Titlebook: Neural Networks for Vision, Speech and Natural Language; R. Linggard (Professor),D. J. Myers,C. Nightingale Book 1992 Springer Science+Bus

Traction

書目名稱Neural Networks for Vision, Speech and Natural Language影響因子(影響力)




書目名稱Neural Networks for Vision, Speech and Natural Language影響因子(影響力)學(xué)科排名




書目名稱Neural Networks for Vision, Speech and Natural Language網(wǎng)絡(luò)公開度




書目名稱Neural Networks for Vision, Speech and Natural Language網(wǎng)絡(luò)公開度學(xué)科排名




書目名稱Neural Networks for Vision, Speech and Natural Language被引頻次




書目名稱Neural Networks for Vision, Speech and Natural Language被引頻次學(xué)科排名




書目名稱Neural Networks for Vision, Speech and Natural Language年度引用




書目名稱Neural Networks for Vision, Speech and Natural Language年度引用學(xué)科排名




書目名稱Neural Networks for Vision, Speech and Natural Language讀者反饋




書目名稱Neural Networks for Vision, Speech and Natural Language讀者反饋學(xué)科排名

Eructation

Image Feature Location in Multi-Resolution Images Using a Hierarchy of Multilayer Perceptronse and track features in digital image sequences. We have concentrated on the location of eyes and mouths in human head-and-shoulders images, as described by Nightingale in the introduction to this part of the book. However the techniques described should be applicable to determining the position of localised features in general images.

負擔

向外供接觸

Kernel

oracle

Finite Wordlength, Integer Arithmetic Multilayer Perceptron Modelling for Hardware Realizationan analogue implementation is being contemplated, it is necessary to know whether the inherent dynamic range and accuracy achievable with the components being used (e.g. resistor or capacitor values) will be adequate to achieve the desired performance of the net.

meritorious

The Detection of Eyes in Facial Images Using Radial Basis FunctionsThis chapter describes work done by the authors on the problem of locating eyes in human head and shoulders images, as described in the introduction to Part 1 of this book, and in Chapters 1 and 2.

嬰兒

Training and Testing of Neural Net Window Operators on Spatiotemporal Image SequencesThe purpose of the investigation was, first, to analyse the ability of single layer neural network algorithms to learn aspects of the local image structure from image sequence data, and second, to test trained networks for their image processing and noise suppression capabilities.

Moderate

草率女