Hiroyuki Shimai

Efficient face detection from news images by adaptive estimation of prior probabilities and Ising search

This paper presents an efficient method to detect faces from image sequences such as news or visual surveillance. To speed up the search, the prior probabilities of the face locations in the image are adaptively estimated and are used in the Ising search algorithm. The search points in the Ising search are selected depending on the estimated prior probabilities. The information obtained by the previous search points in the given image is effectively utilized through spin flip dynamics of the Ising search. If a face is found, the prior probabilities are updated with forgetting. This makes adaptation to the changes of the environment possible. The proposed search method was applied to images captured in the news. The proposed method is about 10 times faster than Ising search method without prior probabilities estimation.

Gaze control on virtual active vision system with binocular fish-eye lenses

A human continuously directs his eyes toward interesting points to recognize an object. Such eye movement or visual attention plays an important role in human vision. To simulate such eye movements, the paper proposes a virtual active vision head with binocular fish-eye lenses. Moving objects are detected within the wide angle of view obtained through the fish-eye lens by comparing the input image with the background image estimated by an adaptive M-estimator. The location of the moving object is used as a visual cue to achieve the saccadic eye movement. The proposed virtual active vision system was implemented on a PC cluster. Two PCs are used to capture images through the left and right fish-eye lenses and a PC with four processors is used for image processing. Real time gaze control is achieved on the proposed virtual binocular active vision system.

Construction of Integrated Mechanical Simulation Model of Whole Body for Alive Human

We are aiming at the mechanical simulation intended for the human body. The targeted mechanical simulation is structural mechanics (bone and soft tissue), fluid dynamics (blood flow), and kinetic (movement of the body). It constructs the simulation model of the whole body that can unitedly do these analyses. Moreover, it includes shape and the mechanical property in this model for the human body to be alive. We took a picture of X-ray CT and MRI for the volunteer. It created the data of 1mm voxel based on information of which it took a picture by X-ray CT. It can identify the soft tissue from the data of MRI. However, it has the spatial resolution and the problem of the distortion of the space, and it cannot construct the model as it is. We matched information on Xray CT and MRI, and constructed the whole body model. In addition, it can request the Young’s modulus of the bone in the measurement of the mechanical property value according to the X-ray transmission rate. We developed the automated system by which it requested the shape of the whole body and the Young’s modulus of the bone from transmission factor of X-ray CT. We had developed system was able to create VCAD data of the whole body of the human body. VCAD system is an integrated system of CAD,CAM,CAE. In this human body model we can manufacture the structure analysis, the flow analysis, and the implant constructed.

Multilevel autoregressive models for planar shape

In this paper we extend the autoregressive (AR) model to the multilevel AR model with wavelet transformation, in order to get the AR coefficients at each level as a set of shape descriptors for every level. To get the multilevel AR model, we use the wavelet transformation such as Haar wavelet to a boundary data. Then real AR and complex-AR (CAR) models are adopted to the multilevel boundary data of a shape to extract the features at each level. Furthermore we present the relation of the autocorrelation coefficients between adjacent resolution levels to elucidate the relation between AR model and wavelet transformation. Some experiments are also shown for the multilevel AR and CAR models with a certain similarity measure.