Invariant image object recognition using mixture densities

Dahmen, Jörg; Keysers, Daniel; Güld, Mark Oliver; Ney, Hermann

doi:10.1109/icpr.2000.906150

Cited by 11 publications

(15 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 shows the results of the proposed method in comparison with other techniques [10]. Using a thresholding distance to avoid great differences between the distances of two image pixels, the classification error rate of the proposed local feature approach was reduced from ½¼ ± to ±.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Medical Images Using Local Representations

Paredes

Keysers

Wein

et al. 2002

Bildverarbeitung Für Die Medizin 2002

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…Using a thresholding distance to avoid great differences between the distances of two image pixels, the classification error rate of the proposed local feature approach was reduced from ½¼ ± to ±. The same technique reduced the error rate of the approach based on distorted tangent distance from ½¼ ± to ¼± [10].…”

Section: Resultsmentioning

confidence: 99%

Classification of Medical Images Using Local Representations

Paredes

Keysers

Wein

et al. 2002

Bildverarbeitung Für Die Medizin 2002

View full text Add to dashboard Cite

show abstract

“…The overall result is then obtained by combining the individual results using the sum rule. An in depth discussion of this method can be found in [8].…”

Section: ô´ üµ Argmaxmentioning

confidence: 99%

“…Ô´µÔ´Ü µ (8) That is we maximize the a posteriori probability for class given an image Ü where the class conditional probability Ô´Ü µ is modeled by…”

Section: ô´ üµ Argmaxmentioning

confidence: 99%

Experiments with an extended tangent distance

Keysers

Dahmen

Theiner

et al.

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then the distance is the minimum distance between one of the points and the tangent subspace of the other point, see figure 4.2. This is known as the single sided tangent distance [Dahmen et al, 2001;Keysers et al, 2004], and for clarity the original tangent distance is sometimes referred to as double sided. In the context of a classification task, the tangent subspace can be either of the reference vector (from the classification model) or the observation vector, consequently the two single sided tangent distances can be easily distinguished as the reference single sided tangent distance (RTD) and the observation single sided tangent distance (OTD) respectively.…”

Section: Tangent Distancementioning

confidence: 99%

Contributions to High-Dimensional Pattern Recognition

Santamaría

View full text Add to dashboard Cite

/ Resumen / ResumThis thesis gathers some contributions to statistical pattern recognition particularly targeted at problems in which the feature vectors are high-dimensional. Three pattern recognition scenarios are addressed, namely pattern classification, regression analysis and score fusion. For each of these, an algorithm for learning a statistical model is presented. In order to address the difficulty that is encountered when the feature vectors are high-dimensional, adequate models and objective functions are defined. The strategy of learning simultaneously a dimensionality reduction function and the pattern recognition model parameters is shown to be quite effective, making it possible to learn the model without discarding any discriminative information. Another topic that is addressed in the thesis is the use of tangent vectors as a way to take better advantage of the available training data. Using this idea, two popular discriminative dimensionality reduction techniques are shown to be effectively improved. For each of the algorithms proposed throughout the thesis, several data sets are used to illustrate the properties and the performance of the approaches. The empirical results show that the proposed techniques perform considerably well, and furthermore the models learned tend to be very computationally efficient.Esta tesis re\' une varias contribuciones al reconocimiento estad\' {\i} stico de formas orientadas particularmente a problemas en los que los vectores de caracter\' {\i} sticas son de una alta dimensionalidad. Tres escenarios de reconocimiento de formas se tratan, espec\' {\i} ficamente clasificaci\' on de patrones, an\' alisis de regresi\' on y fusi\' on de valores. Para cada uno de estos, un algoritmo para el aprendizaje de un modelo estad\' {\i} stico es presentado. Para poder abordar las dificultades que se encuentran cuando los vectores de caracter\' {\i} sticas son de una alta dimensionalidad, modelos y funciones objetivo adecuadas son definidas. La estrategia de aprender simult\' aneamente una funci\' on de reducci\' on de dimensionalidad y el modelo de reconocimiento se demuestra que es muy efectiva, haciendo posible aprender el modelo sin desechar nada de informaci\' on discriminatoria. Otro tema que es tratado en la tesis es el uso de vectores tangentes como una forma para aprovechar mejor los datos de entrenamiento disponibles. Usando esta idea, dos m\' etodos populares para la reducci\' on de dimensionalidad discriminativa se muestra que efectivamente mejoran. Para cada uno de los algoritmos propuestos a lo largo de la tesis, varios conjuntos de datos son usados para ilustrar las propiedades y el desempe\ño de las t\' ecnicas. Los resultados emp\' {\i} ricos muestran que las t\' ecnicas propuestas tienen un desempe\ño considerablemente bueno, y adem\' as los modelos aprendidos tienden a ser bastante eficientes computacionalmente. iv ABSTRACT / RESUMEN / RESUM Esta tesi reunix diverses contribucions al reconeixement estad\' {\i} stic de formes, les quals estan orientades ...

show abstract

Invariant image object recognition using mixture densities

Abstract: Abstract

Cited by 11 publications

References 10 publications

Classification of Medical Images Using Local Representations

Classification of Medical Images Using Local Representations

Experiments with an extended tangent distance

Contributions to High-Dimensional Pattern Recognition

Contact Info

Product

Resources

About