K. Nováková’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (3)


Database model of arithmetic network
  • Article

January 2003

·

9 Reads

K. Nováková

·

J. Kukal

Arithmetic networks consist of neural, Boolean and fuzzy ones. Supposing the acyclic structure, decomposition of arithmetic network is possible. There are three results of our analysis: node unification, edge unification and network decomposition. We obtain only 14 node types and 4 edge types for realization of a wide class of traditional arithmetic networks from literature. The main result of our work is the splitting of the competitive neurons (nodes) to distance and soft extreme nodes. The side result of analysis is using the group of nodes instead of layer. It enables grouping the nodes of the same type but with the possibility of long interconnections. The main aim of our work was to realize the system of arithmetic networks in the SQL language on any SQL server. The database realization enables not only saving, watching and editing the network structures and parameters but also studying the response of archieved networks. The learning process was not included because of being iterative in general and unrealizable without loops on database server at that time.


VARIATION APPROACH TO INVARIANT RECOGNITION OF BINARY IMAGES

7 Reads

Binary image of individual n-dimensional object is an information source for ob- ject recognition. The properties extracted from given binary image should be invariant to translation (T), scaling (S), and rotation (R) of the original pattern, object, or image, respectively. There are many possibilities how to realize TSR invariant properties of n-dimensional binary images. The translation invariance can be achieved by using n-dimensional Fourier transform and amplitude spec- trum, which is trivial. The rotation of original will cause rotation of Fourier spectrum. Thus the rotation invariance is based on envelopes, which are gener- ated by rotation of Fourier spectrum. The resulting envelopes can be rescaled to normalized forms which are TSR invariant. The recognition system uses TSR in- variant envelopes as non-linear preprocessing for proposed variation recognizer. Standard PCA technique is used as referential method. All the programs are realized in Matlab environment.


ELIMINACE VLIVU DRUHÉ ROTACE PêI AFINNÖ INVARIANTNÍM 2D ROZPOZNÁVÁNÍ

6 Reads

Invariantní rozpoznávání 2D binárních obrazje £asto zaloûeno na momentech obrazu. Ty umoû‹ují konstrukci afinní transformace, která zajistí invarianci v•£i posunutí, zm¥n¥ velikosti, první rotaci a protaûení obrazu. Je vöak problém zajistit také invarianci v•£i druhé rotaci. Élánek se zab˝vá dv¥ma metodami, kter˝mi lze dosáhnout vytvo∞ení afinn¥ invariantního rozpoznávacího systému s numericky stabilní eliminací druhé rotace. Modifikované obrazy, které sys- tém pouûívá, jsou získány pomocí polární nebo Radonovy transformace. Nové metody umoû‹ují klasifikaci objektnezávislou na úhlu pohledu pozorovatele, coû má praktick˝ v˝znam v aplikacích po£íta£ového vid¥ní. Pro podporu metod byla vytvo∞ena knihovna funkcí v prost∞edí MATLAB. 1 Úvod V sou£asné dob¥ se £asto diskutuje o rozpoznávání objekt•, které by bylo nezávislé na jejich pozici, velikosti, orientaci a jin˝ch transformacích obrazu. Tento £lánek navrhuje dv¥ nové metody pro binární klasifikaci afinn¥ transformovan˝ch objekt•. Tyto metody vyuûívají znalostí z £lánku Suka a Flussera (2), kter˝ pro rozpoznávání objektnavrhuje metodu zaloûenou na momentech, která funguje dokonce i pro symetrické objekty. V¥töina jin˝ch metod zaloûen˝ch na momentech je p∞i aplikaci na symetrické objekty neúsp¥öná, nebo· mnoho momentje nulov˝ch. Slab˝m místem této metody je vöak zajiöt¥ní invariance v•£i druhé rotaci, protoûe je hledán nenulov˝ moment a to není v diskrétním p∞ípad¥ snadné. Alternativa pro dosaûení invariance v•£i druhé rotaci a zrcadlení je navrûena v tomto £lánku jako aplikace polární nebo Radonovy transformace.