Object recognition with dynamic neural fields

نویسنده

  • Christian Faubel
چکیده

iii iv Acknowledgement This thesis has been elaborated at the Institut für Neuroinformatik at the Ruhr-University Bochum. Working at the Institut für Neuroinformatik has been a huge chance that allowed me to discover the pleasure of interdisci-plinary and exciting scientific work. Advised by Gregor Schöner I experienced a way of doing research that I find very beautiful because of its conceptual clarity. I am very grateful for the guidance, help and inspiration he provided. What makes an aspiring and inspiring work environment is ultimately determined by the surrounding people and the Institut für Neuroinformatik seems to be a place that especially attracts this kind. Thank you all! To name a few of those, I would first like to thank Ioannis Iossifidis for always having an ear and time for discussion for the fun we had and for his cheering laugh. Christian Igel is not only a great partner for having a break but also one for intellectual sparring sessions during those breaks. I am very thankful for these as they trained me to choose my arguments well and how to discuss controversially and yet respectfully. Thanks to Evelina Dineva for teaching me good cooking and food shopping and for being a great colleague to cooperate with even if separated by a huge ocean. I think this thesis would be a pain to read without the help and valuable comments and corrections from John Lipinski. Cheers to John Spencer and the Spam lab crew: your comments and feedback on my work where very motivating and inspiring. Glasmachers and Yulia Sandamirskaya all got pieces of this thesis to read and I am very thankful for their proposals and comments. I would also like to thank Prof. Dr. Christian Schmid for writing the second report on this thesis and for his valuable comments. I am grateful to my family for supporting me during my studies. Finally I thank Cordula Körber for the patience and all the love she gave me during the accomplishment of this thesis.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Neural field model for the recognition of biological motion patterns

Neurophysiological research has revealed evidence that the recognition of stationary three-dimensional objects in the cortex seems to be based on neurons that encode prototypical twodimensional views of the object. Much less is known about the neural mechanisms for the recognition of complex motion patterns, like biological motion and actions. This paper investigates if complex motion patterns ...

متن کامل

Machine learning based Visual Evoked Potential (VEP) Signals Recognition

Introduction: Visual evoked potentials contain certain diagnostic information which have proved to be of importance in the visual systems functional integrity. Due to substantial decrease of amplitude in extra macular stimulation in commonly used pattern VEPs, differentiating normal and abnormal signals can prove to be quite an obstacle. Due to developments of use of machine l...

متن کامل

A NEURO-FUZZY GRAPHIC OBJECT CLASSIFIER WITH MODIFIED DISTANCE MEASURE ESTIMATOR

The paper analyses issues leading to errors in graphic object classifiers. Thedistance measures suggested in literature and used as a basis in traditional, fuzzy, andNeuro-Fuzzy classifiers are found to be not suitable for classification of non-stylized orfuzzy objects in which the features of classes are much more difficult to recognize becauseof significant uncertainties in their location and...

متن کامل

Fast learning to recognize objects: Dynamic Fields in label-feature spaces

We bring Dynamic Field Theory to bear on a problem of robot vision, learning to recognize objects on a fast time scale, while interacting with a human user. Dynamic fields represent each object through low-level features like color, shape, and size cues. Recognition and teaching leads to localized activation peaks in these fields, which leave a memory trace, that preshapes the fields during rec...

متن کامل

Induced Gamma Band Responses Predict Recognition Delays during Object Identification

Neural mechanisms of object recognition seem to rely on activity of distributed neural assemblies coordinated by synchronous firing in the gamma-band range (>20 Hz). In the present electroencephalogram (EEG) study, we investigated induced gamma band activity during the naming of line drawings of upright objects and objects rotated in the image plane. Such plane-rotation paradigms elicit view-de...

متن کامل

3D Convolutional Neural Network for Object Recognition

3D Object recognition is an important task in computer vision applications. After the success of convolutional neural networks for object recognition in 2D images, many researchers have designed convolution neural network (CNN) for 3D object recognition. The state of art methods provide favourable results. However, the availability of large/dynamic 3D dataset and computational complexity of CNN...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009