Iterative multi-class multi-scale stacked sequential learning: Definition and application to medical volume segmentation
In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel ...
Digital fingerprinting for color images based on the quaternion encryption scheme
In this paper we present a new quaternion-based encryption technique for color images. In the proposed encryption method, images are written as quaternions and are rotated in a three-dimensional space around another quaternion, which is an encryption ...
Efficient image mosaicing for multi-robot visual underwater mapping
Robotic platforms have advanced greatly in terms of their remote sensing capabilities, including obtaining optical information using cameras. Alongside these advances, visual mapping has become a very active research area, which facilitates the mapping ...
A simple boundary reinforcement technique for segmentation without prior
Accurate boundary detection is a critical step of the image segmentation process. While most edge detectors rely on the presence of strong intensity gradients, this criteria can limit robustness in many real world cases. In this work we propose a scheme ...
Dictionary-based anisotropic diffusion for noise reduction
This paper presents an anisotropic diffusion-based approach to noise reduction, which utilizes a pre-trained dictionary for diffusivity determination. The proposed method involves off-line and on-line processing steps. For off-line processing, a ...
Customized TRS invariants for 2D vector fields via moment normalization
The behavior of vector fields under translation, rotation and scaling differs with respect to the underlying application. Moment invariants that are customized to the specific problem can be constructed by means of normalization. In this paper, we ...
Fast salient object detection through efficient subwindow search
Salient object detection techniques have a variety of applications of broad interest. However, the detection must be fast to facilitate these processes. In this paper, we address the computational problems in salient object detection. Several approaches ...
Building confidence regions for the ROC surface
The ROC surface is the major criterion for assessing the accuracy of diagnosis test statistics s(X) in regard to their capacity of discriminating between K>=3 statistical populations. It provides additionally a widely used visual tool in the cases K=2 ...
Image segmentation by fusion of low level and domain specific information via Markov Random Fields
We propose a new segmentation method by fusing a set of top-down and bottom-up segmentation maps under the Markov Random Fields (MRF) framework. The bottom-up segmentation maps are obtained by varying the parameters of an unsupervised segmentation ...
Exploring neighborhood and spatial information for improving scene classification
A good image descriptor is essential for the scene classification task. This work proposes an improvement for the Contextual Mean Census Transform (CMCT), an image descriptor, obtained by adding information from distant neighbors to the non-parametric ...
Supervised super-vector encoding for facial expression recognition
Expression recognition from faces with varying pose and illumination conditions is a challenging research area with growing interest. In this paper, we develop a novel supervised super-vector encoding framework to learn discriminative image feature ...
Statistical machine translation of subtitles for highly inflected language pair
This paper addresses the problem of statistical machine translation between highly inflected languages. Even when dealing with closely-related language pairs, statistical machine translation encounters problems if the parallel corpus is not big enough. ...