Classification of images: ICA filters vs human perception
نویسندگان
چکیده
In this paper we compare a machine based semantic organisation of natural images with the one provided by human perception. On one hand, we have conducted a psychophysical experiment to determine a human perception space in which we have identified semantic categories. These categories and the distances between images are emphasised by analysing the human response similarities with a multidimensional scaling technique called Curvilinear Component Analysis (CCA). On the other hand, we try to perform the same scene categorisation with a computational model based on an ICA filter description.
منابع مشابه
The independent components of natural images are perceptually dependent
The independent components of natural images are a set of linear filters which are optimized for statistical independence. With such a set of filters images can be represented without loss of information. Intriguingly, the filter shapes are localized, oriented, and bandpass, resembling important properties of V1 simple cell receptive fields. Here we address the question of whether the independe...
متن کاملImproving the Performance of ICA Algorithm for fMRI Simulated Data Analysis Using Temporal and Spatial Filters in the Preprocessing Phase
Introduction: The accuracy of analyzing Functional MRI (fMRI) data is usually decreases in the presence of noise and artifact sources. A common solution in for analyzing fMRI data having high noise is to use suitable preprocessing methods with the aim of data denoising. Some effects of preprocessing methods on the parametric methods such as general linear model (GLM) have previously been evalua...
متن کاملIca Filter Bank for Segmentation of Textured Images
Independent component analysis (ICA) of textured images is presented as a computational technique for creating a new data dependent filter bank for use in texture segmentation. We show that the ICA filters are able to capture the inherent properties of textured images. The new filters are similar to Gabor filters, but seem to be richer in the sense that their frequency responses may be more com...
متن کاملClassification of emotional speech using spectral pattern features
Speech Emotion Recognition (SER) is a new and challenging research area with a wide range of applications in man-machine interactions. The aim of a SER system is to recognize human emotion by analyzing the acoustics of speech sound. In this study, we propose Spectral Pattern features (SPs) and Harmonic Energy features (HEs) for emotion recognition. These features extracted from the spectrogram ...
متن کاملComplex-Valued Independent Component Analysis of Natural Images
Linear independent component analysis (ICA) learns simple cell receptive fields fromnatural images.Here,we show that linear complexvalued ICA learns complex cell properties from Fourier-transformed natural images, i.e. two Gabor-like filters with quadrature-phase relationship. Conventional methods for complex-valued ICA assume that the phases of the output signals have uniform distribution. We ...
متن کامل