Posted on

What is Metrology Part 23 – Error and Perception

Margin of Error

After a significant amount of time dedicated to this series, I have made some interesting insights.  When you think of metrology and measurement, humans need to understand that we are faulty at what we do. It is difficult to have true precision in measurement. We are prone to error and degrees of various errors. Secondly, no one human has the same perception as another. This leads to various incongruities in the physical realm. We can think in terms of optics, general psychology, and a vast number of phenomena. So how do we escape faulty perception and human error? Well, that seems impossible, but I am going to venture into these topics to show how they affect measurement and metrology as a whole.

Margin of error is a statistic that shows the amount of sampling error due to random occurrences. When we have a large margin of error, there lies less confidence in the data we collect. In reference to metrology, one can think of a scanning system as our measuring apparatus. When operated by a human, various things and random occurrences can affect the margin of error within a laser scan. This can include an unsteady hand when scanning an item. One could also have a slightly unclean lens that may cause distortion within a 3D scan. The movement of a target for 3D scanning may also affect this as well. There are a slew of items that may cause a 3D scan to contain large margins of error.

Act of Perception

Perception is how we organize, identify, and interpret sensory information in order to understand or represent our environment. Perception includes the ability for us to receive signals that go through our nervous system. This results in physical or chemical stimulation of our sensory systems. This allows us to interpret and understand the information we are bombarded with on a daily basis. Examples of this include how vision occurs through light interacting with our eyes, how we are able to use odor molecules to interpret smell, as well as our general ability to detect sound through pressure waves within the air. Perception is denoted by the receiver though. This means their learning, memory, expectation, and attention are vital for how the signals are interpreted.

I bring these things up as it shines a light on a key difference between machines and humans. Machines have less working experience, expectation, and learning compared to humans. Being able to consistently distinguish a watch in 3D form is natural for most humans, but a machine can be thrown off by slight variations in form. A machine automated process may have less error in terms of pure measurement, but the interpretation of the data is still a difficult task for a machine.

Issues of Perception and Metrology

Perception is typically thought of in two forms:

  • Processing an input that transforms into information such as shapes within the field of object recognition.
  • Processing that is interloped with an individual and their own concepts or knowledge. This includes various mechanisms that influence one’s perception such as attention.

Through laser scanning, an individual is able to collect data on a physical product. This data needs interpretation for it to have tangible value. A computer device is not readily able to do so. So metrology is a field based on our innate error and psychology as humans. But that does not mean the field is useless, as we humans have an innate desire to make things quantifiable.

The post What is Metrology Part 23 – Error and Perception appeared first on 3DPrint.com | The Voice of 3D Printing / Additive Manufacturing.

Posted on

What is Metrology Part 13: Object Recognition

3D Perception

We as humans have faulty perception of the physical environment we live in. Although we are able to distinguish 2D items and 3D items, we do not have the ability to measure them in real time with numeric values. We need to use outside devices to assist us. We have discussed at length these topics within our metrology series, but today we will take a look specifically at a subsection of knowledge within this field and computer vision. With computer oriented object recognition, humans are attempting to make the world more precise through the lens of a computer. There are a variety of things that get in the way of precise object recognition.

Object recognition is defined as technology in the field of computer vision for finding and identifying objects in an image or video sequence. Humans have the ability to recognize objects with bare minimal effort, even though an image varies in different viewpoints. The image also varies when it is translated, scaled, and rotated. People are able to recognize images even when they are somewhat incomplete and missing critical information due to an obstruction of view. Humans use the power of gestalt psychology to do such. Gestalt psychology is defined as a German term interpreted in psychology as a “pattern” or “configuration”. 

Gestalt in Practice

Gestalt is based on understanding and perceiving the whole sum of an object rather than its components. This view of psychology was created to go against a belief that scientific understanding is the result of a lack of concern about the basic human details.

The ability for a computer to recognize parts and synthesize them into a larger body object is the main source of error within computer vision and object recognition. This task is extremely challenging for computer vision systems. One must understand that computers have immense capabilities in logically describing constituents or smaller parts, but adding them together consistently to form the basis of a larger item is still difficult. This is personally why I am not too worried about a robot takeover anytime soon. Many approaches to the task have been implemented over multiple decades.

Matlab and object  detection/recognition

For a computer to do sufficient object recognition there needs to be a ton of precision with identifying constituent parts. To do this, a computer relies on a vast amount of point cloud data. A point cloud is defined as a set of data points in space. Point clouds are usually produced by 3D scanners. With this point cloud data, metrology, and 3D builds can be created. An object can be recognized through using point cloud data to create a mesh. For us as humans, we are able to interpret that mesh within our 3D realm. However, computers are not that great at such interpretation. They just give us great and precise data to work with. It is important to note that computers are okay at object detection. This refers to being able to decipher a part or object within a larger scene. But when we place multiple parts into a scene or an item with a complex geometry, things become difficult for a computer to decipher. Hence we only use 3D scanners to grab point cloud data and not process what a 3D object is. 

Currently in terms of object recognition, computers can barely recognize larger scale items within a 2D setting. It will take a long time for computers to have the graphic capabilities to even decipher what an object would be in a 3D environment. For example, MATLAB is a powerful coding software used for large scale data processing, but computers require a large amount of machine learning and deep learning techniques to process 2D images. First these systems need to do this at a rate of 99.9% confidence before one can move on to 3D images. Humans are not necessarily 100% accurate in terms of processing images either, but they are still slightly more consistent than computer vision techniques. Overall I am interested in learning how to develop such technologies, and I wonder who are the people and organizations wrestling with these problems daily.

The post What is Metrology Part 13: Object Recognition appeared first on 3DPrint.com | The Voice of 3D Printing / Additive Manufacturing.

Posted on

What is Metrology Part 11: Computer Vision

In the previous article within our metrology series we took a look into what machine vision is as a whole and how it integrates within metrology. We also made a slight distinction in what machine vision is compared to computer vision. It is important to do so as these terms sometimes get mixed together as one term, but they are not necessarily the same. In this article, we will explore the definition of computer vision, its applications, and how it relates to metrology as a whole.

Doing Fun Stuff in Computer Vision

Computer vision is an interdisciplinary scientific field that deals with how computers can be made to analyze data from digital images or videos. From the perspective of engineering, it seeks to automate tasks that the human visual system can do.

Computer vision tasks include methods for acquiring, processing, analyzing and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information. This information is then used to make decisions through artificial intelligence. The transformation of visual images into descriptions of the world can interface with other thought human processes. This image comprehension can be seen as the understanding of symbolic information from image data using models constructed with the aid of geometry, physics, statistics, and learning theory. We have talked about this a bit more indepthly in terms of complex analysis and geometry previously in this series. 

As a scientific discipline, computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms, such as video sequences, views from multiple cameras, or multidimensional data from a medical scanner. Computer vision seeks to apply its theories and models for the construction of computer vision systems.

Some applications of computer vision include the following:

  • 3D reconstruction
  • Video tracking
  • Object recognition
  • 3D pose estimation
  • Motion Estimation 
  • Image Restoration

3D Reconstructed Truck

3D reconstruction is the process of capturing the shape and appearance of real objects. This process can be accomplished either by active or passive methods. If the model is allowed to change its shape in time, this is referred to as non-rigid or spatio-temporal reconstruction. Spatio-temporal reconstruction refers to 4D reconstruction as it is adding the 4th element of time into creating an object (x-position, y-position, z-position, and time). 

Video Tracking Example

Video tracking is the process of locating a moving object (or multiple objects) over time using a camera. It has many uses, some of which include: human-computer interaction, security and surveillance, video communication and compression, augmented reality, traffic control, medical imaging, and video editing. Video tracking is time consuming due to the amount of data that is contained in a video. The need for object recognition techniques in video tracking is very difficult as well. 

Object Recognition

Object recognition technology in the field of computer vision is used for finding and identifying objects in an image or video sequence. Humans have the ability to recognize a large amounts of objects in images with a lack of effort. We are able to do this despite the fact that the image of the objects may vary somewhat in different viewpoints, in many different sizes and scales, or even when they are translated or rotated. Objects can even be recognized when they are partially hidden from view. This task is still a challenge for computer vision systems. Many approaches to the task have been implemented over multiple decades.

3D pose estimation

3D pose estimation is the problem of determining the transformation of an object in a 2D image which creates a 3D object. One of the requirements of 3D pose estimation comes from the limitations of feature-based pose estimation. There exist environments where it is difficult to extract corners or edges from an image. To deal with these issues, the object is represented as a whole through the use of free-form contours.

Motion Estimation

Motion estimation is the process of determining motion vectors that describe a transformation from one 2D image to another; usually from adjacent frames in a video sequence. There lies a problem as the motion is in three dimensions but the images are a projection of the 3D scene onto a 2D plane. The motion vectors may relate to the whole image or specific parts, such as rectangular blocks, arbitrary shaped patches or pixels. The motion vectors may be represented by a translational model or many other models that can approximate the motion of a real video camera, such as rotation and translation in all three dimensions and zoom.

Image Restoration

Image Restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image. Corruption may come in many forms such as motion blur, noise and camera mis-focus. Image restoration is different from image enhancement in that the latter is designed to emphasize features of the image that make the image more pleasing to the observer, but not necessarily to produce realistic data from a scientific point of view. Image enhancement is when one wants to use software such as Adobe Photoshop or Adobe LightRoom. With image enhancement noise can effectively be removed by sacrificing some resolution, but this is not acceptable in many applications. 

Within our next articles we will be looking indepthly into the previously outlined topics and relate them to the field of metrology as a whole.

The post What is Metrology Part 11: Computer Vision appeared first on 3DPrint.com | The Voice of 3D Printing / Additive Manufacturing.