|
|
Biologically Inspired Methods of Object Recognition
Vaľko, Tomáš ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
Object recognition is one of many tasks in which the computer is still behind the human. Therefore, development in this area takes inspiration from nature and especially from the function of the human brain. This work focuses on object recognition based on extracting relevant information from images, features. Features are obtained in a similar way as the human brain processes visual stimuli. Subsequently, these features are used to train classifiers for object recognition (e.g. SVM, k-NN, ANN). This work examines the feature extraction stage. Its aim is to improve the feature extraction and thereby increase performance of object recognition by computer.
|
|
|
Extraction of spontaneously occurring activity patterns from an electrophysiological signal
Voldřich, Matěj ; Korvasová, Karolína (advisor) ; Riedlová, Kamila (referee)
To be able to elicit desired percepts using a cortical visual prosthesis, is it essential to understand the functional structure of the neural network under the implant. However, in a blind individual the functional proper- ties of neurons cannot be measured by recording responses to visual stimuli and information can only be extracted from spontaneous activity. Spon- taneous activity in the primary visual cortex (V1) of anesthetized primates has been shown to encode information about local functional architecture of the neural network. Particularly, inference of the orientation-preference map from spontaneous activity has been achieved in non-human animals using in- vasive imaging techniques that are not intended for applications in humans. Whether the same inference is possible with spatially sparse electrophysiolo- gical recordings from a micro-electrode array that is currently used as a cortical visual prosthesis remains unknown. The aim of this thesis is to use automatic spatial pattern detection algorithm for orientation preference map inference from spontaneous activity and compare outcomes using four differ- ent variables extracted from signal recorded with intracranial micro-electrode arrays in awake macaque monkeys. 1
|
|
|
Biologically Inspired Methods of Object Recognition
Vaľko, Tomáš ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
Object recognition is one of many tasks in which the computer is still behind the human. Therefore, development in this area takes inspiration from nature and especially from the function of the human brain. This work focuses on object recognition based on extracting relevant information from images, features. Features are obtained in a similar way as the human brain processes visual stimuli. Subsequently, these features are used to train classifiers for object recognition (e.g. SVM, k-NN, ANN). This work examines the feature extraction stage. Its aim is to improve the feature extraction and thereby increase performance of object recognition by computer.
|
guest ::
