Luis Diago

Verification of Models of Personal Perception of Faces by Closed-Eye Classifier Using Histogram Correlation

People rapidly form impressions from facial appearance, and these impressions affect social decisions. Data-driven, computational models are the best available tools for identifying the source of such impressions. However, the computational models cannot be accepted unless they have passed the tests of validation to ascertain their credibility.In this paper, the condition of the eyes of the person is used to validate the fuzzy rules extracted from the computational models. A simple and effective classifier is proposed to evaluate the closeness of the eyes during the evaluation of a small database of portraits. The experimental results show that closed-eyes can be detected only after the proposed shift of the normalized histogram is applied. Although it is very simple, the proposed classifier can achieve better accuracy than other state of the art classifiers. The relationship between the closeness of the eyes and the evaluation of the subjects is also analyzed.Copyright

Evaluation of Brain Models to Control a Robotic Origami Arm Using Holographic Neural Networks

In robotics, one of the most difficult task is to perform a precisely and fast movement of a robotic arm. For paper-folding robots, it is still extremely difficult to execute the required manipulations of the paper mainly because the difficulties in modeling and control of the paper. In this paper two control models are proposed to solve this problem. One of the best approaches comes from Neuroscience, where using a human’s brain inspired control system known as Cerebellar control model (CCM), precisely and fast movements of a robotic arm can be performed. In the CCM a Feedback controller motor command is used as a target signal to train an Artificial Neural Network (NN), and use the output of the NN as a Feed-forward signal. In this paper two training methods were evaluated in order to improve the behavior in CCM: the traditional Back propagation and a Holographic method.Copyright

A Soft-Computing Approach for Quantification of Personal Perceptions

Soft-computing forms the basis of a considerable amount of machine learning techniques which deals with imprecision, uncertainty, partial truth, and approximation to achieve practicability, robustness and low solution cost. This paper describes an application developed to understand what means a picture (portrait) to be Iyashi. The neuro-fuzzy quantification allowed extracting a set of 35 rules that describe the meaning of the word Iyashi to hundreds of users. Facial expressions of the subjects and their brain signals during the evaluation of the images have been explored to validate the obtained rules. The developed system allows discovering the rules that describe the preferences of users while exploring the space of possible design parameters so that the system predictions match the preferences of users. Interactive genetic algorithms (IGAs) have been used for the implementation of a color recommendation system following customer’s preferences. The combination of color and geometric shapes is also explored.

Folding Origami by Two Robotic Fingers

Folding origami is such a challenge for robotic operation. Generally, for human, they use 2 hands when folding and forming the shape from folding pattern. However, building a robotic system which is capable of folding origami like human is not simple, since people have dozens of freedoms in their hand, sensitive skin and binocular vision. In this paper, we consider the folding ability of a 2-robotic-arm system, each hand has 2 fingers, instead of 5 fingers as human hand. Firstly, the difficulty of folding patterns is analyzed through an origami model: origami cylinder. Then, the design of robot system and gripper mechanism is figured out. The behaviors of robot arms are determined by observing human folding process, image segmentation is applied to track hand stages during folding process. The robot movement in each stage is explained and simulated on MATLAB.Copyright

A Color Mapping Method for Decimated Model

In this paper we present a method for coloring the surface of the decimated mesh with an original texture without reparametrization. This approach combines the generation of the dense triangle mesh on each mesh element with the vertex color interpolation across the planes of the new generated triangles. The proposed method minimizes the texture distortion that is obtained by the displacement of points on the mesh during the decimation processing. The suggested approach provides transformation of an original model with texture at-tributes to the model with the decreased size and color-mapped surface.