Takuma Shibahara

3D face recognition using passive stereo vision

This paper proposes a face recognition system that uses (i) passive stereo vision to capture three-dimensional (3D) facial information and (ii) 3D matching using a simple ICP (iterative closest point) algorithm. So far, the reported 3D face recognition techniques assume the use of active 3D measurement for 3D facial capture. However, active methods employ structured illumination (structure projection, phase shift, gray-code demodulation, etc.) or laser scanning, which is not desirable in many human recognition applications. A major problem of using passive stereo vision for 3D measurement is its low accuracy, and thus no passive methods for 3D face recognition have been reported previously. Addressing this problem, we have newly developed a high-accuracy 3D measurement system based on passive stereo vision, where phase-based image matching is employed for sub-pixel disparity estimation. This paper presents the first attempt to create a practical face recognition system based on fully passive 3D reconstruction.

A High-Accuracy Passive 3D Measurement System Using Phase-Based Image Matching

This paper presents a high-accuracy 3D (three-dimen-sional) measurement system using multi-camera passive stereo vision to reconstruct 3D surfaces of free form objects. The proposed system is based on an efficient stereo correspondence technique, which consists of (i) coarse-to-fine correspondence search, and (ii) outlier detection and correction, both employing phase-based image matching. The proposed sub-pixel correspondence search technique contributes to dense reconstruction of arbitrary-shaped 3D surfaces with high accuracy. The outlier detection and correction technique contributes to high reliability of reconstructed 3D points. Through a set of experiments, we show that the proposed system measures 3D surfaces of objects with sub-mm accuracy. Also, we demonstrate high-quality dense 3D reconstruction of a human face as a typical example of free form objects. The result suggests a potential possibility of our approach to be used in many computer vision applications.

A Sub-Pixel Stereo Correspondence Technique Based on 1D Phase-only Correlation

This paper presents a technique for high-accuracy correspondence search between two rectified images using 1D phase-only correlation (POC). The correspondence search between stereo images can be reduced to 1D search through image rectification. However, we usually employ block matching with 2D rectangular image blocks for finding the best matching point in the 1D search. We propose the use of 1D POC (instead of 2D block matching) for stereo correspondence search. The use of 1D POC makes possible significant reduction in computational cost without sacrificing reconstruction accuracy compared with the 2D POC-based approach. Also, the resulting reconstruction accuracy is much higher than those of conventional stereo matching techniques using SAD (sum of absolute differences) and SSD (sum of squared differences) combined with sub-pixel disparity estimation.

A Passive 3D Face Recognition System and Its Performance Evaluation

This paper proposes a three-dimensional (3D) face recognition system using passive stereo vision. So far, the reported 3D face recognition techniques have used active 3D measurement methods to capture high-quality 3D facial information. However, active methods employ structured illumination (structure projection, phase shift, moire topography, etc.) or laser scanning, which is not desirable in many human recognition applications. Addressing this problem, we propose a face recognition system that uses (i) passive stereo vision to capture 3D facial information and (ii) 3D matching using an ICP (Iterative Closest Point) algorithm with its improvement techniques. Experimental evaluation demonstrates efficient recognition performance of the proposed system compared with an active 3D face recognition system and a passive 3D face recognition system employing the original ICP algorithm.

A high-accuracy stereo correspondence technique using 1D band-limited phase-only correlation

This paper presents a technique for high-accuracy correspondence search between stereo images using 1D Band-Limited Phase-Only Correlation(BLPOC). The stereo correspondence search can be reduced to 1D search through image rectification. However, we usually employ block matching with 2D rectangular image blocks for finding the best matching point. In this paper, we propose the use of 1D BLPOC instead of 2D block matching for correspondence search. The use of 1D BLPOC makes possible significant reduction in computational cost without sacrificing reconstruction accuracy. The resulting reconstruction accuracy is comparable with 2D POC-based method, and is much higher than SAD/SSD-based methods.

A 3D Face Recognition System Using Passive Stereo Vision and Its Performance Evaluation

This paper proposes a three-dimensional (3D) face recognition system using passive stereo vision. So far, the reported 3D face recognition systems assume the use of active 3D measurement for 3D facial capture. However, active methods employ structured illumination or laser scanning, which is not desirable in many human recognition applications. Addressing this problem, we propose a 3D face recognition system that uses (i) AdaBoost-based face detection to automatically extract a face region from an image, (ii) passive stereo vision to capture 3D facial information, and (iii) 3D face matching based on a simple ICP (iterative closest point) algorithm. Experimental evaluation demonstrates an efficient recognition performance of the proposed system