| Representative Projects in Machine Vision | |
![]() |
Indirect Quantification of Cotton Fiber Maturity We are studying the interaction of light with individual cotton fibers in high-resolution images in order to extract, among other features, fiber shape information for the quantification of cotton fiber maturity.
|
![]() |
Accurate Length Measurement of Multiple Cotton Fibers We are developing an algorithm that is shown to produce highly accurate fiber length measurements, while invariant to fiber orientation, shape, inter-fiber intersections, and intra-fiber crimps and crossovers. |
![]() |
Combined Measurement of Fabric Stain Release & Dimensional Changes We have developed a novel unsupervised, statistical approach for the detection and localization of a chromatic defect (in this case, a stain) in a uniformly textured background (in this case, the fabric). We are also working on an alternative approach for the assessment of fabric stains that is based on deformable contours. These efforts will be combined with our earlier work to develop a system that can measure fabric stain release and dimensional changes simultaneously. |
![]() |
Automatic Assessment of Fabric Wrinkles We have developed a unique system for the measurement and grading of fabric wrinkles. The system uses a structured-light acquisition system and an algorithm based on the facet model to accomplish its goals. |
|
Representative Projects in Medical Imaging |
|
![]() |
Interactive Image Segmentation Interactive Computer Vision, in general, and Interactive Image Segmentation, in particular, are major focus areas in our research. We are currently applying some of our approaches in these areas to the segmentation of cervix images. |
![]() |
Morphometry of Cervical and Lumbar Vertebrae We continue to develop an extensive tool under Matlab that is capable of segmenting and characterizing the lumbar and cervical vertebrae from digitized x-ray images of the spine. The tool is comprised of customized shape-based segmentation algorithms. |
![]() ![]() |
Detection of Bifurcated Edge As a part of the segmentation tool described above, we have developed a novel approach for the detection of double edges in the x-ray images of lumbar vertebrae. This approach is based on directional gradient vector flow (DGVF) snakes, which we call Pressurized Open DGVF Snakes.
|
![]() ![]() |
Quantification of Gallbladder Contractility We are developing a method for the segmentation of gallbladder from 3D ultrasound images. The segmented objects will be used to measure the change in the volume of the organ over time. |