Adaptive windows for image processing

Aleksander, Igor; Wilson, M.

doi:10.1049/ip-e.1985.0034

Cited by 10 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive window has previously been described in several papers, especially in (Aleksander and Wilson 1985) and . Briefly, It consists of a window of xx y pixels each connected at random to the address inputs of a set of RAMs known as a discriminator.…”

Section: A the Adaptive Windowmentioning

confidence: 99%

Adaptive Windows for Texture Discrimination

Kani¹,

Dobree-Wilson²

1987

Procedings of the Alvey Vision Conference 1987

View full text Add to dashboard Cite

The application of image processing operators known as adaptive windows to the task of complex texture discrimination is reported. Comparisons are made with the ability of the pre-attentive human visual system for the same tasks. A modification to the standard adaptive window is presented which has several advantages for this type of image processing task. The performance of the adaptive windows is reported with reference to texture described in terms of statistical parameters, textons and periodicity radii.

show abstract

Section: A the Adaptive Windowmentioning

confidence: 99%

Adaptive Windows for Texture Discrimination

Kani¹,

Dobree-Wilson²

1987

Procedings of the Alvey Vision Conference 1987

View full text Add to dashboard Cite

show abstract

“…For doing this we use the natural binary encoding which provides high resolution and it enables the conversion of the binary co-ordinate representations back to a decimal form. An alternative encoding scheme, which has been considered, is the so-called thermometer encoding [2]. This encoding has the property of preserving the proportionality of the Hamming distances and Euclidean distances between vectors, but it was not adopted as it becomes impractical if higher resolution is required.…”

Section: Hopfield Neural Networkmentioning

confidence: 99%

Restoration of Partially Occluded Shapes of Faces Using Neural Networks

Draganova

Lanitis

Christodoulou

Advances in Soft Computing

View full text Add to dashboard Cite

One of the major difficulties encountered in the development of face image processing algorithms, is the possible presence of occlusions that hide part of the face images to be processed. Typical examples of facial occlusions include sunglasses, beards, hats and scarves. In our work we address the problem of restoring the overall shape of faces given only the shape presentation of a small part of the face. In the experiments described in this paper the shape of a face is defined by a series of landmarks located on the face outline and on the outline of different facial features.We describe the use of a number of methods including a method that utilizes a Hopfield neural network, a method that uses Multi-Layer Perceptron (MLP) neural network, a novel technique which combines Hopfield and MLP together, and a method based on associative search. We analyze comparative experiments in order to assess the performance of the four methods mentioned above. According to the experimental results it is possible to recover with reasonable accuracy the overall shape of faces even in the case that a substantial part of the shape of a given face is not visible. The techniques presented could form the basis for developing face image processing systems capable of dealing with occluded faces.1

show abstract