A review on image segmentation techniques

A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottom-up) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented.

Hybrid image segmentation using watersheds and fast region merging

This paper presents a methodology for evaluation of low-level image analysis methods, using binarization (two-level thresholding) as an example. Binarization of scanned gray scale images is the first step in most document image analysis systems. Selection of an appropriate binarization method for an input image domain is a difficult problem. Typically, a human expert evaluates the binarized images according to his/her visual criteria. However, to conduct an objective evaluation, one needs to investigate how well the subsequent image analysis steps will perform on the binarized image. We call this approach goal-directed evaluation, and it can be used to evaluate other low-level image processing methods as well. Our evaluation of binarization methods is in the context of digit recognition, so we define the performance of the character recognition module as the objective measure. Eleven different locally adaptive binarization methods were evaluated, and Niblack's method gave the best performance.

Goal-directed evaluation of binarization methods

License plate recognition (LPR) algorithms in images or videos are generally composed of the following three processing steps: 1) extraction of a license plate region; 2) segmentation of the plate characters; and 3) recognition of each character This task is quite challenging due to the diversity of plate formats and the nonuniform outdoor illumination conditions during image acquisition Therefore, most approaches work only under restricted conditions such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds Numerous techniques have been developed for LPR in still images or video sequences, and the purpose of this paper is to categorize and assess them Issues such as processing time, computational power, and recognition rate are also addressed, when available Finally, this paper offers to researchers a link to a public image database to define a common reference point for LPR algorithmic assessment

/pdf/license-plate-recognition-from-still-images-and-video-njnnbay5h5.pdf

License Plate Recognition From Still Images and Video Sequences: A Survey

Image segmentation plays a crucial role in many medical imaging applications by automating or facilitating the delineation of anatomical structures and other regions of interest. We present herein a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Current segmentation approaches are reviewed with an emphasis placed on revealing the advantages and disadvantages of these methods for medical imaging applications. The use of image segmentation in different imaging modalities is also described along with the difficulties encountered in each modality. We conclude with a discussion on the future of image segmentation methods in biomedical research.

A Survey of Current Methods in Medical Image Segmentation

Several model-based algorithms for threshold selection are presented, concentrating on the two-population univariate case in which an image contains an object and background. It is shown how the main ideas behind two important nonspatial thresholding algorithms follow from classical discriminant analysis. Novel thresholding algorithms that make use of available local/spatial information are then given. It is found that an algorithm using alternating mean thresholding and median filtering provides an acceptable method when the image is relatively highly contaminated, and seems to depend less on initial values than other procedures. The methods are also applicable to multispectral k-population images. >

/pdf/a-spatial-thresholding-method-for-image-segmentation-4bfe942w6k.pdf

A spatial thresholding method for image segmentation

In many applications in computer vision and signal processing, it is necessary to assimilate data from multiple sources. This is a particularly important issue in medical imaging, where information on a patient may be available from a number of different modalities. As a result, there has been much recent research interest in this area. The authors suggest an additional Bayesian method which generates a segmented classification concurrently with improving reconstructions of a set of registered images. A synthetic example is used to demonstrate the subjectives and benefits of this proposed approach. Two medical applications, one fusing computed tomography (CT) and single photon emission computed tomography (SPECT) brain scans, and the other magnetic resonance (MR) images at two different resolutions, are considered.

Bayesian fused classification of medical images

Techniques for online gesture recognition on workstations

Penrose hypothesized that fingerprint patterns such as loops, whorls, etc. are formed by ridges corresponding to the lines of curvature of the skin of the embryo at the time when the ridges were being formed. Under this hypothesis, Smith (1979) has shown analytically how some patterns emerge. In this paper it is shown that (i) Smith's differential equation has an exact solution and (ii) the extension given here supplies the remaining important patterns.

On the Penrose hypothesis on fingerprint patterns.

It has gradually been recognised that Bayesian algorithms are more widely applicable and reliable than ad hoc algorithms. Advantages include the use of explicit and realistic stochastic models making it easier to understand the working behind the algorithm and allowing confidence statements about conclusions. The authors propose a method, within a Bayesian framework, to assimilate information from images obtained from different modalities at different resolutions. The algorithm is used with a pair of images, from which a fused high resolution image and improved data reconstructions are simultaneously obtained. The authors illustrate their method by 2 examples, the first fuses a pair of SPECT and CT phantom images and the second a pair of MR brain scan images, obtained from different acquisition techniques. The authors provide a pseudo-comparison of the latter example with a commercially available package called ANALYZE. However, the phantom images from physical experiment given here provide a true validation and performance of the model.

http://ieeexplore.ieee.org/iel3/3806/11134/00534057.pdf

T.J. Hainsworth

Papers

A spatial thresholding method for image segmentation

Bayesian fused classification of medical images

Techniques for online gesture recognition on workstations

On the Penrose hypothesis on fingerprint patterns.

Hierarchical Bayesian classification of multimodal medical images