What is Computer Vision and Machine Vision

Computer vision describes the ability of computers or subsystems to identify

objects, scenes and activities in images. To this end, technologies are used

with the help of which the complex image analysis tasks are divided among

as small sub-tasks as possible and then computed. These techniques are

applied to recognise individual edges, lines and textures of objects in one.

Classification, machine learning and other processes, for example, are used

to determine whether the features identified in an image probably represent

an object already known to the system.

Computer vision has multifaceted applications, among them the anal-

ysis of medical imaging to improve prognoses, diagnoses and treatment

of diseases or facial recognition on Facebook, which ensures that users are

automatically recognised by algorithms and are suggested for tags. Such sys-

tems are already used for security and surveillance purposes for the identi-

fication of suspects. In addition, e-commerce companies such as Amazon

are working on systems with which specific products can be identified on

images and subsequently be purchased directly online. Whilst researchers in

the field of computer vision are working on the aim of being able to utilise

systems independent of the environment, with machine vision, sensors are

used with the help of which relevant information can be captured within

restricted environments. This discipline is technically mature to the extent

that it is no longer part of ongoing informatics research, but part of sys-

tem technology today. At the same time, it is less a matter of recognising

the meaning or content of an image but of deriving information relevant for

action.

Comments

What is Machine Learning

The term machine learning (ML) as a part of artificial intelligence is ubiq- uitous nowadays. The term is used for a wide number of various appli- cations and methods that deal with the “generation of knowledge from experience”. The well-known US computer scientist Tom Mitchell defines machine learning as follows: A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E (Mitchell 1997). An illustrative example of this would be a chess computer program that improves its performance (P) in playing chess (the task T) by experience (E), by playing as many games as possible (even against itself ) and analysing them (Mitchell 1997). Machine learning is not a fundamentally new approach for machines to generate “knowledge” from experience. Machine learning technology was used to filter out junk e-mails a long time ago. Whilst spam filters that tack- ...

Possible Limitations of AI-Based Bots

The examples above already show the present-day potential of AI-based bots. At present, these systems are still in an early stage and still have certain limitations and potentials for optimisation. Twitter Bot Tay by Microsoft Most bots at present are reactive service bots. Engagement bots that actively interact with the users as market and brand ambassadors go one step further. The most famous example here is the chatbot Tay by Microsoft. Microsoft removed Tay from the web apologetically within one day. The example shows that the uncontrolled training of bots by the community can lead to fatal consequences. AI systems still have to learn ethical standards. It thus becomes apparent that even bots require a kind of guideline. Like a journalist has to observe editorial guidelines, bots have to observe certain standards. The next generation of AI-based bots must control and create the possible room for communication. IBM Watson has been able to celebrate quite a few respectable resul...

Random Forest Classifier

The algorithm gradient boosted regression trees, also called random forests, belong to the ensemble learning methods This classifier uses an ensemble of weak regression trees that have a low hit quota when considered in isola- tion. The quality of the prediction can be improved significantly when vari- ous trees are trained with different parameters or samples. The results of the individual trees are aggregated to a total result which then enables a more balanced and high-quality prediction. The so-called bagging triggered a boom of the traditional regression trees. As aggregation, either a majority vote or a probability function is chosen (Fig. 5.5). The lead prediction generates high-conversion leads because • The entire spectrum of information available about a company is inte- grated into the decision-making; • The data is highly topical and without bias; • The random forest is capable of abstracting complex correlations in the data; and • The method learns iteratively from t...

Tech & Fun

Search This Blog