
	Where results make sense

Topic: Image segmentation

Related Topics

Image processing

Computer vision

Registration

Noise reduction

Computer graphics

Color space

Volition

Medical imaging

Cognitivism (psychology)

Cognition

Belief

Mental functions

Cognitive psychology

Behavior

	Image Segmentation (Site not responding. Last check: 2007-10-24)
		C++ implementation of the image segmentation algorithm described in the paper:
		Segmentation parameters: sigma = 0.5, K = 500, min = 50.
		Segmentation parameters: sigma = 0.5, K = 1000, min = 100.
	people.cs.uchicago.edu /~pff/segment (53 words)

	Segmentation (image processing) - Wikipedia, the free encyclopedia
		In image analysis, segmentation is the partitioning of a digital image into multiple regions (sets of pixels), according to a given criterion.
		Some other segmentation algorithms are based on segmenting images into regions of similar texture according to wavelet or Fourier transforms.
		Image segmentations are computed at multiple scales in scale-space and sometimes propagated from coarse to fine scales; see scale-space segmentation.
	en.wikipedia.org /wiki/Segmentation_(image_processing) (360 words)

	February 1993/Image Processing, Part 9: Histogram-Based Image Segmentation (Site not responding. Last check: 2007-10-24)
		Image segmentation is the process of dividing an image into regions or objects.
		The secondary peak in the histogram at gray level 8 indicates it is the primary gray level for the object in the image.
		On the left side of the photograph, the second pass thresholded the image array and found the background mean to be 94 and the object mean to be 205.
	www.tcnj.edu /~hernande/cujv5/html/11.02/phillips/phillips.htm (2984 words)

	Image segmentation studies (Site not responding. Last check: 2007-10-24)
		Ten images were used for training and 12 points were chosen from the background and 12 from the interior of the object for each image.
		The segmented image is then analysed for estimating the regions of interest and the results are compared against previously known diagnosis of the radiologist.
		There are two aspects in a segmented image representation: the geometrical aspect which describes the shape of regions, and the topological aspect which describes neighbourhoods and inclusions of regions.
	www.dcs.ex.ac.uk /research/pann/master/web2/sreview.htm (11863 words)

	image segmentation
		Image segmentation is a process of segmenting an image into a group of homogeneous regions according to the characteristics such as color and texture.
		So, we may model blurred image as hierarchical MRFs that the higher level is used to model the segmenting of image pixel into regions and the lower level is used to model blurring matrix of each region.
		To segment noisy and blurred images, we need to estimate a number of unknown parameters such as mean and variance of noise and blurring matrices of each region.
	ailab.kyungpook.ac.kr /ImgUnd/MRF/imagesegmentation.htm (1742 words)

	Viper Segmentation page
		While segmentation automated techniques are very advanced, they still are not capable of mapping the image into a semantically meaningful decomposition.
		It is the context in which an image is viewed that determines the sense (interpretation) of its components.
		Two main factors are the scale at which the image is looked at (defining the sense of a "detail") and the semantic interpretation allowing for grouping visually unrelated components into a meaningful group.
	viper.unige.ch /research/segmentation/index.html (724 words)

	Image Segmentation (Site not responding. Last check: 2007-10-24)
		For gray-level images, each pixel corresponds to an oscillator, and two pixels establish a permanent connection with the weight that is reciprocal to the difference of their pixel values.
		The entire image is segmented into 17 regions, each of which corresponds to a different density in the figure, which indicates the phases of oscillators.
		The segments are put together in Figure 7b merely for illustration purposes.
	www.cs.utexas.edu /~nn/web-pubs/htmlbook96/wang/node9.html (343 words)

	3-D IMAGE SEGMENTATION
		The pixel detection process is called image segmentation, which identifies the attributes of pixels and defines the boundaries for pixels that belong to same group.
		Image segmentation by thresholding is a simple but powerful approach for images containing solid objects which are distinguishable from the background or other objects in terms of pixel intensity values.
		The texture based segmentation starts with a user defined training area, where texture characteristics are calculated and then applied as a pixel classifier to other pixels in one cross-section image or the entire volume to separate them into groups.
	www.ablesw.com /3d-doctor/3dseg.html (1182 words)

	Image Segmentation
		Image segmentation --- for homogeneous grey/color/texture region processes.
		A segmentation algorithm must be general enough to handle many families of image models in a principled way.
		Image segmentation is a computational process and should NOT be treated as a task.
	civs.stat.ucla.edu /Segmentation/Segment.htm (798 words)

	Image Segmentation
		Segmentation is an important part of practically any automated image recognition system, because it is at this moment that one extracts the interesting objects, for further processing such as description or recognition.
		Segmentation of an image is in practice the classification of each image pixel to one of the image parts.
		The two halves of the image labelled ``original'' contain peaks of random height, but of different shape: in the bottom half, the peaks are steeper than in the top half.
	rkb.home.cern.ch /rkb/AN16pp/node131.html (475 words)

	IRM: Integrated Region Matching for Image Retrieval
		The same algorithm may segment another image of a dog into six regions: the body of the dog, the front leg(s) of the dog, the rear leg(s) of the dog, the eye(s), the background grass, and the sky.
		Being aware that segmentation cannot be perfect, we ``soften'' the matching by allowing one region of an image to be matched to several regions of another image.
		The query image in Figure 5 is difficult to match because objects in the image are not distinctive from the background.
	www-db.stanford.edu /IMAGE/Simplicity/ACM00.1/li (5394 words)

	Graphics & Media lab: "GrowCut" - Interactive Multi-Label N-D Image Segmentation (Site not responding. Last check: 2007-10-24)
		Image segmentation is an inherent part of important image processing applications like automated medical images analysis and photo editing.
		Fully automated segmentation techniques are being constantly improved, however, current state-of-the art is such that no automated image segmentation technique can be applied fully autonomously with reliable results in general case.
		In many cases they are graylevel and objects that should be segmented are very different in their structure and appearance from the objects that are common in photo editing.
	graphics.cs.msu.su /en/research/Segment/index.html (771 words)

	Random Walker Image Segmentation Demo Page
		A primary strength of the random walker segmentation approach is a natural ability to perform the segmentation even in the presence of a degraded boundary.
		This property of weak/noisy boundary resistance is crucial in the segmentation of real-world images.
		The segmentation target is the aorta in a low-resolution CT scan.
	www.cns.bu.edu /~lgrady/Random_Walker_Image_Segmentation.html (566 words)

	Image Segmentation Demands Fast Adaptive Computing Electronic News - Find Articles
		This issue rests squarely on image segmentation, a part of computer vision and pattern recognition, and the fact that typical DSP technology lacks the computational power to efficiently process the algorithms that support image segmentation.
		Image segmentation analyzes the visual information contained in digital images by describing what is in a visual scene and where it is located.
		And, according to a given application, image segmentation is required to provide analysis and interpretation of the input data.
	www.findarticles.com /p/articles/mi_m0EKF/is_39_47/ai_78690847 (919 words)

	Image Segmentation (Site not responding. Last check: 2007-10-24)
		Image segmentation is the most important processing step in a low level vision system.
		It consists on the division of the image into a group of elemental disjoint regions characterized by the constancy of some property (grey level, colour, texture, etc.).
		Image segmentation is a previous step in any image interpretation system, the correction of the results will greatly depend on the segmentation process results quality.
	varpa.lfcia.org /ImageSegmentation.html (66 words)

	Image Segmentation
		Texture segmentation is the process by which an image is segmented into a group of homogeneous regions according to texture.
		Texture segmentation are very useful for image understanding, for example, retrieving images with similar textures from a database and extracting text region in image and so on [1, 2].
		Structural methods seek to partition images under the assumption that the textures in the image have detectable primitive elements, arranged according to placement rules.
	ailab.kyungpook.ac.kr /ImgUnd/Texture/video-introduction.html (781 words)

	Fuzzy Image Processing: Fuzzy Image Segmentation
		The different theoretical components of fuzzy image processing provide us with diverse possibilities for development of new segmentation techniques.
		Fuzzy clustering is the oldest fuzzy approach to image segmentation.
		If we interpret the image features as linguistic variables, then we can use fuzzy if-then rules to segment the image into different regions.
	pami.uwaterloo.ca /tizhoosh/segment.htm (358 words)

	Image Segmentation.
		A central problem, called segmentation, is to distinguish objects from background [10].
		For intensity images (ie, those represented by point-wise intensity levels) four popular approaches are: threshold techniques, edge-based methods, region-based techniques, and connectivity-preserving relaxation methods.
		A connectivity-preserving relaxation-based segmentation method, usually referred to as the active contour model, was proposed recently.
	people.csail.mit.edu /seth/pubs/taskforce/paragraph3_5_0_0_3.html (491 words)

	IRM: Integrated Region Matching for Image Retrieval
		The same algorithm may segment another image of a dog into six regions: the body of the dog, the front leg(s) of the dog, the rear leg(s) of the dog, the eye(s), the background grass, and the sky.
		Being aware that segmentation cannot be perfect, we ``soften'' the matching by allowing one region of an image to be matched to several regions of another image.
		The query image in Figure 5 is difficult to match because objects in the image are not distinctive from the background.
	infolab.stanford.edu /IMAGE/Simplicity/ACM00.1/li (5394 words)

	Segmentation & Registration for Microscopy Imaging
		Segmenting the inner boundary of a duct with the Live-Wire.
		Segmenting the outter boundary of a duct with the Live-Wire.
		This method would be used in a multi-scale framework, and would at the same time register two images and computing the transformation from one image to the other in order to warp the boundaries of the object extracted in one image to the other giving automatically the segmentation result.
	math.lbl.gov /~deschamp/html/lifeScience.html (2324 words)

	Interactive Supercomputing: Success Stories
		Image segmentation is a technique used in computer vision for identifying regions in an image as separate components.
		Regions of the original image thought to be part of the same object are colored with the same color.
		To parallelize the algorithms, the images were stored as distributed matrices on the parallel server; the watershed segmentation algorithms were run on each processor's data; and the segmented image slices were merged back together in MATLAB.
	www.interactivesupercomputing.com /success/imagesegmentation.php (301 words)

	Amazon.com: Genetic Learning for Adaptive Image Segmentation (The International Series in Engineering and Computer ... (Site not responding. Last check: 2007-10-24)
		Image segmentation is generally the first task in any automated image understanding application, such as autonomous vehicle navigation, object recognition, photointerpretation, etc. All subsequent tasks, such as feature extraction, object detection, and object recognition, rely heavily on the quality of segmentation.
		One of the fundamental weaknesses of current image segmentation algorithms is their inability to adapt the segmentation process as real-world changes are reflected in the image.
		Image segmentation is a process of partitioning an image into different regions that are homogeneous or "similar" in some image characteristics.
	www.amazon.com /Learning-Adaptive-Segmentation-International-Engineering/dp/0792394917 (1194 words)

	Perceptual Color Image Segmentation
		The textures in the image are taken from the MIT VisTex database.
		Before the probabilistic relaxation scheme is applied to the image at the last/coarsest level of the pyramid, we perform a set of pre-processing on this blurred image.
		First, the segmentation algorithm is quite sensitive to the initial value of K, as can be seen from the different segmentations resulting from two different K values for the grass image.
	socrates.berkeley.edu /~angichau/cs223b/finalproj/index.html (2780 words)

	The Watershed Transformation page
		Two images are generated from the scene: an average image (emphasizing the still regions of the scene) and a differential image (enhancing the moving parts of the scene).
		From this image, a new criterion function is built (based on the relative heights of the walls separating the initial catchment basins).
		The watershed transformation applied to this image provides a higher level of hierarchy in the segmented image (thus suppressing much of the over-segmentation).
	cmm.ensmp.fr /~beucher/wtshed.html (614 words)

	Vision Research Lab - Image Segmentation
		This image segmentation method uses image diffusion based on an edge vector field based on color and/or texture.
		This image segmentation utilizes an edge vector field (EVF) within the curve evolution framework by using both color and texture features.
		Edge Flow is an image segmentation scheme appropriate for large images and database retrieval.
	vision.ece.ucsb.edu /segmentation (150 words)

	IBM Research \| IBM Haifa Research Lab \| SEGEN Image Segmentation Engine
		A region-based approach is the method of choice when images must be divided into connected homogeneous segments, which can be further classified more efficiently and with higher accuracy than unsegmented images.
		SEGEN does not depend on image dimension and connectivity, and can be easily adapted to handle different types of images.
		SEGEN can also be combined with a number of other image processing techniques, such as using various color spaces, selecting an adequate filter, or using different preprocessing procedures to achieve the initial segmentation needed for enhancing image processing.
	www.research.ibm.com /haifa/projects/image/segen/index.html (225 words)

	Image Segmentation
		The primary goal of this research is to develop image analysis methods that can be used to detect bottom type change in shallow waters using data obtained from airborne or spaceborne hyperspectral imaging spectrometers.
		With the single assumption of a locally uniform in-water diffuse attenuation coefficient, we are able to estimate atmospheric path radiance over regions of constant bottom type based on deviations between model prediction and remotely observed changes in radiance that occur with changes in bottom depth.
		Briefly, in the single-band case the average and variance of band intensity is determined for a block of nine pixels centered about a given pixel and for blocks of six pixels each extending from the central pixel in the n, s, e, w, ne, nw, se, sw directions.
	ceeserver.cee.cornell.edu /wdp2/RemoteSensing/Atmos_Segment/Monger.html (3158 words)

	Normalized Cuts and Image Segmentation (Site not responding. Last check: 2007-10-24)
		A large amount of the work on image segmentation and data clustering use segmentation criteria based on local properties of a data set.
		This paper's segmentation algorithm is able to extract the major components of five different scenes without getting thrown off by small variations inside the components.
		There are various ways in which the running time of the segmentation algorithm can be improved, and the segmentations themselves are promising in that the extracted regions do in fact seem to separate out the major components of the ``big picture" of a scene.
	www.stanford.edu /~ctj/liteseer/segparmf/shi00normalized/shi00normalized.html (333 words)

Try your search on: Qwika (all wikis)