In this work we address the common problem of low bit rate image coding, i.e. perceptual quality loss. We propose a novel scheme to tackle this problem. The salient part of this work is to first encode the most important visual features of images extracted from Sigma filtering preprocessing. The preliminary results show that the image decoded by our scheme contains much less artifacts comparing...

An image entails a huge amount of data and information. For this reason, image synthesis and analysis by computer systems requires a high processing time. This represents a handicap in systems where real time processing or an immediate interpretation is demanded as in visual inspection industrial applications. Present work, introduces a computer architecture for the construction of a compact re...

In electrophysiological experiments on visual pattern discrimination, decision difficulty was manipulated either via the physical characteristics of the test stimuli, or by changing the instruction given to the observer. Visual stimuli were rectangular matrices each composed of 100 Gabor patches having different orientations. Matrices differed in the number of Gabor patches with vertical, or ho...

Since its introduction, fractal theory has been exploited in many research topics such as image processing, pattern recognition and image coding, because of the intrinsic properties which make fractals highly suited to tasks such as segmentation, feature extraction and indexing, just to name a few. Unfortunately, they are based on a strong asymmetric scheme, consequently suffering from very hig...

We introduce a compact coding of image information which explicitly separates visual information into geometric information (orientation) and structural information (phase and colour) and temporal information (optic flow). We investigate the importance of these visual attributes for stereo matching on a large data set. From these investigation we can conclude that it is the combination of diffe...

Recently, Bag of Visual Words (BoW) model has shown its success in image classification and retrieval. The key idea behind the BoW model is to quantize the continuous highdimensional space of image features (e.g. SIFT [1]) to a manageable visual codebook. The quality of the visual codebook has an important impact on BoW-based methods. Different from the existing techniques, such as Kernel codeb...

A new form of denotational mathematics known as Visual Semantic Algebra (VSA) is presented for abstract visual object and architecture manipulations. A set of cognitive theories for pattern recognition is explored such as cognitive principles of visual perception and basic mechanisms of object and pattern recognition. The cognitive process of pattern recognition is rigorously modeled using VSA ...

The contourlet transform is a new directional transform, which is capable of capturing contours and fine details in images. We recently introduced the wavelet-based contourlet transform (WBCT) that is a non-redundant version of the contourlet transform, and appropriately used this transform for image coding. In this paper, we introduce the concept of wavelet-based contourlet packets (WBCP), whi...

This paper presents a novel L1-norm semisupervised learning algorithm for robust image analysis by giving new L1-norm formulation of Laplacian regularization which is the key step of graph-based semi-supervised learning. Since our L1-norm Laplacian regularization is defined directly over the eigenvectors of the normalized Laplacian matrix, we successfully formulate semi-supervised learning as a...

To extract the global structure of an image, the visual system must integrate local orientation estimates across space. Progress is being made toward understanding this integration process, but very little is known about whether the presence of structure exerts a reciprocal influence on local orientation coding. We have previously shown that adaptation to patterns containing circular or radial ...