Searching for authors named "George Nagy" – sorted by Relevance.
-
Visual pattern recognition in the years ahead, Procs
- Conventional classification algorithms have already reached a plateau at the trade-off imposed by the bias due to the structure of the classifier and the variance due to the limited size of the training set. The latter may be alleviated by exploiting known constraints, including class and style prio
- Cited by 2 (1 self) – Add To MetaCart
-
Towards a Ptolemaic Model for OCR
- In style-constrained classification often there are only a few samples of each style and class, and the correspondences between styles in the training set and the test set are unknown. To avoid gross misestimates of the classifier parameters it is therefore important to model the pattern distributio
- Cited by 4 (3 self) – Add To MetaCart
-
Interactive Document Processing and Digital Libraries
- We explore connections between digital libraries and interactive document image analysis. Digital libraries can provide useful data and metadata for research in automated document image analysis, and allow unbiased testing of DIA algorithms. With these goals in mind, we suggest criteria for construc
- Cited by 3 (1 self) – Add To MetaCart
-
Adaptive Classifiers for Multi-Source OCR
- When patterns occur in large groups generated by a single source (style consistent test data), the statistics of the test data differ from those of the training data which consists of patterns from all sources. We present a Gaussian model for continuously distributed sources under which we develop
- Cited by 7 (6 self) – Add To MetaCart
-
Evaluation of Model-Based Interactive Flower Recognition
- We introduce the concept of Computer Assisted Visual InterActive Recognition (CAVIAR). In CAVIAR, a parameterized geometrical model serves as the human-computer communication channel. We implemented a flower recognition system and evaluated it on 30 inexperienced subjects. Major conclusions include:
- Cited by 8 (2 self) – Add To MetaCart
-
Human-computer interaction for complex pattern recognition problems, to appear
- We review some applications of human-computer interaction that alleviate the complexity of visual recognition by partitioning it into human and machine tasks to exploit the differences between human and machine capabilities. Human involvement offers advantages, both in the design of automated patter
- Cited by 1 (1 self) – Add To MetaCart
-
Online handwriting recognition using time-order of lexical and signal co-occurrences
- Abstract. Letter-polygram based Symbolic Indirect Correlation is a new method that offers significant advantages for ordered unsegmented signals. However, its application to on-line, cursive handwriting requires solving several difficult problems. (1) Reference strings of words must satisfy certa in
- Cited by 3 (2 self) – Add To MetaCart
-
Mobile Interactive Support System for Time-Critical Document Exploitation
- Computer Assisted Visual Interactive Recognition, or CAVIAR, has proven to be an effective methodology for integrating human and machine expertise in addressing challenging pattern recognition tasks. In this paper, we examine the application of the CAVIAR paradigm to problems arising in real-time do
- Cited by 1 (1 self) – Add To MetaCart
-
Analytical results on style-constrained Bayesian classification of pattern fields.” Accepted to
- Abstract—We formalize the notion of style context, which accounts for the increased accuracy of the field classifiers reported in this journal recently. We argue that style context forms the basis of all order-independent field classification schemes. We distinguish between intraclass style, which u
- Cited by 1 (0 self) – Add To MetaCart
-
Writer consistency
- Abstract. When patterns occur in large groups generated by a single source (style consistent test data), the statistics of the test data differ from those of the training data, which consist of patterns from all sources. We present a Gaussian model for continuously distributed sources under which we
- Add To MetaCart

