Automatization in the design of image understanding systems
Contents
1. lt Ramos Satie imo Fapa Bakana iag durchgef hrt Pazaxtits Objects Objekte deren Rayianen vom baitet werden mehan tEmgbe Objcktparamster Topel Fete Objekta deron Region des Ergiheis der Diktien Oparntinn und war aee tee Oaa doe Rogan gc Dn Dien ci A mage brag jekiparamneter Fig 12 Section of the online user manual 41 explanations into the manual In combination with PROLOG as the host lan preset HERE Prandikate guage the help module is currently enhanced by ie more functionality One direction is to help the Graphik afd user to understand why an error occurred It traces ome Sesertpt elaenif2 back the chain of PROLOG clauses to identify the Yarkaale Deinen place where a chain of computations and operator Vorsteleate dietion slay applications caused the generation of an invalid direction situation Here debugging can be done on the same abstract level as programming eu init 1 sx The other direction is to analyse the actions which ttre partikel 7 2 a the user has performed during a session in the ne PROLOG and in the HORUS system Klotz 89 Here the help systems monitors the user input and is therefore able to give more precise advice in case the user needs help or an error message comes up A first step in the realisation of this concept is the module operated by the window of Fig 13 It provides the user with a complete list of predicates he has defined in field 2 and HORUS operators2. Construction of Image Processing Procedures by Sample Figure Presentation Proceedings 8th International Conference on Pattern Recognition 1986 Paris 586 588 Hesse Klette 88 R Hesse R Klette Knowledge Based Program Synthesis for Computer Vision Journal of New Generation Computer Systems 1 1 1988 63 85 Ikeuchi Kanade 88 Katsushi Ikeuchi Takeo Kanade Automatic Generation of Object Recognition Programs Proceedings of the IEEE Vol 76 No 8 August 1988 1016 1035 Klotz 89 K Klotz Uberwachte Ausfiihrung von Prolog Programmen Proceedings 2nd IF Prolog User Day Chapter 9 Miinchen June 16 1989 Langer Eckstein 90 W Langer W Eckstein Konzept und Realisierung des netzwerkfahigen Bildverarbei tungssystems HORUS Proceedings 12th DAGM Symposium R E GroBkopf Ed Springer Verlag Berlin 1990 Liedike Ender 86 C E Liedtke M Ender A Knowledge Based Vision System for the Automated Adaption to NewScene Contents Proceedings 8th International Conference on Pattern Recognition 1986 Paris 795 797 Liedtke Ender 89 C E Liedtke M Ender Wissensbasierte Bildverarbeitung Springer Verlag Berlin 1989 Matsuyama 89 T Matsuyama Expert Systems for Image Processing Composition of Image Analysis Processes in Computer Vision Graphics and Image Processing 48 1989 22 49 Messer 92a T Messer Model Based Synthesis of Vision Routines in Advances in Vision Strategies and Applications C Archibal
3. Springer Verlag 406 410 Radig 84 B Radig Image sequence analysis using relational structures Pattern Recognition 17 1984 161 167 Risk B rner 89 C Risk H Borner VIDIMUS A Vision System Development Environment for Industrial Applications in W Brauer C Freksa Eds Wissensbasierte Systeme M nchen Oct 1989 Procee dings Springer Verlag Berlin 477 486 Vernon Sandini 88 D Vernon G Sandini VIS A Virtual Image System for Image Understanding Research in Software Practice and Experience 18 5 1988 395 414 Weymouth etal 89 T E Weymouth A A Amini S Tehrani TVS An Environment for Building Knowledge Based Vision Systems in SPIE Vol 1095 Applications of Artificial Intelligence VI 1989 706 716
4. can be described in a formal way or even better by demonstrating examples and eventually counterexamples of what kind of image feature has to be detected a configura tion module could be able to choose an optimal sequence of optimal parameterized operators automatically from the operator base First results in this direction are reported by Ender 85 Haas 87 Hasegawa et al 86 Hesse Klette 88 Ikeuchi Kanade 88 Messer Schubert 91 Liedtke Ender 89 Automatic Adaption If a part of an image understanding problem is given by supplying a generic model e g of the real world object to be detected or by showing representative exam ples it becomes essential to guarantee the transfer the problem solution based on this descrip tion to the real operation of the final system To do this with a minimum of the engineer s inter vention an automatic adaption or specialization of the generic description to the varying situa tions during operation has to be included into the design of the toolbox which in turn has to include this capability into the runtime system Ender Liedtke 86 Pauli et al 92 Competence Awareness If a machine vision system is able to adapt itself to slightly vary ing conditions it should be able to detect when its limited capabilities to follow changing situa tions is exceeded To be able to report this is a prerequisite for controllable reliability Then it can ask for human intervention from manual paramet
5. composed of objects constructed as Fig 19 First frame of an image sequence a part of hierarchy and related by constraints Fickenscher 91 The more complex such models are the more difficult it will be to attempt a generalizable description A typical situation exists in an image sequence with moving objects Nitz Pauli 91 Here the model of an region in each image has to follow the expected or pre dicted changes Varying attributes are area boundary shape grey value position contrast to background etc as well as relations such as below darker between inside etc In the example of Fig 19 which shows the first frame of a sequence a man is moving his right leg A part of hierarchy can easily be constructed guided by the segmentation result of Fig 20 A model of the right leg is obtained by specifying an elongated nearly vertical region whose centre of gravity is left of a simi lar region both connected to a more compact region which is above Fig 22 consists of an overlay of Fig 20 and the isolated right leg in dif ferent positions For matching the model with the image structure maximal cliques totally connected subgraphs in an assignment graph are computed Radig 84 The nodes of the assignment graph are formed from poten tially corresponding pairs of image and model elements Edges in this graph link relational consistent assignments This approach is able to establish correspondence even in the case of deviations
6. Automatization in the Design of Image Understanding Systems Bernd Radig W Eckstein K Klotz T Messer J Pauli l Bayerisches Forschungszentrum f r Wissensbasierte Systeme 2 Institut f r Informatik IX Technische Universit t M nchen Orleansstra e 34 D 8000 M nchen 80 Abstract To understand the meaning of an image or image sequence to reduce the effort in the de sign process and increase the reliability and the reusability of image understanding systems a wide spectrum of AI techniques is applied Solving an image understanding problem corresponds to specifying an image understanding system which implements the solution to the given problem We describe an image understanding toolbox which supports the design of such systems The tool box includes help and tutor modules an interactive user interface interfaces to common procedu ral and AI languages and an automatic configuration module 1 Introduction Machine Vision and in general the interpretation of sensor signals is an important field of Ar tificial Intelligence A machine vision system coupled with a manipulator is able to act in our real world environment without the human being in the loop Typical tasks of understanding the semantics of an image involve such applications as medical diagnosis of CT images traf fic monitoring visual inspection of surfaces etc Given an image understanding problem to be solved for a specific application usually a long process
7. SP and even AI shells to access these structures System Architecture Typical modules in a toolbox should be the internal data management system an external image database management system device drivers operator base net work communication subsystem to allow for remote access and load sharing within a distrib uted environment procedural interface with extensions specialized for each host language graphical user interface command history with undo redo replay facilities online help ad vice and guidance module automatic operator configuration module knowledge acquisition tool including editors for different forms of knowledge description and a consistency checker and a code export manager which generates source or binary code for the operators and data structures used in the prototype for compilation and linking in the target environment 2 2 Goals Portability To save investments into software as well into the target systems as into the tool box itself such a system must be highly portable and has to generate reusable code for the tar get system A UNIX environment for the toolbox and eventually for the runtime system too is the current choice The user should not been forced as far as possible to invest time in inte grating different hardware and software concepts and products before being sure that his idea 37 of a problem solution will work Uniform Structures If on all levels of an image understanding developm
8. cess control requirements but concentrated on solving the image understanding problem 2 1 Toolbox Properties A toolbox supporting fast prototyping should have some of the following properties Sensor Input and Documentation Output Control A wide variety of sensors may be uti lized to take images and image sequences e g CCD camera satellite scanner etc which de liver various image formats Also a variety of display and hardcopy devices is in use e g film recorder colour displays black and white laser printers and the like The toolbox should ac cept input from usual sources and produce output for usual display and hardcopy devices as well as for desktop publishing systems Repertoire of Operators The core of atoolbox are efficient operators which manipulate and analyse images and structural descriptions of images e g affine transformations linear fil ters classifiers neuronal networks morphological operators symbolic matching methods etc Ifthe toolbox provides uniform data structures and their management together with pre formed interfaces new operators can be easily incorporated They should be written with port ability in mind so that they can be transferred later into the target system and are reusable in other toolbox versions Data Structures The concept of abstract data structures has to be implemented to hide imple mentation details and to allow programming in different languages e g C C Pascal PRO LOG LI
9. communication and X Windows and OSF Motif to interact with the user Eck stein 88a Eckstein 90 The interfaces to the operating system are so well defined and localized that it has been transferred with an effort of two hours through one day to different platforms such as DECStation Ultrix even DECVAX VMS HP9000 family SUN Sparc Silicon Graphics family and even multiprocessor machines such as Convex and Alliant Load Sharing If more than one processor is available ina workstation network or a multiprocessor machine execu tion of operators can automatically be directed to a proces sor which has capacity left or which is especially suited e g asignal or vector processor The interprocess commu nication uses standard socket mechanisms the load situa tion is monitored using Unix system commands Langer Eckstein 90 Interaction A typical screen using the interactive version of HORUS looks as in Fig 1 The user starts with the main menu sub window 2 in Fig 2 where he may open sub window 8 to create or modify windows to display pictures or text sub window 4 see Fig 3 to see a list of operators organized in chapters which are contained in HORUS sub window 7 see Fig 4 to set parame ters sub window 1 to see a directory of images or image objects he hasused and produces in his session or other win dows to call the online help and manual select input and output devices etc Fig 4 shows an example of the
10. d ed Singapore World Scientific Press 1992 to appear Messer 92b Tilo Messer Acquiring Object Models Using Vision Operations Proceedings Vision Interface 92 Vancouver to appear Messer Schubert 91 T Messer M Schubert Automatic Configuration of Medium Level Vision Routines Using Domain Knowledge Proceedings Vision Interface 91 Calgary 56 63 Nitzl Pauli 91 F Nitzl J Pauli Steuerung von Segmentierungsverfahren in Bildfolgen menschlicher Bewe gungen Proceedings 13th DAGM Symposium Miinchen B Radig Ed Springer Verlag Berlin 1991 Pauli 90 J Pauli Knowledge based adaptive identification of 2D image structures Symposium of the Internati onal Society for Photogrammetry and Remote Sensing SPIE Procecding Series Band 1395 S 646 653 Washington USA 1990 Pauli et al 92 J Pauli B Radig A Bl mer C E Liedtke Integrierte adaptive Bildanalyse Report 19204 Institut f r Informatik IX Technische Universit t M nchen 1992 Pfleger Radig 90 S Pfleger B Radig Eds Advanced Matching in Vision and Artificial Intelligence Pro ceedings of an ESPRIT workshop June 1990 Report TUM 19019 Technische Universit t M nchen to be published by Springer Verlag Berlin 1992 Polensky Messer 89 G Polensky T Messer Ein Expertensystem zur frame basierten Steuerung der Low und Medium Level Bildverarbeitung Proceedings 1 1th DAGM Symposium 89 Hamburg H Burkhardt K H H hne B Neumann Eds
11. ent system signal processing through symbolic description functions and data structure are presented in an uni form way which hides most implementation details the user is motivated to explore even apparently complex constructs of operator sequences He can easily combine and switch between different levels of abstraction in his program focussed on functionality on what to do and not on how to do it Interaction This motivation has then to be supported by an highly interactive user friendly toolbox interface which stimulates the engineer to test alternatives and not to think from the very beginning in terms of technical details and implementation effort Tutorial Tactical and Strategical Support Of the user especially anovice one it cannot be expected that he is able to keep the functionality applicability and parameters of all image analysis methods cast into operators and sequences of them which the toolbox can offer in his mind Therefore a tutorial tactical and strategical support is a must He needs advice what operators to select what alternatives exists how to determine parameter values for their argu ments time and space complexity to be expected and how to optimize if the prototype does not produce acceptable results Automatic Configuration If the toolbox has some knowledge about the methods included in its operator base automatic configuration becomes available If at least a partial image under standing problem
12. er tuning through a complete redesign to analyse and handle such situations We do not believe that it is an easy task realizing a machine vision toolbox those properties striving at these goals Automatic design and programming of problem solutions is a dream Nevertheless in such aspecial environment as image understanding is methods of knowledge engineering software engineering and life cycle support may be with greater success than a an data processing combined into a form of computer aided vision engineering AVE 3 The HORUS Project About five years ago we started building two alternatives of tools intended to support research and education in image processing and understanding One based on special hardware digi tizer display system Transputer board and special software OCCAM which required high competence in hardware and software engineering to become operational and to be main 38 tained This concept survived in a spin off company of the author The weak point with this approach is the intensive use of hard ware dependant imple mentation and there fore the costly adapta tion to technical inno vations The other alternative aimed at realizing some of the properties and goals as described in Chapter 2 Portability As hard ware platform for the HORUS toolbox a ge neric UNIX worksta tion environment was chosen using standard C as implementation language TCP IP protocols for
13. g 11 Here the name of the operator where the error occurred is dis played The bottom part of the window explains which result is generated and which errors arise in what situation in this case dilation on an empty image In the upper part of the win dow a menu offers related information Pressing the help button gives an explana tion how to use these menus The buttons keywords see_also and alternatives open access to related topics e g descrip tion of operators with similar functionality or explanation of the meaning of the word abstract alternatives complexity keywords peramtar result etete ses alien Inttisl info Hawwe Hilfe jaet_eysten empty Sel lon result ul gt Featlegen Gegebenenfalls wird eine Exception Behondiung durchgef Eurpstorenton wd FZ Fleeche der Int die Lafesiikere jexitaet fuer win Objekt Pr sqt F2 Iterations Fig 11 Error related window information about operator dilatioul Object Pattera Rasuli Hermijons Aarden von Rogisnen a de a oper einer Verschinbungunsche Die D kosnu int eine mengrethowetiocks Reginneneperaiion Sie van di Opal Verinkeg Se M Petter vd OR et Regionen vobi M de Veschisbungeirusiet vod R die mu veracheitunde Regive demidi Bei weiterhin m ein Bildpunlt ave M thon ind der Venetiae me a Peer Akten un Mok dem Wr m Die rain nar Region R om din Valter o mi mit 1112 besnichent Dana tat Slaten KR Mme U ab wi Eo wird Fo
14. hould detect in an image or a sequence This can be done interactively e g using the mouse to indicate the region where the object is or by some simple seg mentation method In the application illustrated in Fig 14 the pins of the Fig 14 Board with integrated circuits pins to be detected 42 integrated circuits have to be detected FIGURE analyses the boundary the background surrounding the object and its inter ior It then constructs a search space of all reasonable operators which might be applied Various rules and constraints restrict the search space to a manageable size Static restrictions help to determine the order of operators within the algorithm to be con structed An example of such a rule is Zf dynamic thresholding is selected then it should be preceded by smoothing The even more difficult task is to supply the modules with values for their parameters Elementary knowledge about computer vision is included in the rule base as well as operator specific knowledge No domain specific knowledge is incorporated in the rule base These rules are rather simple telling the system such elementary statements as for edge preserving smoothing a median filter is better than a low pass filter Constraints between operators for bid e g applying a threshold operator on a binary image But from the operator specific knowledge the system knows that a threshold operator needs a threshold value between 1 and 255 The quality
15. in field 1 which are from the point of view of PRO LOG built in predicates Field 3 displays the his tory of actions which are available for inspection modification and redo application Field 4 accepts as input PROLOG and HORUS commands which are performed in the current context of execution Similar concepts of debugging are well known from several LISP systems and ee The innovation here is the uniform handling of actions in PROLOG as well as in HORUS Further development will include the automatic analysis of interaction protocols to guide the user in understanding why an error occurred Traces of rule activations and proce dure calls as well as the assignment of variables at the moment when the error occurred will be available The idea is to give the user a meaningful access to all those objects which might be associated with an exception and to suggest alternatives for control structure and parameter values Automatic Configuration The online manual contains all informa tion about HORUS operators which are needed for advice and guidance Using this information represented in a frame based knowledge base Polensky Messer 89 together with basic knowledge of image process ing the module FIGURE Messer 92a b is able to automatically gener ate image interpretation algorithms which are composed of operators from the HORUS operator base In the current version the configuration module is given an example of that kind of objects it s
16. ki Eds Springer Verlag Berlin 1988 Eckstein 88b W Eckstein Prologschnittstelle zur Bildverarbeitung Proceedings 1st IF Prolog User Day Chapter 5 Miinchen June 10 1988 Eckstein 90 W Eckstein Report on the HORUS System INTER Revue International de L Industrie et du Commerce No 634 Oct 1990 pp 22 Ender 85 M Ender Design and Implementation of an Auto Configuring Knowledge Based Vision System in 2nd International Technical Symposium on Optical and Electro Optical Applied Sciences and Engineering Conference Computer Vision for Robots Dec 1985 Cannes Ender Liedtke 86 M Ender C E Liedtke Repr sentation der relevanten Wissensinhalte in einem selbstadaptierenden regelbasierten Bilddeutungssystem Proceedings 8th DAGM Symposium 1986 G Hartmann Ed Springer Verlag Berlin 1986 Fickenscher 91 H Fickenscher Konstruktion von 2D Modellsequenzen und episoden aus 3D Modellen zur Analyse von Bildfolgen Technische Universitat Miinchen Institut fiir Informatik IX Diplomarbeit 1991 F rstner Ruwiedel 92 W F rstner R Ruwiedel Eds Robust Computer Vision Proceedings of the 2nd 45 International Workshop March 1992 in Bonn Herbert Wichmann Verlag Karlsruhe 1992 Haas 87 L J de Haas Automatic Programming of Machine Vision Systems Proceedings 13th International Joint Conference on Artificial Intelligence 1987 Milano 790 792 Hasegawa et al 86 J Hasegawa H Kubota J Toriwaki Automated
17. lights form the contours of the lines where these are gt covered by solder The solution is then straightforward By thresholding all pixels with an intensity value lower than 70 this can be determined interactively in each image L R O U an object Dark is obtained which contains four components of dark areas A union of these four pixel sets rep resenting the lines is formed Low pass filtering dynamic threshold ing and set union produces the contour image of Fig 9 The threshold parameter is also selected by an interactively controlled test The regions which are enclosed by contours are filled forming a cover of all lines except where solder is missing Subtracting this result from the object Line uncovers those areas The remaining pixels are collected and connected regions are formed Regions with an area of less than 20 pixels are excluded and the result is stored in the object Fault which is displayed in Fig 10 Fig 9 Highlights from four images Fig 10 Missing solder on black regions The LISP program is a transcription of the PRO LOG program The data structures are objects which have hidden components created and selected automatically by operators This kind of abstraction allows the engineer to write compact programs without being involved in implementa tion details Help Modes Operators perform exception hand ling to inform the user A window is opened which displays related information Fi
18. of incremental design begins A huge space of parameters and decisions has to be mastered to achieve satisfying results Ilumina tion conditions if they are under control have to be experimentally set Operators acting on in put images and intermediate results have to be selected The procedures implementing them are usually further specified by individual sets of parameters Appropriate data structures have to be invented which somehow correspond to the image structures which have to be computed The search space of interpretation hypotheses has to be managed and hypotheses have to be evaluated until a final result is obtained No theory of Machine Vision exists to guide the design of an image understanding system and the methodological framework to support the design is not sufficiently developed Therefore to improve the efficiency of the design process and the quality of the result tools have to be uti lized which offer support for the different phases of the design process of an image under standing system Most of those which are available now concentrate on fast prototyping of low level image processing Older tools merely consist of FORTRAN or C libraries e g SPI DER Tamuraetal 83 of modules which implement typical signal and image processing op erators e g filters Newer ones supply front ends which use some window mouse based inter action e g Weymouth et al 89 A CASE tool for constructing a knowledge based machine vision s
19. of relation and attribute values To match image and model structure is a NP hard problem Application of heuristics using some kind of A search tech nique reduces complexity Pauli 90 Other techniques of matching structures are presented in Pfleger Radig 90 The problem of how to evaluate the quality of the match has received much attention in the last decade A recent workshop on Robust Computer Vision F rstner Ruwiedel 92 discussed different approaches A major problem solved only for simple situations is the specification of tolerance parameters to attribute values given their interdependence by the relations which exists between different elements It is impossi ble to describe analytically e g how the height and width of the rectan gle circumscribing the leg in Fig 22 varies with the motion The length of the boundary of the right leg is somehow related to the area of the enclosed region but impossible to state exactly Even if for some rela Fig 20 Initial seg mentation Fig 22 Leg in motion tionships an exact dependency might be found itusually becomes corrupted by the unreliabil ity of the image processing methods by noise or by the effects of digital geometry on the ras tered image Therefore variations of attribute values which should be tolerated by the match ing process are not easily determined and need time consuming experimentation The model adaptation module to be enclosed in the HORUS to
20. of the generated proposals of operator sequences depends not only on the knowledge base but even more on the precision with which a vision problem can be described and the sequences can be evaluated Of course there is a correlation between both Since at the moment a problem is described by indicating the boundary of a region which has to be extracted two aspects are used for evaluation The evaluation function takes into account how good the area of the found object matches the area of the given object and the distance between the boun daries of both objects To force the configuration system to gen erate alternative sequences which include different operators in their sequences and not only different parameter values for essentially the same sequence two templates are generated from the indicated boundary namely a boundary oriented and a region oriented one The best of both alternatives generated for these two classes survives As an example consider the problem of detecting the pins of integrated circuits on a printed board asin Fig 14 One pin s boundary is drawn e g the one indicated by an arrow in Fig 14 The configu ration system generates an operator sequence which detects correctly most of the pins but also a lot of other small regions The simple remedy is to filter out all regions which are not close to the body of the IC Therefore the detection of IC bodies is given as a second task to the configuration system Fig 16 sh
21. olbox contains methods of qualitative reasoning to help the engineer determining trends of parameter values and to follow difficult interrelationships without violating consistency between those parameter tolerances 44 4 Conclusion After more than twenty years of image understanding research the situation with respect to the methodology of designing image understanding systems is disappointing A theory of compu tational vision still does not exists which guides the implementation of computer vision algo rithms Our approach originated from an engineering point of view We identified some of the problems which decrease quality of the results and productivity of the design process in the area of image understanding Obviously we could not address all aspects and could not offer solutions to all the problems we are faced with Our advantages in the problem areas of portability user interfacing parallelisation multi host language interfacing tutorial support high level debugging model adaptation reusability and automatic configuration are sufficient to start integrating all related software modules in a toolbox for Computer Aided Vision Engineering In the HORUS system the availability of an interactive and a high level programming interface the online help and debugging system and the automatic configuration module have been in use for some period of time We use it exten sively in a practical course on Computer Vision as part of our Com
22. ows the result The closeness constraint cannot be implemented in the current version The vision engineer has to do some programming formulating such code as in Fig 17 The arguments to the simple PROLOG rule are both images as inputs and the resulting image as output For the IC bodies the contours of their convex hulls are computed A circle of radius 5 pixels is defined and used to widen the contour implementing the predi cate close A simple intersection of this image with that of the small regions eliminates most of the unwanted spots Itis obvious from Fig 18 that the result is not completely correct detected by operator sequence first configured Fig 16 IC bodies detected as dark regions by second operator sequence Fig 18 Spots close to IC boundary combined from both results mostly pins 43 Anyhow the automatic configuration is utilized here in the context of rapid prototyping The result gives agood starting point to improve on To prepare this example for this paper took less than one hour It could be done on a very abstract but natural level in terms of design decisions such as find small bright regions close to IC bodies Two mouse interactions and one PROLOG rule implemented it Model Adaptation The models for describing objects used so far are simple closed contours This is of course not sufficient for the analysis of more complex situations Liedtke Ender 86 where scenes are to be
23. puter Science curriculum We observed a drastic increase of creative productivity of our students working on their exer cises Other Computer Vision Labs testing our system reported a similar experience In the near future the model adaptation will be more closely integrated into HORUS The tuto rial module will be able to give recommendations to the designer which module and parameter values to choose an interactive complement of the automatic configuration module During the process of integration some new challenges will appear One is the extension of the internal object data structure which is effective and efficient for low and medium level processing to structures needed by high level image understanding A second problem is the description of operators in such the way that all modules are able to extract automatically that part of the information which it needs To describe more than 400 operators ranging from a simple linear filter up to a complete Neural Network simulator is a time consuming task To specify for mally for an author of anew module how he has to encode for HORUS the knowledge about his operator is not solved in general Nevertheless we could demonstrate that some parts in the design process of image under standing systems can be automatized successfully References Eckstein 88a W Eckstein Das ganzheitliche Bildverarbeitungssystem HORUS Proceedings 10th DAGM Symposium 1988 H Bunke O Kiibler P Stuc
24. r jeden Packs m M oina Trmasation m dar Region R durchgef hrt Die Verisigung bbar il Te a T Rei ss Pattern at chee Badai wag jenen bag dae beit wand Me Binge bevbjeia f r die nie Remtion wird die obigen Detlction ergibt ch da bei ainar fearon Mache sin Objold wit loueur Region srsmugt wird Mashin Paitern bianca wit Precederen wie circle rectangtel tectangiet allipee steve poiran sora soord sic arorut werden threshold The button parameter tellshow to choose parameter values for this opera tor the button abstract delivers a short description and the button manual gives a long description of the operator Fig 12 The manualis written in LATEX therefore astandard UNIX tool has been used to pro vide the functionality of the manual man agement and a LATEX preview program generates the window A new version will use a Postscript previewer which allows the inclusion of pictorial examples and Kouraxm t Sa Pi die Fiche einer Eungaherngien wad Fy die Fl che der Maske jaaa int die Laufzeit heurgleriht Soe ein Objekt Ojleerations Fr VF ALTERNATIVEN Simia Supa AUCH d intien golog dilation ser erseisel eirche roctan glad siora palygen YERBALTEN distina i bda den Wert TRUE falls die Parammater borreta sind Das Verhalten bai Sowas Fingabe riae Tmpebanbjchte verkunden Kit sich viieks set systems onsbjei zuch reden den bei krer Topher fia Object dark set oystamfs Tomnpty seginn rank
25. variety of parameters which control the display of colored draw linewidth color Lut paint shape part ma ena or Be ee Fig 4 Default window parameters for image display hysteresis_threshold label_to_obj an image in this example 3 colours raster image line width 1 pixel in white colour default lookup table default presentation optimized for the screen original shape and dis f play of the whole picture without zooming etc Since HORUS knows which screen is in use this menu automatically offers only such parameter values which are needed and applicable High Level Programming The engineer may choose the interactive exploration to get some feeling about which operators to apply in which sequence A history of commands is logged which can be modified and executed again Furthermore HORUS offers a comfortable host language interface which allows the f engineer to program his solutionina U procedural using C or Pascal as lan guage functional LISP object oriented C or declarative PRO LOG style Eckstein 88b As an example a PROLOG see Fig es ae 7 and an equivalent LISP program Fig 8 are given which solve the task of finding on a thick film ceramic board areas which are not covered correctly by solder Fig 5 6 The basic idea is to illuminate the board from four sides in such a way that the high
26. ystem will not be available in the near future Nevertheless some of the limitations of existing tools can be overcome by directing research into those phases of the design process in which parts can be operationalized and therefore incorporated into a next generation of those tools Matsuyama 89 Risk B rner 89 Vernon Sandini 88 36 2 Computer Aided Vision Engineering In solving a machine vision problem an engineer follows more or less a general life cycle model He has to analyse the problem collect a sample oftypical images for testing specify a coarse design on a conceptual level match this design with available hardware and software modules specify and implement some missing functionality realize a prototype perform tests using the collected set of images improve the prototype observe more and more con straints which accompany the transfer into real use specify and implement the final system validate the system using a different sample of images monitor the system during operation and do final modifications In the first part of the life cycle to perform a feasibility study fast prototyping is the usual strategy Experience tells that in reality even for not to complex prob lems prototyping is slow This was our motivation to start building a toolbox which supports machine vision engineering especially suited for feasibility studies As aconsequence of this focus we omitted those parts which could handle real time and pro
Download Pdf Manuals
Related Search