How our innovation is original and how it fulfills a need in the market that hasn’t been addressed which increases productivity and leverages a novel technology.
Automated Inspection of tablets and capsules packed in blister in not a new requirement, but even today it is extremely challenging task for vision system designers. Since pharmaceutical companies are constantly coming-up with different colors of product (i.e. tablets and capsules) packed in various types of forming foil (i.e. Aluminum, PVC-Clear, PVC-Opaque, etc.)
Examples of few challenging products:
In addition to this pharm companies today requires high productivity with consistency in quality. So they are investing more and more on high speed machines but when it comes to inspections there is still a lag in productivity and consistency. One of the most important processes in handling vision systems is a teaching process. Teaching a new product in vision system is still a time consuming task and prone to human dependency specifically for bister inspection system. It requires expertise of users on every step, i.e. manually identifying of formed cavities, segmentation of tablet/capsule color, setting optimum tolerances to detect geometric and color defects. Also manual teaching in certain times is a time consuming process and also depends on user proficiency. Even after teaching there are various acceptance tolerances that user has to tune manually to get the optimum results.
After market survey of various blister inspection system available today and understanding pain points of users, our aim was to make this teaching process completely automatic including auto learning of acceptance tolerance. After a constant research and development efforts of 2 years, we developed an algorithm which works for most of the products packed in all types of forming foils. With this today all our customers are very happy with their productively increased drastically. E.g. certain products which took 7-8 hours of users for teaching products earlier, it just takes 2-3 minutes now, even though inspection consistency is maintained.
What are the unique features of this product/system/technology as it compares to existing solutions?
Blister pack inspection is all about color based segmentation of tablets and capsules, and then quantifying the segmented region by product geometry and color.
Since its inception in the 1980s, machine vision is constantly advancing in optical technology, processors, and software algorithms and making it easier for end-user to use it. so we talk about upcoming trends in machine vision.
Just like in other industries which are benefiting from rapid advancements in technology like big data, cloud, artificial intelligence (AI). Likewise these technologies will also hugely beneficial to manufacturing industries, the three key advances in machine vision for automation will be:
Day by day demand for bulk inspection is increasing which require larger area to be seen by the camera for inspection purpose. 1, 2 and 5 Megapixel cameras continue to lead market but we are also seeing considerable demand of higher resolution sensors such as 12-20 megapixels owing to the requirement of larger inspection area. Earlier multiple cameras were used to cater this requirement but using multiple camera increases a lot of error prone post processing on images which consume huge amount of processing power.
Measuring depth of on object or distance to the object has also turned out to be crucial which was earlier done by using multiple cameras placed at different viewing angles. Now the technology such as stereo vision, time of flight (tof) and leaser triangulation is supported by required advance hardware to meet the requirements.
Traditional methods are still widely used in most food industries due to the unavailability of smart alternatives. Traditional destructive methods are not suitable in today's hypercompetitive marketplace. Consequently, a cost-effective, efficient, rapid, and reliable method is required. In particular, there is a great interest in developing non-destructive optical technologies that have the capability of monitoring in a real-time assessment. Among them, hyper spectral imaging techniques have received ample attention. Hyper spectral imaging systems provide spatial and spectral details; therefore, these systems introduce new sensing facilities that enable improved inspection.
“fabulous machine that have all our senses, all our reasons and think just like we do – you have seen these machine in movies as a friend or foe, now fiction becomes reality”
AI is allowing enterprises to automate inspections that were previously only able to do manually. It efficiently solve complex inspection challenges that are cumbersome or time-consuming to do with traditional rule-based machine vision algorithms.
With deep learning, engineers can train a machine vision system to learn what is an acceptable or unacceptable defect from a data set of reference pictures rather than program the vision system to account for the thousands of defect possibilities.
For example, a pharmaceutical company’s systems
“Human vision has no meaning without a beautiful brain”
“Images from camera has no value without a powerful software”
The Irony is we still don’t know exactly how human vision works, but here is a example illustrating how we humans can do most complicated task with utmost ease.
So we can conclude that brain do well what computers do poorly, and vice versa. Human brain is the best learning machine and can also produce new thoughts / ideas whereas Computers are meant to perform repeated task.
Correlation between human eye and camera can be seen below:
Our understandings of visual information are highly developed. But for computer to understand the images captured by the camera are very difficult. Because we humans visualize an image as a whole while computer software works on pixels (i.e. the smallest unit of image). So below video clip will help us to visualize how difficult it is for humans to work in similar way as a computer dose.
Video 1: https://www.youtube.com/watch?v=NGGLFUuhXDQ
Video 2: https://www.youtube.com/watch?v=NkQ58I53mj
Video 3: Courtesy from Basler
Video 4: Courtesy of BBC