Human and Computer Vision

We cannot think of image processing without considering the human vi- sual system. This seems to be a trivial statement, but it has far-reaching consequences. We observe and evaluate the images that we process with our visual system. Without taking this elementary fact into considera- tion, we may be much misled in the interpretation of images.

The fi rst simple questions we should ask are:

• What intensity diff erences can we distinguish?

1.6 Human and Computer Vision                                                     19

 

a                                                    b

c                                                     d

Figure 1.14: Test images for distance and area estimation: a parallel lines with up to 5 % diff erence in length; b circles with up to 10 % diff erence in radius; c the vertical line appears longer, though it has the same length as the horizontal line; d deception by perspective: the upper line (in the background) appears longer than the lower line (in the foreground), though both are equally long.

 

• What is the spatial resolution of our eye?

• How accurately can we estimate and compare distances and areas?

• How do we sense colors?

• By which features can we detect and distinguish objects?

It is obvious that a deeper knowledge would be of immense help for computer vision. Here is not the place to give an overview of the human visual system. The intention is rather to make us aware of the elementary relations between human and computer vision. We will discuss diverse properties of the human visual system in the appropriate chapters. Here, we will make only some introductory remarks. A detailed comparison of human and computer vision can be found in Levine [109]. An excellent up-to-date reference to human vision is also the monograph by Wandell [193].

The reader can perform some experiments by himself. Figure 1.14 shows several test images concerning the question of estimation of dis- tance and area. He will have no problem in seeing even small changes in the length of the parallel lines in Fig. 1.14a. A similar area compar- ison with circles is considerably more diffi cult (Fig. 1.14b). The other examples show how the estimate is biased by the context of the im- age. Such phenomena are known as optical illusions. Two examples of estimates for length are shown in Fig. 1.14c, d. These examples show

20                                                                                      1 Applications and Tools

 

Figure 1.15: Recognition of three-dimensional objects: three diff erent represen- tations of a cube with identical edges in the image plane.

 

A                                                  b

   

Figure 1.16: a Recognition of boundaries between textures; b “interpolation” of object boundaries.

 

that the human visual system interprets the context in its estimate of length. Consequently, we should be very careful in our visual estimates of lengths and areas in images.

The second topic is that of the recognition of objects in images. Al- though Fig. 1.15 contains only a few lines and is a planar image not containing any direct information on depth, we immediately recognize a cube in the right and left image and its orientation in space. The only clues from which we can draw this conclusion are the hidden lines and our knowledge about the shape of a cube. The image in the middle, which also shows the hidden lines, is ambivalent. With some training, we can switch between the two possible orientations in space.

Figure 1.16 shows a remarkable feature of the human visual system. With ease we see sharp boundaries between the diff erent textures in Fig. 1.16a and immediately recognize the fi gure 5. In Fig. 1.16b we iden- tify a white equilateral triangle, although parts of the bounding lines do not exist.

From these few observations, we can conclude that the human vi- sual system is extremely powerful in recognizing objects, but is less well suited for accurate measurements of gray values, distances, and areas.

In comparison, the power of computer vision systems is marginal and should make us feel humble. A digital image processing system can

1.7 Components of an Image Processing System                            21

 

only perform elementary or well-defi ned fi xed image processing tasks such as real-time quality control in industrial production. A computer vision system has also succeeded in steering a car at high speed on a highway, even with changing lanes. However, we are still worlds away from a universal digital image processing system which is capable of “understanding” images as human beings do and of reacting intelligently and fl exibly in real time.

Another connection between human and computer vision is worth noting. Important developments in computer vision have been made through progress in understanding the human visual system. We will encounter several examples in this book: the pyramid as an effi cient data structure for image processing (Chapter 5), the concept of local orientation (Chapter 13), and motion determination by fi lter techniques (Chapter 14).

 

⇐ Предыдущая12345678910Следующая ⇒

Поделиться: