This paper discusses a method of improving the discrimination power of a certain class of GLCM features. We investigate where co-occurrence matrix features derive their discriminatory power, and provide a theoretical basis for improving this method. Finally, we present examples of discrimination improvement using real-world data. Cross-validation results… (More)
Statistical Geometric Features (SGF) have recently been proposed for the classification of image textures. The SGF method is easily extended to use other geometric properties of connected regions. Following a brief review of the method, we propose such an extension to the set of SGF features for the purpose of classifying cervical cell textures. The… (More)
This paper presents preliminary results for the classiication of Pap Smear cell nuclei, using Gray Level Co-occurrence Matrix (GLCM) textural features. We outline a method of nuclear segment-ation using fast morphological gray-scale transforms. For each segmented nucleus, features derived from a modiied form of the GLCM are extracted over several angle and… (More)
The following paper details results for the classiication of Papanicolaou stained cervical smear cell nuclei, using Gray Level Co-occurrence Matrix (GLCM) and Markov Random Field (MRF) image textural features. Following imaging, cell nuclei are extracted via fast morphological gray-scale transforms. Textural features comprising seven GLCM features and eight… (More)
We exploit a property of microalgae-that of their ability to autofluoresce when exposed to epifluorescence illumination-to tackle the problem of detecting and analysing microalgae in sediment samples containing complex scenes. We have added fluorescence excitation to the hardware portion of our microalgae image processing system. We quantitatively measured… (More)
This report investigates a recently published method of texture analysis called Statistical Geometric Features (SGF). The method is rstly reviewed, salient features discussed, and deecien-cies in terms of its application to texture analysis are identiied. New features more appropriate to cervical cell texture analysis are deened and trialed. Those features… (More)
We will outline the method of scaled gradient watersheds which we proposed recently and demonstrate it by an application to the extraction of classiication features from the nuclear texture in cervical cells.
Notice: Changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source: Notice: Changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document. For a… (More)