Dipti Prasad Mukherjee

Scale space classification using area morphology

We explore the application of area morphology to image classification. From the input image, a scale space is created by successive application of an area morphology operator. The pixels within the scale space corresponding to the same image location form a scale space vector. A scale space vector therefore contains the intensity of a particular pixel for a given set of scales, determined in this approach by image granulometry. Using the standard k-means algorithm or the fuzzy c-means algorithm, the image pixels can be classified by clustering the associated scale space vectors. The scale space classifier presented here is rooted in the novel area open-close and area close-open scale spaces. Unlike other scale generating filters, the area operators affect the image by removing connected components within the image level sets that do not satisfy the minimum area criterion. To show that the area open-close and area close-open scale spaces provide an effective multiscale structure for image classification, we demonstrate the fidelity, causality, and edge localization properties for the scale spaces. The analysis also reveals that the area open-close and area close-open scale spaces improve classification by clustering members of similar objects more effectively than the fixed scale classifier. Experimental results are provided that demonstrate the reduction in intra-region classification error and in overall classification error given by the scale space classifier for classification applications where object scale is important. In both visual and objective comparisons, the scale space approach outperforms the traditional fixed scale clustering algorithms and the parametric Bayesian classifier for classification tasks that depend on object scale.

Cloud tracking by scale space classification

The problem of cloud tracking within a sequence of geo-stationary satellite images has direct relevance to the analysis of cloud life cycles and to the detection of cloud motion vectors (CMVs). The proposed approach first identifies a homogeneous consistent cloud mass for tracking and then establishes motion correspondence within an image sequence. In contrast to the crosscorrelation based approach as adopted in automatic CMV detection analysis, a scale space classifier is designed to detect cloud mass in the source image taken at time t and the destination image at time t+/spl delta/t. Boundaries of the extracted cloud segments are matched by computing a correspondence between high curvature points. This shape based method is capable of tracking in the cases of rotation, scaling, and shearing, while the correlation technique is limited to translational motion. The final tracking results provide motion magnitude and direction for each contour point, allowing reliable estimation of meteorological events and wind velocities aloft. With comparable computational expense, the scale space classification technique exceeds the performance of the traditional correlation-based approach in terms of reduced localization error and false matches.

Constraining active contour evolution via Lie Groups of transformation

We present a novel approach to constraining the evolution of active contours used in image analysis. The proposed approach constrains the final curve obtained at convergence of curve evolution to be related to the initial curve from which evolution begins through an element of a desired Lie group of plane transformations. Constraining curve evolution in such a way is important in numerous tracking applications where the contour being tracked in a certain frame is known to be related to the contour in the previous frame through a geometric transformation such as translation, rotation, or affine transformation, for example. It is also of importance in segmentation applications where the region to be segmented is known up to a geometric transformation. Our approach is based on suitably modifying the Euler-Lagrange descent equations by using the correspondence between Lie groups of plane actions and their Lie algebras of infinitesimal generators, and thereby ensures that curve evolution takes place on an orbit of the chosen transformation group while remaining a descent equation of the original functional. The main advantage of our approach is that it does not necessitate any knowledge of nor any modification to the original curve functional and is extremely straightforward to implement. Our approach therefore stands in sharp contrast to other approaches where the curve functional is modified by the addition of geometric penalty terms. We illustrate our algorithm on numerous real and synthetic examples.

Bacterial colony counting using distance transform

A distance-transform based technique is presented for the segmentation of monochrome images of colonies grown on membrane filters. This is used to count the number of Escherichia coli in a given water sample, which is used as a parameter for determining water quality. The result is compared with fuzzy c-means clustering approach.

Recognizing Architectural Distortion in Mammogram: A Multiscale Texture Modeling Approach with GMM

We propose a generative model for constructing an efficient set of distinctive textures for recognizing architectural distortion in digital mammograms. In the first layer of the proposed two-layer architecture, the mammogram is analyzed by a multiscale oriented filter bank to form texture descriptor of vectorized filter responses. Our model presumes that every mammogram can be characterized by a “bag of primitive texture patterns” and the set of textural primitives (or textons) is represented by a mixture of Gaussians which builds up the second layer of the proposed model. The observed textural descriptor in the first layer is assumed to be a stochastic realization of one (hard mapping) or more (soft mapping) textural primitive(s) from the second layer. The results obtained on two publicly available datasets, namely Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM), demonstrate the efficacy of the proposed approach.

Key Frame Estimation in Video Using Randomness Measure of Feature Point Pattern

In this paper, a generalized statistical tool is introduced to estimate key frames in a video sequence. The tool works based on the inter-relationship between different features of image frames in a video. The image feature vectors are plotted in feature space as points and a randomness measure is determined from the distribution of these points. The randomness measure of the feature vectors is defined with respect to simulated random point patterns and expressed as a probability value of a frame being a key frame. Since, depending on the video content more than one inter-relationship of features can be used to determine a single key frame, different probability values are derived to support a frame as a key frame. To integrate these probability values a combiner model is designed to uniquely decide the status of a key frame. The combiner model is based on the Dempster-Shafer theory of evidence. To demonstrate the idea, randomness measures, and consequently the probabilities of a frame to be a key frame, are obtained separately from spatial domain and frequency domain features. The combined probability value enhances the confidence in selecting a frame as a key frame. The result is tested on a number of standard video sequences and it outperforms the related approach

Fuzzy c -means approach to tissue classification in multimodal medical imaging

A fuzzy c-means approach is described for tissue segmentation of X-ray computed tomography (CT) and T1 weighted magnetic resonance (MR) images of the same crosssection of the human brain. A fuzzy set approach is then utilized to obtain a fused classification displaying the salient features of image data of the individual modalities.

Point landmarks for registration of CT and MR images

We propose here a point landmark based registration method utilizing geometric invariance properties of biomedical images. These point landmarks constitute entrance and exit points of concavities of individual structures and points of inflexion of curves, derived from the convex hull. Registration is performed in a canonical frame of reference. This technique is fast, semi-automatic and computationally inexpensive.

Recognizing interactions between human performers by `Dominating Pose Doublet'

A graph theoretic approach is proposed to recognize interactions (e.g., handshaking, punching, etc.) between two human performers in a video. Pose descriptors corresponding to each performer in the video are generated and clustered to form initial codebooks of human poses. Compact codebooks of dominating poses for each of the two performers are created by ranking the poses of the initial codebooks using two different methods. First, an average centrality measure of graph connectivity is introduced where poses are nodes in the graph. The dominating poses are graph nodes sharing a close semantic relationship with all other pose nodes and hence are expected to be at the central part of the graph. Second, a novel similarity measure is introduced for ranking dominating poses. The ‘pose doublets’, all possible combinations of dominating poses of the two performers, are ranked using an improved centrality measure of a bipartite graph. The set of ‘dominating pose doublets’ that best represents the corresponding interaction are selected using the perceptual analysis technique. The recognition results on standard interaction datasets show the efficacy of the proposed approach compared to the state-of-the-art.

Sodar image segmentation by fuzzy c -means

Sodar facsimile records provide meteorological information of the atmospheric boundary layer (ABL). Segmentation of sodar image (digitised sodar record) is vital for subsequent interpretation of ABL structure. The problem of segmentation is presented here as classification problem. Fuzzy c-means classification algorithm has been adopted for segmentation purpose using a set of four feature vectors calculated over a mask such that they characterise the nature of local grey value distribution. The classified images are also compared to another segmentation technique. The results presented prove the definite merits of the proposed technique.