Showing papers by "Majid Mirmehdi published in 2003"
TL;DR: This study indicates that automated evaluation of digital retinal images could be used to screen for exudative diabetic retinopathy, where the trade off between sensitivity and specificity was appropriately balanced for this particular problem.
Abstract: Aim: To identify retinal exudates automatically from colour retinal images.
Methods: The colour retinal images were segmented using fuzzy C-means clustering following some key preprocessing steps. To classify the segmented regions into exudates and non-exudates, an artificial neural network classifier was investigated.
Results: The proposed system can achieve a diagnostic accuracy with 95.0% sensitivity and 88.9% specificity for the identification of images containing any evidence of retinopathy, where the trade off between sensitivity and specificity was appropriately balanced for this particular problem. Furthermore, it demonstrates 93.0% sensitivity and 94.1% specificity in terms of exudate based classification.
Conclusions: This study indicates that automated evaluation of digital retinal images could be used to screen for exudative diabetic retinopathy.
270 citations
TL;DR: A novel extension to the commonly used 2D projection profiles in document recognition to locate the horizontal vanishing point of the text plane is introduced, useful for ‘point-and-click’ scanning or when generally seeking regions of text in a scene.
75 citations
TL;DR: A novel approach to the detection and classification of shot transitions in video sequences including cuts, fades and dissolves is introduced that uses the average inter-frame correlation coefficient and block-based motion estimation to track image blocks through the video sequence and to distinguish changes caused by shot transitions from those caused by camera and object motion.
53 citations
17 Sep 2003
TL;DR: In this article, a novel approach is presented to select multiple key frames within an isolated video shot where there is camera motion causing significant scene change, which is achieved by determining the dominant motion between frame pairs whose similarities are represented using a directed weighted graph.
Abstract: A novel approach is presented to select multiple key frames within an isolated video shot where there is camera motion causing significant scene change. This is achieved by determining the dominant motion between frame pairs whose similarities are represented using a directed weighted graph. The shortest path in the graph, found using the A* search algorithm, designates the key frames. The overall method can be applied to extract a set of key frames which portray both the video content and camera motions, all of which are useful features for video indexing and retrieval.
28 citations
01 Sep 2003
TL;DR: A novel graph theoretic approach is presented to extract representative key frames corresponding to the shortest path of the graph for each shot, distinguishing amongst paths of similar weight by examining the standard deviation of their constituent edge weights.
Abstract: Summarising video data is essential to enable content-based video indexing and retrieval. A novel graph theoretic approach is presented to extract representative key frames corresponding to the shortest path of the graph for each shot. We distinguish further amongst paths of similar weight by examining the standard deviation of their constituent edge weights which improves the distribution of the selected key frames. The perceived camera motions contained within each shot are also annotated to introduce a further level of indexing and searching video content.
22 citations
TL;DR: A novel automatic text reading system is introduced using an active camera focused on text regions already located in the scene (using this recent work), and a number of images are captured over the text region to construct a high-resolution mosaic composite of the whole region.
Abstract: Document recognition is a lively research area with much effort concentrated on optical character recognition. Less attention is paid to locating and extracting text from the general (non-desktop, non-scanner) environment. Such contact-free extraction of text from a general scene has applications in the context of wearable computing, robotic vision, point and click document capture, or as an aid for visually handicapped people. Here, a novel automatic text reading system is introduced using an active camera focused on text regions already located in the scene (using our recent work). Initially, a located region of text is analysed to determine the optimal zoom that would foveate onto it. Then a number of images are captured over the text region to construct a high-resolution mosaic composite of the whole region. This magnified image of the text is suitable for reading by humans or for recognition by OCR, or even for text-to speech synthesis. Although we employed a low resolution camera, we still obtained very good results.
13 citations
03 Aug 2003
TL;DR: Using this selection method along with a text-processing pipeline and OCR, a general purpose hand-held device (such as a PDA or mobile phone) with a camera could be used as effectively as single-purpose pen scanning devices.
Abstract: We describe a method to enable the selection of specific text regions with a hand-held camera by means of projecting a structured light pointer on the document. The user indicates the text required by dragging the laser pointer over it while a sequence of images is captured. By tracking the motion of the camera over the document and matching the trajectory to the actual text, the system is able to precisely determine the text portion the user intended to capture. By using this selection method along with a text-processing pipeline and OCR, a general purpose hand-held device (such as a PDA or mobile phone) with a camera could be used as effectively as single-purpose pen scanning devices. We present our results showing successful capture and extraction of text.
12 citations
01 Jan 2003
TL;DR: This paper presents an alternative to Elastography by speckle tracking ultrasonic frames quantifying both motion and strain by combining two similarity measures for varying echographic content including displacement processing.
Abstract: This paper presents an alternative to Elastography by speckle tracking ultrasonic frames quantifying both motion and strain. We combine two similarity measures for varying echographic content including displacement processing, with interframe and trajectory performance measured on extensive synthetic and in vitro data.
8 citations
24 Nov 2003
TL;DR: A novel method is introduced to force a geometric-based snake be more tolerant towards weak edges and noise in images by integrating gradient flow forces with region constraints obtained from diffused region segmentation forces.
Abstract: A novel method is introduced to force a geometric-based snake be more tolerant towards weak edges and noise in images. The method integrates gradient flow forces with region constraints obtained from diffused region segmentation forces. The diffusion is obtained from the region map vector flow field. This extra region force gives the snake a global view of the boundary information within the image. We present results on both graylevel and colour images.
7 citations
07 Jul 2003
TL;DR: In this article, a 2D variable sized block matching algorithm with hierarchical exhaustive search is proposed to examine tissue deformations in dynamic musculoskeletal ultrasonograhy.
Abstract: We propose a 2D variable sized block matching algorithm with hierarchical exhaustive search to examine tissue deformations in dynamic musculoskeletal ultrasonograhy. Novel aspects include improved matching by updating reference and candidate blocks at each scale and the application area. Performance is quantified on controlled in vitro gold standard (groundtruth) sequences and clinical in vivo data. We extend the process by refining displacements to sub-pixel accuracy. The proposed technique is validated, by application, to yield quantitatively reliable results.
5 citations
01 Sep 2003
TL;DR: The principles of 2D interframe displacements produced by the earlier work using hierarchical variable block size matching are extended, to quantify displacement trajectories and present trajectory strain that yields a novel strain history for musculoskeletal tendon tissue samples.
Abstract: A novel methodology to quantify displacements and strain in musculoskeletal ultrasound sequences is presented. We extend the principles of 2D interframe displacements produced by our earlier work using hierarchical variable block size matching, to quantify displacement trajectories. We provide novel solutions for probe motion, quantification of objects moving in the 3D volume traversing the 2D plane, and improving the temporal coherence of displacements for longer image sequences than the frame pairs traditionally applied in ultrasound. We also present trajectory strain that yields a novel strain history for musculoskeletal tendon tissue samples.
Journal Article•
01 Jan 2003
TL;DR: A new region-aided, geometric, colour active contour that integrates gradient flow forces with region constraints is proposed that gives the snake a global view of the boundary information within the image which helps detect fuzzy boundaries and overcome noisy regions.
Abstract: The standardgeometric orgeodesic active contourisa powerful segmentation method, yet it is susceptible to weak edges and image noise. We propose a new region-aided, geometric, colour active contour that integrates gradient flow forces with region constraints. These constraints are composed of image region vector flow forces obtained through the diffusion of the region segmentation map. The extra region force gives the snake a global view of the boundary information within the image which, along with the local gradient flow, helps detect fuzzy boundaries and overcome noisy regions. The partial differential equation (PDE) resulting from this integration of image gradient flow and diffused region flow is implemented using the level set approach.