Hitoshi Imaoka

A Complex Cell–Like Receptive Field Obtained by Information Maximization

The energy model (Pollen & Ronner, 1983; Adelson & Bergen, 1985) for a complex cell in the visual cortex is investigated theoretically. The energy model describes the output of a complex cell as the squared sum of outputs of two linear operators. An information-maximization problem to determine the two linear operators is investigated assuming the low signal-to-noise ratio limit and a localization term in the objective function. As a result, two linear operators characterized by a quadrature pair of Gabor functions are obtained as solutions. The result agrees with the energy model, which well describes the shift-invariant and orientation-selective responses of actual complex cells, and thus suggests that complex cells are optimally designed from an information-theoretic viewpoint.

Percolation transition in two-dimensional ±J Ising spin glasses

The percolation properties of geometrical clusters are investigated for the Ising spin glasses in the square and triangular lattices with the asymmetric weights of ferromagnetic and antiferomagnetic bonds. By Monte Carlo simulation, we obtain the phase diagram of the percolation transition temperature as a function of the weight of ferromagnetic bonds. At each transition temperature, we estimate the critical exponents ν and γ which agree well with those exponents belonging to the universality class of the random bond percolation except for the pure ferromagnetic case.

An algorithm for the detection of faces on the basis of Gabor features and information maximization

We propose an algorithm for the detection of facial regions within input images. The characteristics of this algorithm are (1) a vast number of Gabor-type features (196,800) in various orientations, and with various frequencies and central positions, which are used as feature candidates in representing the patterns of an image, and (2) an information maximization principle, which is used to select several hundred features that are suitable for the detection of faces from among these candidates. Using only the selected features in face detection leads to reduced computational cost and is also expected to reduce generalization error. We applied the system, after training, to 42 input images with complex backgrounds (Test Set A from the Carnegie Mellon University face data set). The result was a high detection rate of 87.0, with only six false detections. We compared the result with other published face detection algorithms.

Real-time face recognition demonstration

In recent years there have been great expectations of biometric authentication in view of increasing vicious crimes and terrorist threats. Face recognition is expected to be applied widely not only to security applications but also to image indexing and natural user interfaces. Accuracy of face recognition has been improved steadily in these years, but further improvements are demanded to meet performance requirements of these applications. We participated in Multiple Biometric Evaluation Still test conducted by National Institute of Standards and Technology (NIST) in 2010. In this evaluation, our algorithm achieved the best performance among all participants, with the highest identification rate of 95% among 1.8 million enrolled population, the lowest false match rate of 0.3% at false non-match rate 0.1%. In this demonstration, we show a real-time face recognition system using the above algorithm.

Topological Expression for Frustration in Antiferromagnetic Triangular Ising Model

A duality of the antiferromagnetic triangular Ising model, a fully-frustrated model, is investigated. Using Onsagers recipe, a dual model with complex coupling constants on a honeycomb lattice is obtained. By Kasteleyn and Fortuins transformation of the partition function of the dual model, we find a percolation system whose cluster sizes are restricted to be even. This is a new realization on the frustration of the original Ising model, which reflects a dimer character of frustrated spin clusters. Those results are extended to the Potts model.

Fast k-Nearest Neighbor Search for Face Identification Using Bounds of Residual Score

A novel fast k-nearest neighbor (k-NN) search method is proposed for the face identification task. It is well suited for this task because (1) it works well with high dimensionality, (2) it can be used with various similarity scores such as inner product, Euclidean distance, and correlation coefficient, (3) it can achieve not only fast exact k-NN search but much faster approximate search, and (4) it does not require any training or special data structure, resulting in low maintenance cost for the target database. Similarity scores between query and target samples are aggregated sequentially along with their dimensions, and target samples with no possibility of being included in k-NNs are rejected. The possibility is evaluated on the basis of the upper and lower bounds of the score for residual dimensions. Experimental results for a face database demonstrated that the proposed method achieves equal or better accuracy than other methods and is ten times faster than an exhaustive search with no degradation in the rank-k identification rate.

Fast and accurate scale estimation method for object tracking

Many of the existing tracking methods do not estimate the object scale (width, height), only the location (x, y). In this paper we present a method which can accurately estimate the object scale given the location. The proposed approach works by cascading two methods together; such that each method refines the estimate by removing the false scale samples. Our method does not depend on the tracking technique and can be applied with any tracking system. We apply our approach to an existing tracker and compare the performance on benchmark sequences. The proposed method outperforms the existing tracker, while hardly affecting the speed.

Fast and accurate personal authentication using ear acoustics

This paper presents a biometric personal-authentication method that exploits acoustic characteristics of human ears. It transmits a probe signal into the ear and receives its reflection, which contains personal identity information about the shape of the ear canal. Based on a study of effective and efficient acoustic feature representation and the use of audio equipment suitable for acquiring features with low within-individual variability, the proposed method achieves a promising equal error rate of 0.97% with only 12 feature components. A prototype system for Android smartphones is also presented.

Occlusion handling in feature point tracking using ranked parts based models

A method for feature point tracking with partial occlusion handling is proposed. Occlusion causes distortion of entire face shape and not just the occluded part. To address this multiple models are learnt using regression, each aligning some part of the complete feature point set. A ranking SVM is then used to select the best feature points from among the aligned parts. The proposed method gives improved results compared to state of the art methods.

Large-Scale Face Recognition on Smart Devices

Most of highly accurate face recognition methods are not suitable for real-time requirement in smart devices which have computational limitations. In this demonstration, we exhibit a face recognition application, in which only essential facial features from images are used for personal identification. In the algorithm used in this application, the face feature size is dramatically compressed into 512 bytes per face in spite of high recognition rate, a false rejection rate of 1.6% at false acceptance rate of 0.1% on identification photos. Consequently, computational cost for face matching is reduced dramatically and the system achieves 1.16 million times matching/second in dual-core 1.5GHz ARM processor. The demonstration on the smart device shows a high recognition performance and the feasibility for diverse applications.