Hierarchy of Image Processing Operations

Image processing is not a one-step process. We are able to distinguish between several steps which must be performed one after the other until we can extract the data of interest from the observed scene. In this way a hierarchical processing scheme is built up as sketched in Fig. 1.13. The fi gure gives an overview of the diff erent phases of image processing, together with a summary outline of this book.

Image processing begins with the capture of an image with a suitable, not necessarily optical, acquisition system. In a technical or scientifi c application, we may choose to select an appropriate imaging system. Furthermore, we can set up the illumination system, choose the best wavelength range, and select other options to capture the object feature of interest in the best way in an image (Chapter 6). 2-D and 3-D image formation are discussed in Chapters 7 and 8, respectively. Once the image is sensed, it must be brought into a form that can be treated with digital computers. This process is called digitization and is discussed in Chapter 9.

The fi rst steps of digital processing may include a number of diff erent operations and are known as image preprocessing. If the sensor has non- linear characteristics, these need to be corrected. Likewise, brightness and contrast of the image may require improvement. Commonly, too, co- ordinate transformations are needed to restore geometrical distortions introduced during image formation. Radiometric and geometric correc- tions are elementary pixel processing operations that are discussed in Chapter 10.

A whole chain of processing steps is necessary to analyze and iden- tify objects. First, adequate fi ltering procedures must be applied in order to distinguish the objects of interest from other objects and the back- ground. Essentially, from an image (or several images), one or more feature images are extracted. The basic tools for this task are averaging (Chapter 11), edge detection (Chapter 12), the analysis of simple neigh- borhoods (Chapter 13) and complex patterns known in image process- ing as texture (Chapter 15). An important feature of an object is also its motion. Techniques to detect and determine motion are discussed in Chapter 14.

Then the object has to be separated from the background. This means that regions of constant features and discontinuities must be identifi ed by segmentation (Chapter 16). This can be an easy task if an object is well distinguished from the background by some local features. This is, however, not often the case. Then more sophisticated segmentation techniques are required (Chapter 17). These techniques use various op- timization strategies to minimize the deviation between the image data and a given model function incorporating the knowledge about the ob- jects in the image.

16                                                                                      1 Applications and Tools

 

The same mathematical approach can be used for other image process- ing tasks. Known disturbances in the image, for instance caused by a de- focused optics, motion blur, errors in the sensor, or errors in the trans- mission of image signals, can be corrected (image restoration). Images can be reconstructed from indirect imaging techniques such as tomog- raphy that deliver no direct image (image reconstruction).

Now that we know the geometrical shape of the object, we can use morphological operators to analyze and modify the shape of objects (Chapter 18) or extract further information such as the mean gray value, the area, perimeter, and other parameters for the form of the object (Chapter 19). These parameters can be used to classify objects (classi- fi cation, Chapter 20). Character recognition in printed and handwritten text is an example of this task.

While it appears logical to part a complex task such as image process- ing into a succession of simple subtasks, it is not obvious that this strat- egy works at all. Why? Let us discuss a simple example. We want to fi nd an object that diff ers in its gray value only slightly from the background in a noisy image. In this case, we cannot simply take the gray value to diff erentiate the object from the background. Averaging of neighboring image points can reduce the noise level. At the edge of the object, how- ever, background and object points are averaged, resulting in false mean values. If we knew the edge, averaging could be stopped at the edge. But we can determine the edges only after averaging because only then are the gray values of the object suffi ciently diff erent from the background. We may hope to escape this circular argument by an iterative approach. We just apply the averaging and make a fi rst estimate of the edges of the object. We then take this fi rst estimate to refi ne the averaging at the edges, recalculate the edges and so on. It remains to be studied in detail, however, whether this iteration converges at all, and if it does, whether the limit is correct.

In any case, the discussed example suggests that more diffi cult im- age processing tasks require feedback. Advanced processing steps give parameters back to preceding processing steps. Then the processing is not linear along a chain but may iteratively loop back several times. Fig- ure 1.13 shows some possible feedbacks. The feedback may include non- image processing steps. If an image processing task cannot be solved with a given image, we may decide to change the illumination, zoom closer to an object of interest or to observe it under a more suitable view angle. This type of approach is known as active vision. In the framework of an intelligent system exploring its environment by its senses we may also speak of an action-perception cycle.

1.4 Image Processing and Computer Graphics                                 17

 

⇐ Предыдущая12345678910Следующая ⇒

Поделиться: