Classifying image analysis techniques from their output

In this paper we discuss some main image processing techniques in order to propose a classification based upon the output these methods provide. Because despite a particular image analysis technique can be supervised or unsupervised, and can allow or not the existence of fuzzy information at some stage, each technique has been usually designed to focus on a specific objective, and their outputs are in fact different according to each objective. Thus, they are in fact different methods. But due to the essential relationship between them they are quite often confused. In particular, this paper pursues a clarification of the differences between image segmentation and edge detection, among other image processing techniques.

Core scan image analysis corrected for cracks, ODP Hole 154-926C

Drill cores are essential for the study of deep-sea sediments and on-land sites because often no suitable outcrop is available or accessible. These cores form the backbone of stratigraphical studies using and combining various dating techniques. Cyclostratigraphy is usually based on fast and inexpensive measurements of physical sediment properties. One indirect but highly valuable proxy for reconstructing the sediment composition and variability is sediment color. However, cracks and other disturbances in sediment cores may dramatically influence the quality of color data retrieved either directly from photospectrometry or derived from core image analysis. Here we present simple but powerful algorithms to extract color data from core images, and focus on routines to exclude cracks from these images. Results are discussed using the example of an ODP core from the Ceara Rise in the Central Atlantic. The crack correction approach presented highly improves the quality of color data and allows the easy incorporation of cracked cores into studies based on core images. This facilitates the quick and inexpensive generation of large color datasets directly from quantified core images, for cyclostratigraphy and other purposes.

Analysis of texture,

"COO-2118-0035."

Computer methods for analysis and synthesis of visual texture,

"C00-2118-0048."

Parallel image-processing for automated cervical smear analysis,

"COO-2118-0029."

Video image analysis of aggregates : a study report on evaluation of coarse aggregate shape and size properties using video imaging /

"Report no. FHWA-IL-UI-278"--Technical report documentation page.

Automatic texture segmentation for texture-based image retrieval

Texture-segmentation is the crucial initial step for texture-based image retrieval. Texture is the main difficulty faced to a segmentation method. Many image segmentation algorithms either can’t handle texture properly or can’t obtain texture features directly during segmentation which can be used for retrieval purpose. This paper describes an automatic texture segmentation algorithm based on a set of features derived from wavelet domain, which are effective in texture description for retrieval purpose. Simulation results show that the proposed algorithm can efficiently capture the textured regions in arbitrary images, with the features of each region extracted as well. The features of each textured region can be directly used to index image database with applications as texture-based image retrieval.

Extraction of texture features from arbitrary-shaped regions for image retrieval

Lots of work has been done in texture feature extraction for rectangular images, but not as much attention has been paid to the arbitrary-shaped regions available in region-based image retrieval (RBIR) systems. In This work, we present a texture feature extraction algorithm, based on projection onto convex sets (POCS) theory. POCS iteratively concentrates more and more energy into the selected coefficients from which texture features of an arbitrary-shaped region can be extracted. Experimental results demonstrate the effectiveness of the proposed algorithm for image retrieval purposes.

Quantification of axonal loss in Alzheimer’s disease: an image analysis study

The density of axons in the optic nerve, olfactory tract and corpus callosum was quantified in non-demented elderly subjects and in Alzheimer’s disease (AD) using an image analysis system. In each fibre tract, there was significant reduction in the density of axons in AD compared with non-demented subjects, the greatest reductions being observed in the olfactory tract and corpus callosum. Axonal loss in the optic nerve and olfactory tract was mainly of axons with smaller myelinated cross-sectional areas. In the corpus callosum, a reduction in the number of ‘thin’ and ‘thick’ fibres was observed in AD, but there was a proportionally greater loss of the ‘thick’ fibres. The data suggest significant degeneration of white matter fibre tracts in AD involving the smaller axons in the two sensory nerves and both large and small axons in the corpus callosum. Loss of axons in AD could reflect an associated white matter disorder and/or be secondary to neuronal degeneration.