The review of methods of identification of a random field of points is given. We have discussed the approaches existing in literature and presented Russian works unknown for a Western reader. The review is focused on the problem of the parts of star sky recognition for spacecrafts navigation. We tested a group of invariant methods of the recognition with computer simulation technique and proposed the most noise-stable method.

Identification of random fields of points

We propose a new shift-, scale-, rotation- and pose-invariant method for three-dimensional object recognition. The method is based on angular scanning about the centroid of two-dimensional images of the objects yielding features invariant under changes in position, orientation and scale and a modified feature space trajectory classifier for pose invariance. Experimental results are shown and optical implementation is discussed.

Shift-, scale-, rotation- and pose-invariant object recognition using centroid wedge sampling and a feature space trajectory classifier

A new method for pattern recognition that is invariant under changes of position, orientation, intensity, and scale is presented. The centroids of objects provide unique points that are related to the energy distribution. For obtaining more such unique points a conformal transform can be used to rearrange the energy distribution of the object. By means of the conformal transform many different centroids can be produced from the same object. A useful pattern-recognition and object-registration method that yields a position-, rotation-, intensity-, and scale-invariant feature vector based on these centroids can be created.

Invariant pattern recognition based on centroids

This paper describes an application of the Cascade-Correlation (CC) network to pattern recognition. The pattern recognition task was to simulate an automatic vision inspection system that had to properly classify five different objects. The feature vectors were extracted from 2D images of circularly scanned images and used as inputs for a neural network that was then trained to classify an unknown presented object. The results show that the CC network is viable tool in pattern recognition tasks. It is able to classify partially occluded objects with high accuracy, and to considerably improve classification of noisy images based on simple histogram trimming preprocessing.

Application of the Cascade-Correlation network to the classification of circularly scanned images

Circular scanning of the image provides an efficient and simple way to achieve feature extraction of 2-D images. The obtained features are insensitive to object's position, orientation, and scale. The main shortcoming of the method is that such features do not uniquely determine the shape of an object. An overview of the method is presented. An experiment with recognition of latin capitals in two different fonts and scales is described and results are given.

Application of circular scanning of images to invariant pattern recognition

Circular scanning of images enables simple feature extraction basically insensitive to object orientation and position. Such is a histogram representing concentric luminous intensity of the image. The histogram shows luminous intensity of concentrinc rings having center in object's centroid. However, features extracted from the image in such a way do not uniquely describe an object. This can cause certain difficulties in pattern recognition stage of image analysis. Latin capitals have been chosen as the objects to be recognized. Two approaches have been analysed. In the deterministic approach pattern recognition is based on matching of the features of an object with those from the feature space. Satisfactory matching results in recognition of the particular capital. Small changes in shapes of the capitals to be recognized can show applicability of the described method in practice. The other approach is based on simple form of adaptive recognition. The result of recognition changes the feature space in order to increase reliability of further recognition. Averaging the data from feature space with the features extracted from the recognized image increase the reliability of further recognition. Experimental results were obtained in problem of recognition of the six capitals given in two different fonts and scales. Images of the capitals were obtained by means of binary semiconductor camera. Image processing, feature extraction and pattern recognition were performed on IBM PC AT.

Vojislav Divljakovic

Papers

Application of circular scanning of images to invariant pattern recognition

Pattern Recognition Based On Circular Scanning Of Images