Showing papers by "Sidharta Gautama published in 2007"
TL;DR: This paper uses error-tolerant graph matching to find correspondences between the detected image features and the geospatial vector data and shows that the number of null labels is an important measure to determine relevancy.
Abstract: In this paper, we present a graph-based approach for mining geospatial data. The system uses error-tolerant graph matching to find correspondences between the detected image features and the geospatial vector data. Spatial relations between objects are used to find a reliable object-to-object mapping. Graph matching is used as a flexible query mechanism to answer the spatial query. A condition based on the expected graph error has been presented which allows determining the bounds of error tolerance and, in this way, characterizes the relevancy of a query solution. We show that the number of null labels is an important measure to determine relevancy. To be able to correctly interpret the matching results in terms of relevancy, the derived bounds of error tolerance are essential
9 citations
28 Aug 2007
TL;DR: In this article, shape information encoded in contour energy components values can be used for detection of microscopic organisms in population images, and features based on shape and geometrical statistical data obtained from samples of optimized contour lines integrated in the framework of Bayesian inference for recognition of individual specimens.
Abstract: In this paper we study how shape information encoded in contour energy components values can be used for detection of microscopic organisms in population images. We proposed features based on shape and geometrical statistical data obtained from samples of optimized contour lines integrated in the framework of Bayesian inference for recognition of individual specimens. Compared with common geometric features the results show that patterns present in the image allow better detection of a considerable amount of individuals even in cluttered regions when sufficient shape information is retained. Therefore providing an alternative to building a specific shape model or imposing specific constrains on the interaction of overlapping objects.
8 citations
Journal Article•
TL;DR: Results show that patterns present in the image allow better detection of a considerable amount of individuals even in cluttered regions when sufficient shape information is retained, providing an alternative to building a specific shape model or imposing specific constrains on the interaction of overlapping objects.
Abstract: In this paper we study how shape information encoded in contour energy components values can be used for detection of microscopic organisms in population images. We proposed features based on shape and geometrical statistical data obtained from samples of optimized contour lines integrated in the framework of Bayesian inference for recognition of individual specimens. Compared with common geometric features the results show that patterns present in the image allow better detection of a considerable amount of individuals even in cluttered regions when sufficient shape information is retained. Therefore providing an alternative to building a specific shape model or imposing specific constrains on the interaction of overlapping objects.
8 citations
23 Jul 2007
TL;DR: It is shown that when used for remote sensing images this leads to 'over- reconstruction', with a decreased classification performance as a result, and a new method called 'partial reconstruction' is proposed to overcome this problem and still be able to preserve the shape of objects.
Abstract: Meter to sub-meter resolution satellite images have generated new interests in extracting man-made structures in the urban area. However, classification accuracies for such purposes are far from satisfactory. Spectral characteristics of urban land cover classes are so similar that they cannot be separated using only spectral information. As a result, there is an increased interest in incorporating geometrical information. One possible approach is the use of a morphological profile [1]. This profile contains information about the size of objects. In literature this is usually combined with morphological reconstruction to better preserve the shapes of objects. In this paper, we show that when used for remote sensing images this leads to 'over- reconstruction', with a decreased classification performance as a result. We propose a new method called 'partial reconstruction' to overcome this problem and still be able to preserve the shape of objects. Classification experiments show a better performance with partial reconstruction.
6 citations
22 Aug 2007
TL;DR: An approach to perform automated analysis of nematodes in population images by studying how shape similarity in the objects of interest, is encoded in active contour energy component values and exploit them to define shape features.
Abstract: In this paper we present an approach to perform automated analysis of nematodes in population images. Occlusion, shape variability and structural noise make reliable recognition of individuals a task difficult. Our approach relies on shape and geometrical statistical data obtained from samples of segmented lines. We study how shape similarity in the objects of interest, is encoded in active contour energy component values and exploit them to define shape features. Without having to build a specific model or making explicit assumptions on the interaction of overlapping objects, our results show that a considerable number of individual can be extracted even in highly cluttered regions when shape information is consistent with the patterns found in a given sample set.
2 citations
01 Jan 2007
TL;DR: An automatic analysis algorithm of the microtubules in (EB1) fluorescence images is proposed based on a segmentation technique based on mathematical morphology which extracts the micro Tubules out of a 2D image.
Abstract: The study of microtubules by biologists is a very time consuming task. To support the research on microtubules, this paper proposes an automatic analysis algorithm of the microtubules in (EB1) fluorescence images. The proposed algorithm consist of two parts. The first part is a segmentation technique based on mathematical morphology which extracts the microtubules out of a 2D image. After the extraction of the microtubules a tracking algorithm is started to extract information on the dynamics of the microtubules in video. Keywords— Segmentation, Tracking, Kalman filter, microtubules
Proceedings Article•
09 Aug 2007TL;DR: It is shown that bad quality can often be stated, but that it is difficult to confirm good quality when the quality of the reference data is insufficient, and the method is tested and evaluated.
Abstract: In the past, theories of quality measuring of imperfect data have always assumed the use of perfect reference data. In practice, this isn't always the case. In our new approach we consider the possibility of measuring quality using imperfect reference data. Especially the use of classified satellite images is considered. The question we want to answer is what can be said about the quality of a questioned object taking the quality of the reference data as input: is it good, is it bad or is it unknown? In first instance, an imperfection model for the reference data is built based on possibility theory. From this we extract a fuzzy egg-yolk model, consisting of two parts: a fuzzy set of what must be in the object and a fuzzy set of what might be in the object. A special buffering operation is defined to build in tolerance in relation to the mistakes in the classified satellite images. Operators are defined for measuring quality using this model. Finally the method is tested and evaluated. It is shown that bad quality can often be stated, but that it is difficult to confirm good quality when the quality of the reference data is insufficient.