The accurate left ventricular boundary detection in echocardiographic images allow cardiologists ... more The accurate left ventricular boundary detection in echocardiographic images allow cardiologists to study and assess cardiomyopathy in patients. Due to the tedious and time consuming manner of manually tracing the borders, deformable models are generally used for left ventricle segmentations. However, most deformable models require a good initialization, which is usually outlined manually by the user. In this paper, we propose an automated left ventricle detection method for two-dimensional echocardiographic images that could serve as an initialization for deformable models. The proposed approach consists of pre-processing and post-processing stages, coupled with the watershed segmentation. The pre-processing stage enhances the overall contrast and reduces speckle noise, whereas the post-processing enhances the segmented region and avoids the papillary muscles. The performance of the proposed method is evaluated on real data. Experimental results show that it is suitable for automatic contour initialization since no prior assumptions nor human interventions are required. Besides, the computational time taken is also lower compared to an existing method.
A recurrent neural network is presented which performs quadratic optimization subject to bound co... more A recurrent neural network is presented which performs quadratic optimization subject to bound constraints on each of the optimization variables. The network is shown to be globally convergent, and conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and to roundoff errors. The optimization method employed by the neural network is shown to fall into the general class of gradient methods for constrained nonlinear optimization and, in contrast with penalty function methods, is guaranteed to yield only feasible solutions.
Proceedings of the 1994 IEEE International Conference on Robotics and Automation
Abstract Fully autonomous mobile robots often rely on an array of sensors to provide them with an... more Abstract Fully autonomous mobile robots often rely on an array of sensors to provide them with an adequate picture of their environment. Furthermore, these systems tend to have strict limitations in terms of available processing capability. Hence the so-called smart sensing ...
Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004.
This article describes a contrast measure inspired by findings from human vision. It takes into a... more This article describes a contrast measure inspired by findings from human vision. It takes into account the frequency and orientation selectivity of cortical cells in the mammalian visual system. The input image is decomposed into different spatial frequency bands and orientations using Gabor filters. Then, a local directional contrast measure is computed for each spatial frequency band by introducing a
Proceedings of the 1996 IEEE National Radar Conference
The Jindalee high frequency OTH radar network sensors are capable of detecting and tracking a ver... more The Jindalee high frequency OTH radar network sensors are capable of detecting and tracking a very large number of tracks within surveillance regions that can overlap. The large number of tracks can lead to ambiguity especially on the regions boundaries. One potential solution to this problem involves the development of algorithms capable of associating tracks received from various sensors. This
Recent developments in digital technologies that make use of large scale image and video data, su... more Recent developments in digital technologies that make use of large scale image and video data, such as the internet, multimedia systems, digital TV, digital cinema, and mobile/wireless devices, have increased the need for efficient processing, storage, and transmission of visual information. It is now widely acknowledged that such technologies can further benefit by incorporating concepts from human vision and corresponding implementation of biologically inspired models. Indeed, in many applications, the human observer plays a crucial role in the decisionmaking tasks such as diagnosis, recognition, and evaluation based on visual assessment of images. Therefore, biologically inspired image/video processing and analysis approaches have been receiving considerable interest in recent years. This special issue presents some of the recent advances in image and video processing techniques inspired by the human visual system (HVS), with applications to multimedia, visual pattern recognition, surveillance, visual information coding and security, and other related subjects. The first paper by Beghdadi, Larabi, Bouzerdoum, and Iftekharuddin provides an overview of the state-of-the-art techniques in perceptual image processing, with particular emphasis on image enhancement, segmentation, and coding. The remaining articles are grouped into four categories, according to the topics addressed in the papers. The first group deals with perceptual video and image coding. The first paper entitled “Perceptual video coding based on MB classification and rate-distortion optimization,” by Guillotel, Aribuki, Olivier and Urban, exploits the perceptual image quality of macroblock in rate-distortion optimization to improve the perceptual quality of coded video sequences. The main idea is to introduce the perceptual distortion metric in the encoding loop in order to adapt the macroblock quantization parameters. A learning strategy is then applied to a number of sequences to provide a set of representative distortion–quantization curves for all macroblock types. The second paper by Hrarti, Saadane and Larabi, entitled “Attentional mechanisms driven adaptive quantization and selective bit allocation scheme for H.264/AVC,” proposes a saliency based
The accurate left ventricular boundary detection in echocardiographic images allow cardiologists ... more The accurate left ventricular boundary detection in echocardiographic images allow cardiologists to study and assess cardiomyopathy in patients. Due to the tedious and time consuming manner of manually tracing the borders, deformable models are generally used for left ventricle segmentations. However, most deformable models require a good initialization, which is usually outlined manually by the user. In this paper, we propose an automated left ventricle detection method for two-dimensional echocardiographic images that could serve as an initialization for deformable models. The proposed approach consists of pre-processing and post-processing stages, coupled with the watershed segmentation. The pre-processing stage enhances the overall contrast and reduces speckle noise, whereas the post-processing enhances the segmented region and avoids the papillary muscles. The performance of the proposed method is evaluated on real data. Experimental results show that it is suitable for automatic contour initialization since no prior assumptions nor human interventions are required. Besides, the computational time taken is also lower compared to an existing method.
A recurrent neural network is presented which performs quadratic optimization subject to bound co... more A recurrent neural network is presented which performs quadratic optimization subject to bound constraints on each of the optimization variables. The network is shown to be globally convergent, and conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and to roundoff errors. The optimization method employed by the neural network is shown to fall into the general class of gradient methods for constrained nonlinear optimization and, in contrast with penalty function methods, is guaranteed to yield only feasible solutions.
Proceedings of the 1994 IEEE International Conference on Robotics and Automation
Abstract Fully autonomous mobile robots often rely on an array of sensors to provide them with an... more Abstract Fully autonomous mobile robots often rely on an array of sensors to provide them with an adequate picture of their environment. Furthermore, these systems tend to have strict limitations in terms of available processing capability. Hence the so-called smart sensing ...
Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004.
This article describes a contrast measure inspired by findings from human vision. It takes into a... more This article describes a contrast measure inspired by findings from human vision. It takes into account the frequency and orientation selectivity of cortical cells in the mammalian visual system. The input image is decomposed into different spatial frequency bands and orientations using Gabor filters. Then, a local directional contrast measure is computed for each spatial frequency band by introducing a
Proceedings of the 1996 IEEE National Radar Conference
The Jindalee high frequency OTH radar network sensors are capable of detecting and tracking a ver... more The Jindalee high frequency OTH radar network sensors are capable of detecting and tracking a very large number of tracks within surveillance regions that can overlap. The large number of tracks can lead to ambiguity especially on the regions boundaries. One potential solution to this problem involves the development of algorithms capable of associating tracks received from various sensors. This
Recent developments in digital technologies that make use of large scale image and video data, su... more Recent developments in digital technologies that make use of large scale image and video data, such as the internet, multimedia systems, digital TV, digital cinema, and mobile/wireless devices, have increased the need for efficient processing, storage, and transmission of visual information. It is now widely acknowledged that such technologies can further benefit by incorporating concepts from human vision and corresponding implementation of biologically inspired models. Indeed, in many applications, the human observer plays a crucial role in the decisionmaking tasks such as diagnosis, recognition, and evaluation based on visual assessment of images. Therefore, biologically inspired image/video processing and analysis approaches have been receiving considerable interest in recent years. This special issue presents some of the recent advances in image and video processing techniques inspired by the human visual system (HVS), with applications to multimedia, visual pattern recognition, surveillance, visual information coding and security, and other related subjects. The first paper by Beghdadi, Larabi, Bouzerdoum, and Iftekharuddin provides an overview of the state-of-the-art techniques in perceptual image processing, with particular emphasis on image enhancement, segmentation, and coding. The remaining articles are grouped into four categories, according to the topics addressed in the papers. The first group deals with perceptual video and image coding. The first paper entitled “Perceptual video coding based on MB classification and rate-distortion optimization,” by Guillotel, Aribuki, Olivier and Urban, exploits the perceptual image quality of macroblock in rate-distortion optimization to improve the perceptual quality of coded video sequences. The main idea is to introduce the perceptual distortion metric in the encoding loop in order to adapt the macroblock quantization parameters. A learning strategy is then applied to a number of sequences to provide a set of representative distortion–quantization curves for all macroblock types. The second paper by Hrarti, Saadane and Larabi, entitled “Attentional mechanisms driven adaptive quantization and selective bit allocation scheme for H.264/AVC,” proposes a saliency based
A recurrent neural network is presented which performs quadratic optimisation subject to bound co... more A recurrent neural network is presented which performs quadratic optimisation subject to bound constraints on each of the optimisation variables. The optimisation strategy employed by the neural network falls into the general class of gradient methods for constrained nonlinear optimisation, and is compared briefly with the strategies employed by conventional techniques for bound-constrained quadratic optimisation. Conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. These conditions are shown to provide a tighter bound on the degree of exponential stability than that previously established for this network. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and roundoff-errors and to accelerate convergence
Uploads