Name: Context and Subcategories for Sliding Window Object Recognition (en Inglés)
Price: 1418.82 MXN
Availability: InStock
Author: Divvala Santosh Kumar
ISBN: 9783659481895

Envío gratis

portada Context and Subcategories for Sliding Window Object Recognition (en Inglés)

Formato

Libro Físico

Autor

Divvala Santosh Kumar

Editorial

LAP Lambert Academic Publishing

Idioma

Inglés

N° páginas

152

Encuadernación

Tapa Blanda

Dimensiones

22.9 x 15.2 x 0.9 cm

Peso

0.23 kg.

ISBN13

9783659481895

Categorías

Tecnología: cuestiones generales

Context and Subcategories for Sliding Window Object Recognition (en Inglés)

Divvala Santosh Kumar (Autor) · LAP Lambert Academic Publishing · Tapa Blanda

Libro Nuevo

$ 1,418.82

$ 2,364.69

Ahorras: $ 945.88

40% descuento

Envío normal

Origen: España (Costos de importación incluídos en el precio)

Se enviará desde nuestra bodega entre el Viernes 26 de Julio y el Lunes 05 de Agosto.

Lo recibirás en cualquier lugar de México entre 1 y 3 días hábiles luego del envío.

Reseña del libro "Context and Subcategories for Sliding Window Object Recognition (en Inglés)"

The sliding window approach is the current de facto standard for building high-performance object detectors. The approach involves scanning an image with a fixed-size rectangular window and applying a classifier to the features extracted within the sub-image defined by the window. In this work, we study two important factors influencing its performance. First is the role played by context, where information outside the window is used to rescore the detections output by the local window classifier. Context helps in suppressing detections in regions that are less probable to contain an object and encourages those that are more plausible. We enumerate different sources and uses of context, and evaluate their role in aiding detection performance. Second is the role played by subcategories, where information within the window is used to split training data into smaller groups, for learning multiple classifiers to model the object appearance. The smaller groups have reduced appearance diversity and thus lead to simpler classification problems. We show that the use of subcategories not only improves detection performance, but also alleviates the need for complex representation and models.