# What is the difference between image processing and computer vision?

What is the difference between image processing and computer vision? They are apparently both used in artificial intelligence.

The Wikipedia article related to computer vision gives, in my opinion, a good description of the field and its relation to image processing. Below, I will only cite the most relevant parts of the article.

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

The image data can take many forms, such as video sequences, views from multiple cameras, or multi-dimensional data from a medical scanner.

Sub-domains of computer vision include scene reconstruction, event detection, video tracking, object recognition, 3D pose estimation, learning, indexing, motion estimation, and image restoration.

The fields most closely related to computer vision are image processing, image analysis and machine vision. There is a significant overlap in the range of techniques and applications that these cover. This implies that the basic techniques that are used and developed in these fields are similar, something which can be interpreted as there is only one field with different names. On the other hand, it appears to be necessary for research groups, scientific journals, conferences and companies to present or market themselves as belonging specifically to one of these fields and, hence, various characterizations which distinguish each of the fields from the others have been presented.

Image processing and image analysis tend to focus on 2D images, how to transform one image to another, e.g., by pixel-wise operations such as contrast enhancement, local operations such as edge extraction or noise removal, or geometrical transformations such as rotating the image. This characterization implies that image processing/analysis neither require assumptions nor produce interpretations about the image content.

What is the difference between computer vision and image processing?

Computer vision is about gaining high-level understanding from images or videos. For example, object recognition, which is the task of identifying the type of objects (e.g. apples or humans) in an image, is a computer vision problem. Of course, this task requires a high-level understanding of the image, that is, an understanding of the image similar to the way humans understand visual inputs, given that an apple is a high-level object that is composed of atoms, can be green, etc. For example, a neural network that attempts to classify the type of object in an image (assuming, for simplicity, there is just one type of object) would be a computer vision technique. In computer vision, you receive an image as input and you can produce an image as output or some other type of information (e.g. the type of objects in the image).

On the other hand, image processing does not necessarily imply a high-level understanding of the image. Image processing is a subfield of signal processing but applied to images, which are $$2$$d signals (or functions of a fixed domain). So, for example, if you have a blurred or noisy image, the task of deblurring or denoising it is part of image processing. The typical tasks in image processing are filtering (e.g. using the Gaussian filter or the mean filter), noise removal, edge detection and color processing. In image processing, you receive an image as input and you produce another image as output.

However, note that, in many cases, to gain a high-level understanding of the images, you first need to e.g. denoise them, so you could use an image processing technique to partially solve a computer vision task. In this sense, computer vision is an interdisciplinary field.

To conclude, computer vision is not a subfield of image processing, given that image processing does not necessarily involve a high-level understanding of images. On the other hand, computer vision can use image processing techniques to gain a high-level understanding of images.

• Are images 2d signals though? Coloured images should appear 3D (CHW) to a computer. – DuttaA Jul 26 '19 at 2:36
• @DuttaA Images can be thought of as signal and sometimes vector-valued functions. – nbro Jul 26 '19 at 7:45