Joseph Czechowski

Mobile, contactless, single-shot, fingerprint capture system

In some applications such as field stations, disaster situations or similar conditions, it is desirable to have a contactless, rugged means to collect fingerprint information. The approach described in this paper enables acceleration of the capture process by eliminating an otherwise system and finger cleanup procedure, minimizes the chance of the spread of disease or contaminations, and uses an innovative optical system able to provide rolled equivalent fingerprint information desirable for reliable 2D matching against existing databases. The approach described captures highresolution fingerprints and 3D information simultaneously using a single camera. Liquid crystal polarization rotators combined with birefringent elements provides the focus shift and a depth from focus algorithm extracts the 3D data. This imaging technique does not involve any moving parts, thus reducing cost and complexity of the system as well as increasing its robustness. Data collection is expected to take less than 100 milliseconds, capturing all four-finger images simultaneously to avoid sequencing errors. This paper describes the various options considered for contactless fingerprint capture, and why the particular approach was ultimately chosen.

XIM: X-Ray Inspection Module for Automatic High Speed Inspection of Turbine Blades and Automated Flaw Detection and Classification

Under military manufacturing technology funding, a production prototype X-ray Inspection Module (XIM) has been established at General Electric Corporate Research and Development (GE-CRD) and delivered to Quality Technology (QT), General Electric Aircraft Engine Business Group (GE-AEBG). A company funded production unit has been built by GE-AEBG and delivered to the GE-AEBG manufacturing facility in Madisonville, Kentucky where it is in use in production. Computerized tomography (CT) and digital fluoroscopy (DF) images are produced with the system. The CT images provide an image cross-section, and the DF images are much like chest X-rays.The system was designed to automatically inspect and analyze flaws present in turbine blades. It was applied to two flaw types; each type in a different turbine blade. The image processing is performed on complex gray scale images with varying background. The XIM system may be used either automatically or in a manual mode with a trained operator to interpret the images and make quality decisions.

Real-time 3D part metrology using polarization rotation

This paper describes a real time, low cost part metrology method for capturing and extracting 3D part data using a single camera and no moving elements. 3D capture in machine vision is typically done using stereo photogrammetry, phase shifting using structured light, or autofocus mechanism for depth capture. These methods rely on expensive and often slow components such as multiple cameras, specialized lighting, or motion components such as motors or piezoelectric actuators. We demonstrated a method for 3D capture using only a single camera, birefringent lenses and ultra-fast electronic polarization switches. Using multiple images acquired at different polarization states and thus different focal distances, a high-resolution 3D point cloud of a test part was extracted with a good match to the ground truth data. This paper will describe the operation of the method and discuss the practical limitations.

A single lens with no moving parts for rapid high-resolution 3D image capture

There are many visual inspection and sensing applications where both a high resolution image and a depth-map of the imaged object are desirable at high speed. Presently available methods to capture 3D data (stereo cameras and structured illumination), are limited in speed, complexity, and transverse resolution. Additionally these techniques rely on a separated baseline for triangulation, precluding use in confined spaces. Typically, off the shelf lenses are implemented where performance in resolution, field-of-view, and depth of field are sacrificed in order to achieve a useful balance. Here we present a novel lens system with high-resolution and wide field-of-view for rapid 3D image capture. The design achieves this using a single lens with no moving parts. A depth-from-defocus algorithm is implemented to reconstruct 3D object point clouds and matched with a fused image to create a 3D rendered view.

Automated 3D IR defect mapping system for CZT wafer and tile inspection and characterization

In this paper, the design and evaluation of a 3D stereo, near infrared (IR), defect mapping system for CZT inspection is described. This system provides rapid acquisition and data analysis that result in detailed mapping of CZT crystal defects across the area of wafers up to 100 millimeter diameter and through thicknesses of up to 20 millimeter. In this paper, system characterization has been performed including a close evaluation of the bright field and dark field illumination configurations for both wafer-scale and tile-scale inspection. A comparison of microscope image and IR image for the same sample is performed. As a result, the IR inspection system has successfully demonstrated the capability of detecting and localizing inclusions within minutes for a whole CZT wafer. Important information is provided for selecting defect free areas out of a wafer and thereby ensuring the quality of the tile. This system would support the CZT wafer dicing and assembly techniques that enable the economical production of CZT detectors. This capability can improve the yield and reduce the cost of the thick detector devices that are rarely produced today.

A spoof detection method for contactless fingerprint collection utilizing spectrum and polarization diversity

The paper presents a spoof detection technique employing multi-spectral and multi-polarization imaging for a contactless fingerprint-capture system. While multispectral imaging has been proven to enable spoof detection for contact fingerprint imagers, these imagers typically rely on frustrated total internal reflection that requires a planar fingerprint, achieved by contact. The multispectral imaging method is based primarily on the difference in the spectral absorption profile between a real finger and a fake one. This paper will describe the expansion of this capability using blue and red light with contactless imaging in conjunction with polarization. This new method uses images at various rotated linear polarizations (each image representing a different value of specular and diffuse components), which are used to create the feature vectors representing the spectral and polarization diversity. The software extracts complex wavelet transforms (CWT) and FFT features from the images and builds a supervised learning method to train Support Vector Machine (SVM) classifiers. Experimental data was collected from a diversity of human fingers and silicon based phantoms molded from the corresponding humans. Fake and actual fingerprints were collected using individuals with a large diversity in skin tone, age, and finger dimensions. Our initial results, with an accuracy rate of at least 83%, are promising and imply that using the polarization diversity can enhance the spoof detection performance.