Koichi Sasakawa

Personal verification system with high tolerance of poor-quality fingerprints

A highly reliable personal verification system using fingerprint images has been developed. Various image enhancement techniques including a directional spatial filter and local thresholding for each point are applied to improve the quality of noisy and unstable images and to extract the feature data as accurately as possible. This process is performed by our special hardware for rapid image processing operations. In the matching process we propose a new algorithm combining the coarse matching of ridge direction data with the precise matching of minutia data to achieve registration efficiently. This system provides high reliability and a real-time response at reasonable cost.

Multiple-person tracker with a fixed slanting stereo camera

This work presents a method for tracking multiple persons in a room by a stereo camera. If the ceiling of a building is not high enough, the camera needs to be located at low height. This camera location causes the problem of the significant view changes of the person in the image and each person consecutively occludes the other. We propose a method that projects the 3D variable voxels onto the floor, and tracks their peaks in order to ignore the view changes. The voxels vary along with the distance from the camera, so as not to be influenced by the stereo measurement accuracy. In addition we define repulsive forces between trackers to avoid collisions each other. The experimental results using real images show that our method is effective for the above camera location.

Fingerprint Authentication Device Based on Optical Characteristics Inside a Finger

Fingerprint is the most popular modality that is widely used in various authentication applications; PC logon, gate access control systems, and so on. The reason can be considered that fingerprint can achieve the best balance among authentication performance, cost, size of device, and ease of use. However, most of fingerprint authentication devices have some problems to be solved. One is that captured images are easily affected by the condition of finger surface and it can degrade authentication performance. The other is that the problem of impersonation by artificial gummy fingers has been pointed out. To solve those problems, we developed a new fingerprint authentication device that has a novel sensing principle. This device forms a image of fingerprint pattern based on optical characteristics of a finger’s interior by scattered transmission light. The images so obtained are unaffected by the condition of finger surface such as dry or moist fingers or operating environment, and enable stable authentication processes. And it can differentiate between real fingers and fake gummy fingers made from gelatin or other material using optical characteristics. Because this device utilizes the optical characteristics inside a finger, it has possibility to achieve higher authentication performance by combining multiple characteristics of a finger’s interior as a modality. In this paper, we describe the sensing principle and process algorithm of this device.

Characteristics of the Identification Algorithm Using a Matching Score Matrix

Biometrics authentication can be achieved by either verification or identification. In terms of convenience, identification are superior since a user does not have to input his/her ID number. However, it must be capable of searching the database storing user enrollment templates at high speed. To meet this need, we proposed an identification algorithm. In this paper, we describe our proposed method and discuss its characteristics of response speed using some simulation results. It is shown that response speed depends on the way to select enrollment data.

Multiple-Person tracking using a plan-view map with error estimation

In this paper we describe a new method for detecting and tracking multiple persons with a stereo camera. The method is based on the idea of the plan-view map, i.e., the 2D histogram of projected 3D measurements from the camera. It estimates the statistical feature in an optimal window, e.g., a rectangular region, on the histogram, considering stereo measurement error, human breadth, and height. Then, it measures the actual statistical feature in the same window on the input histogram and compares estimated feature with measured one to detect and track persons. Experimental results show that our method can achieve higher performance than a normal plan-view map.

Detection of small moving object by optical flow

Deals with a method of detecting small moving objects in an image sequence. Although it is difficult to recognize small objects in a single image, if they are moving in an image sequence, it is easy to detect them, no matter how small they are. In order to detect small objects with robotic eyes, The authors propose a new interpretation of optical flow. If a small moving object exists in the scene, a pair of feature points appear. The authors call these points the contraction point and the diffusion point. The paper proposes an extraction method for these points.<<ETX>>

A method for threshold selection in binary images using mean adjacent-pixel number

This paper proposes a method of selecting an appropriate adaptive threshold in binarization (0 or 1) of a gray-level image. A measure representing compactness of a connected component in an image, “the mean adjacent-pixel number,” is introduced. The best threshold is determined by taking the maximal of this measure. The method is applied successfully to actual gray-level images. The results show that appropriate thresholds can be obtained even for difficult images (e.g., a small object in a noisy and low-contrast image) which are less successful in conventional adaptive methods (e.g., the gray-level histogram method). Conventional methods using an adaptive threshold generally have a shortcoming in that the amount of computation is proportional to the number of thresholds. This paper also proposes a method to calculate the mean adjacent-pixel number at a high speed by combining the rank filters and histograms so that the amount of computation becomes independent of the number of thresholds.

Optimization of illuminating system to detect optical properties inside a finger

Biometrics performs personal authentication using individual bodily features including fingerprints, faces, etc. These technologies have been studied and developed for many years. In particular, fingerprint authentication has evolved over many years, and fingerprinting is currently one of worlds most established biometric authentication techniques. Not long ago this technique was only used for personal identification in criminal investigations and high-security facilities. In recent years, however, various biometric authentication techniques have appeared in everyday applications. Even though providing great convenience, they have also produced a number of technical issues concerning operation. Generally, fingerprint authentication is comprised of a number of component technologies: (1) sensing technology for detecting the fingerprint pattern; (2) image processing technology for converting the captured pattern into feature data that can be used for verification; (3) verification technology for comparing the feature data with a reference and determining whether it matches. Current fingerprint authentication issues, revealed in research results, originate with fingerprint sensing technology. Sensing methods for detecting a persons fingerprint pattern for image processing are particularly important because they impact overall fingerprint authentication performance. The following are the current problems concerning sensing methods that occur in some cases: Some fingers whose fingerprints used to be difficult to detect by conventional sensors. Fingerprint patterns are easily affected by the fingers surface condition, such noise as discontinuities and thin spots can appear in fingerprint patterns obtained from wrinkled finger, sweaty finger, and so on. To address these problems, we proposed a novel fingerprint sensor based on new scientific knowledge. A characteristic of this new method is that obtained fingerprint patterns are not easily affected by the fingers surface condition because it detects the fingerprint pattern inside the finger using transmitted light. We examined optimization of illumination system of this novel fingerprint sensor to detect contrasty fingerprint pattern from wide area and to improve image processing at (2).

Analysis of response performance characteristics for identification using a matching score generation model

To make person authentication systems be more useful and practical, we have developed an identification algorithm, and also showed that the authentication accuracy depends on response performance. Current identification algorithm employs a comparison computation function that is optimized for one-to-one comparison. By optimizing a comparison computation function, however, it might be possible to improve response performance. In this paper, we describe design guidelines for a comparison computation function for improving the response performance of the identification. To show the guidelines, we clarify the relation between the characteristics of a matching score distribution and response performance using a matching score generation model, and also demonstrate the effectiveness of the design guidelines with a simulation using an example of another comparison computation function.