Object Recognition Using a Multichannel Vision System
| Project/Area Number |
15500124
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Osaka Electro-Communication University |
|---|
Principal Investigator |
TOMINAGA Shoji Osaka Electro-Communication Univ., Professor, 総合情報学部, 教授 (10103342)
|
|---|
| Project Period (FY) |
2003 – 2004
|
| Project Status |
Completed (Fiscal Year 2004)
|
| Budget Amount *help |
¥3,500,000 (Direct Cost: ¥3,500,000)
Fiscal Year 2004: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 2003: ¥2,600,000 (Direct Cost: ¥2,600,000)
|
|---|
| Keywords | Vision system / Multichannel / Spectral image / Color / Object recognition / Reflection model |
|---|
| Research Abstract |
1.Estimation of reflection models of objects by using multichannel images
A method is proposed for estimating various parameters of a reflection model using both the image data and the range data of an object surface. A unified measuring system, combining a laser range and a multi-band camera system, is made for acquiring the 3D shape data and the spectral reflectance data of the object surface. First, the diffuse reflection component and the specular reflection component at every pixel are obtained using the observed images at two illumination directions and the surface normal vectors calculated from the range data. The spectral reflectance is then estimated from the diffuse reflection component. Next, the extracted specular reflection component is fitted to the specular function of the Torrance-Sparrow model.
2.Measuring and rendering of art paintings by using a multichannel vision system
We propose a method for measuring an art painting by using the simple imaging system of an RGB came
… More
ra and a light source, and rendering the painting as CG images under any conditions of illumination and viewing. The surface shape is considered as the rough plane with paints on a flat canvas. We capture some images of the same painting under different illumination directions. First, the surface normal is estimated from the diffuse component, based on a photometric stereo. Next, the surface-spectral reflectance is estimated from the RGB values for the diffuse component. Moreover, the Torrance-Sparrow model is used for image rendering.
3.Recognition of printed circuit boards by using a multichannel vision system
We propose a method for classifying object materials on a raw circuit board based on surface-spectral reflectance. The multi-spectral imaging system is composed of a liquid-crystal tunable filter, a monochrome CCD camera, macro-lens and a personal computer. We have shown that dielectric materials like plastics can be distinguished from metals based on the reflectance difference in changing illumination geometries. Then an algorithm is presented for classifying the objects into several circuit elements. Region segmentation results of the circuit board are demonstrated in an experiment using a real board. Less
|
Report
(3 results)
Research Products
(21 results)
