Pharmaceuticals
Quality control for the world's medicine
[breadcrumbs]?
Hameln Group
Just what the doctor ordered
Machine vision solutions for your pharmaceutical line
Virtually every aspect of pharmaceutical or supplement manufacturing benefits from machine vision, from drug or supplement synthesis to packaging, labeling and serialization. Horizon Imaging has the expertise you need to develop accurate, reliable, high-speed systems for inspection, sorting and packaging. We specialize in the optics, lighting and software tools you need to get the job done.
Case study
See how we engineered a solution for locating pills in a blister pack.
Put our expertise to work for you
The engineers at Horizon Imaging have extensive experience, expertise and resources in the following areas
Optical engineering
- Cameras
- Lighting technology
Real-time embedded software
- Image acquisition with frame grabbers
- High-speed image processing
- Custom classification algorithms
Ejection or separation
- Mechanical and electrical design of ejection device
- Integration to ejection devices you provide
User interface
- Intuitive and elegant touchscreen interfaces
- Database design
- Communication with external devices or sensors in your plant
Mechanical design
- Packaging for computers, power supplies and other electronics
- Product presentation
- Sanitation
- Mechanical interfaces to equipment in your plant
Challenging engineering problem? Contact us today.
Case study
BUILDING A BLISTER-PACK TEMPLATE
Blister pack How do you build an application to examine pharmaceuticals in a blister pack? The challenge is to identify pill zones. We want to do this automatically to reduce operator errors, and because the size of the image can vary depending on zoom and focus. So we devised software to automatically build an object template.
Creating a zone ring First we find the outer edge of the blister pack by histogramming the image and detecting edges. Then two disks are drawn. The first disk (yellow) covers the entire blister pack and the second (blue) covers the inside. The overlap of the two disks forms a ring, shown on the next slide.
Zone ring The smaller disk is assigned background. The portion of the larger disk that is not overlapped by the smaller disk is the object zone. We now need to divide the object zone into pill zones.
Cutting the ring into object zones Given the number of pills in the ring, the single zone ring is divided into pill zones by drawing a line from the center of the ring and through the outer edge at precise degrees, one line for each pill. The result is the appropriate number of pill zones.
Final template At this stage we have the final template; however, it may not be rotated optimally so that each of the object zones is directly over an object. To solve that issue we run a series of test rotations.
Template rotation The template is rotated in a series of small rotations, each time counting the number of nonbackground pixels in each zone. The peak count is remembered for each rotation along with the rotation value. The final rotation will be the peak value shown in image 3. We can now use the template to verify the content of each pill zone.
See how we do it
Click the numbered tabs to walk through our solution for locating objects in a blister pack.