraction. Section 4 concludes this paper.