This module provides a set of functions that allow a wide range of measurements on binary image objects. These tools allow sorting out or counting special parts in the image. It can also be used to preprocess the image to find the location and orientation of objects which have to be classified or measured in the next step.
Many object measurement results can be obtained:
- Center of gravity
- Position of main axes
- Object histogram
- Feret diameter
- Euler number, etc.
Like the other modules, blob analysis is multidimensional. This enables highly advanced measurements, for example tracking the growth or change of objects over time, or calculating volumes in 3D images.
Blob analysis is a well-known technique to isolate objects and features of an arbitrary kind, analyze their shape or position, and classify them. It combines image binarization and connected component analysis for segmentation.
The innumerable applications of this powerful method relate to item counting, presence/absence check, placement control, part identification, flaw detection, defect characterization, morphometry...
To allow full control on the segmentation process, binarization is kept as an external preprocessing step. This allows to pre-filter by any means such as morphology in the gray-level or binary domains, using the base module or custom functions.
An extended range of geometric characteristics can be computed, dealing with:
- Pose: center of gravity and centroid, Feret and inertia angles
- Size: bounding box, ellipse of inertia, Feret diameters, fiber width and length
- Extent: surface, convex surface, polar distance, perimeter, convex perimeter
- Inside: Euler number, total and average hole surface, perforation
- Shape: central moments, roundness, roughness
- Density: autocorrelation, contrast, cooccurrence matrix, energy, entropy, histogram, histogram statistics, optical density...
When objects have been characterized, further processing can be focused on the relevant ones by checking if the measured values belong to given acceptance ranges. This way, clutter, noise and irrelevant items can be discarded. This selection process can be cascaded to narrow down the search of objects of interest.
In addition to standard pixel-based parameter computation, calibrated coordinates can be used. This means that reference axis can be placed anywhere in the image, scale factors and rotation angle specified, to yield real-world measurements.
Datenblatt / Datasheet mvIMPACT 3D Display
Datenblatt / Datasheet mvIMPACT Barcode
Datenblatt / Datasheet mvIMPACT Base
Datenblatt / Datasheet mvIMPACT Blob
Datenblatt / Datasheet mvIMPACT Color
Datenblatt / Datasheet mvIMPACT Data Matrix
Datenblatt / Datasheet mvIMPACT Focus
Datenblatt / Datasheet mvIMPACT Geometric Model Matcher
Datenblatt / Datasheet mvIMPACT Match
Datenblatt / Datasheet mvIMPACT Measure
Datenblatt / Datasheet mvIMPACT OCR
Datenblatt / Datasheet mvIMPACT
You can evaluate mvIMPACT SDK for 30 days free of charge once. Afterwards, you will need a licence! If you are using a dongle for licensing mvIMPACT, you have to use the latest USB dongle in combination with the 64bit version!
Nightly builds are tested exemplarily and should be tested by oneself before use!
Modifications possibles sans préavis, date 11/2011