Surface shape from the deformation of apparent contours

The spatiotemporal analysis of deforming silhouettes (apparent contours) is here extended using the mathematics of perspective projections and tools from differential geometry. Analysis of the image motion of a silhouette or apparent contour enables computation of local surface curvature along the corresponding contour generator on the surface, assuming viewer motion is known. To perform the analysis, a spatiotemporal parameterization of image-curve motion is needed, but is underconstrained (a manifestation of the well-known aperture problem). It is shown that an epipolar parameterization is most naturally matched to the recovery of surface curvature.One immediate facility afforded by the analysis is that surface patches can be reconstructed in the vicinity of contour generators. Once surface curvature is known, it is possible to discriminate extremal contours from other fixed curves in space. Furthermore, the known robustness of parallax as a cue to depth extends to the case of surface curvature. Its derivative—rate of parallax—is shown theoretically to be a curvature cue that is robust to uncertainties in the known viewer motion. This robustness has been confirmed in experiments.Finally, the power of the new analysis for robotics applications is demonstrated. Illustrations are given of an Adept robot, equipped with a CCD camera, circumnavigating curved obstacles. When further equipped with a suction gripper the robot manipulator can pick up an object by its curved surface, under visual guidance.     

Fast classification of discrete shape contours

A fast and novel nonoverlapping planar shape recognition scheme with efficiency virtually independent of the number of prototypes is developed. It is composed of new contour normalization, control point extraction and discriminant analysis algorithms also presented here. The system thus applies to shapes regardless of their position, size and orientation. A related shape inspection scheme for detecting locations of shape flaws based on similar principles is also demonstrated.     

Learning visual models from shape contours using multiscaleconvex/concave structure matching

A novel approach is proposed for learning a visual model from real shape samples of the same class. The approach can directly acquire a visual model by generalizing the multiscale convex/concave structure of a class of shapes, that is, the approach is based on the concept that shape generalization is shape simplification wherein perceptually relevant features are retained. The simplification does not mean the approximation of shapes but rather the extraction of the optimum scale convex/concave structure common to shape samples of the class. The common structure is obtained by applying the multiscale convex/concave structure-matching method to all shape pairs among given shape samples of the class and by integrating the matching results. The matching method, is applicable to heavily deformed shapes and is effectively implemented with dynamic programming techniques. The approach can acquire a visual model from a few samples without any a priori knowledge of the class. The obtained model is very useful for shape recognition. Results of applying the proposed method are presented     

A shape prior constraint for implicit active contours

We present a shape prior constraint to guide the evolution of implicit active contours. Our method includes three core techniques. Firstly, a rigid registration is introduced, using a line search method within a level set framework. The method automatically finds the time step for the iterative optimization processes. The order for finding the optimal translation, rotation and scale is derived experimentally. Secondly, a single reconstructed shape is created from a shape distribution of a previously acquired learning set. The reconstructed shape is applied to guide the active contour evolution. Thirdly, our method balances the impact of the shape prior versus the image guidance of the active contour. A mixed stopping condition is defined based on the stationarity of the evolving curve and the shape prior constraint. Our method is completely non-parametric and avoids taking linear combinations of non-linear signed distance functions, which would cause problems because distance functions are not closed under linear operations. Experimental results show that our method is able to extract the desired objects in several circumstances, namely when noise is present in the image, when the objects are in slightly different poses and when parts of the object are invisible in the image.     

Independent shape component-based human activity recognition via Hidden Markov Model

In proactive computing, human activity recognition from image sequences is an active research area. In this paper, a novel human activity recognition method is proposed, which utilizes Independent Component Analysis (ICA) for activity shape information extraction from image sequences and Hidden Markov Model (HMM) for recognition. Various human activities are represented by shape feature vectors from the sequence of activity shape images via ICA. Based on these features, each HMM is trained and activity recognition is achieved by the trained HMMs of different activities. Our recognition performance has been compared to the conventional method where Principal Component Analysis (PCA) is typically used to derive activity shape features. Our results show that superior recognition is achieved with the proposed method especially for activities (e.g., skipping) that cannot be easily recognized by the conventional method. Furthermore, by employing Linear Discriminant Analysis (LDA) on IC features, the recognition results further improved significantly in the recognition performance.     

Discrete contours in multiple views: approximation and recognition

Recognition of discrete planar contours under similarity transformations has received a lot of attention but little work has been reported on recognizing them under more general transformations. Planar object boundaries undergo projective or affine transformations across multiple views. We present two methods to recognize discrete curves in this paper. The first method computes a piecewise parametric approximation of the discrete curve that is projectively invariant. A polygon approximation scheme and a piecewise conic approximation scheme are presented here. The second method computes an invariant sequence directly from the sequence of discrete points on the curve in a Fourier transform space. The sequence is shown to be identical up to a scale factor in all affine related views of the curve. We present the theory and demonstrate its applications to several problems including numeral recognition, aircraft recognition, and homography computation.     

A novel application of self-organizing network for facial expression recognition from radial encoded contours

We propose an efficient algorithm for recognizing facial expressions using biologically plausible features: contours of face and its components with radial encoding strategy. A self-organizing network (SON) is applied to check the homogeneity of the encoded contours and then different classifiers, such as SON, multi-layer perceptron and K-nearest neighbor, are used for recognizing expressions from contours. Experimental results show that the recognition accuracy of our algorithm is comparable to that of other algorithms in the literature on the Japanese female facial expression database. We also apply our algorithm to Taiwanese facial expression image database to demonstrate its efficiency in recognizing facial expressions.     

Object recognition by spectral feature derived from canonical shape representation

In this paper, we introduce a new spectral shape feature that can be used in content-based object recognition. We explain a new canonical string representation for a polygonal shape approximation from which the proposed spectral feature is derived. This spectral feature is a composition of Fourier coefficients of the shape function that is derived from the canonical representation. We applied the proposed feature in classification of lung nodules by means of our hierarchical learning scheme proposed in another study. The results show that the spectral feature is promising for lung nodule recognition.     

Attractor networks for shape recognition

We describe a system of thousands of binary perceptrons with coarse-oriented edges as input that is able to recognize shapes, even in a context with hundreds of classes. The perceptrons have randomized feedforward connections from the input layer and form a recurrent network among themselves. Each class is represented by a prelearned attractor (serving as an associative hook) in the recurrent net corresponding to a randomly selected subpopulation of the perceptrons. In training, first the attractor of the correct class is activated among the perceptrons; then the visual stimulus is presented at the input layer. The feedforward connections are modified using field-dependent Hebbian learning with positive synapses, which we show to be stable with respect to large variations in feature statistics and coding levels and allows the use of the same threshold on all perceptrons. Recognition is based on only the visual stimuli. These activate the recurrent network, which is then driven by the dynamics to a sustained attractor state, concentrated in the correct class subset and providing a form of working memory. We believe this architecture is more transparent than standard feedforward two-layer networks and has stronger biological analogies.     

Biomimetic whiskers for shape recognition

Rodents demonstrate an outstanding capability of tactile perception with their whiskers. Mechanoreceptors surrounding the whisker shaft in their follicle structure measure deflection of the whisker. We designed biomimetic whiskers following the basic design of the follicle. In experiments with the artificial whiskers, we have explored tactile perception based on active whisking where the deflection angle or velocity provides the localization information which is the basis of shape recognition. Measuring contact distances at varying protraction angles allows discrimination of round objects with a varying curvature, or objects with different lateral shapes, such as square and round objects. We show the capabilities and limitations of a single whisker for shape recognition as well as the usefulness of multiple whiskers. In addition, measuring both vertical and horizontal deflection of a single whisker allows detection of the vertical shape for objects with a smooth surface. Two or more whiskers stacked vertically can recognize the vertical shape by observing the difference of their deflection amplitudes or the time shift of deflection velocity peak. The results provide a clue on how autonomous robots could improve their sensory capabilities with mechanical probes.     

Bounds on shape recognition performance

The localization and the recognition tasks are analyzed here relying on a probabilistic model, and independently of the recognition method used. Rigorous upper and lower bounds on the probability that a set of measurements is sufficient to localize an object within a certain precision, are derived. The bounds quantify the difficulty of the localization task regarding many of its aspects, including the number of measurements, the uncertainty in their position, the information they reveal, and the “ability of the objects to confuse the recognizer”. Similar results are obtained for the recognition task. The asymptotic difficulty of recognition/localization tasks is characterized by a single parameter, thus making it possible to compare between different tasks. The bounds provide a theoretical benchmark to which experimentally measured performance of localization/recognition methods can be compared     

Hand shape recognition based on coherent distance shape contexts

In this paper, we propose a novel hand shape recognition method named as Coherent Distance Shape Contexts (CDSC), which is based on two classical shape representations, i.e., Shape Contexts (SC) and Inner-distance Shape Contexts (IDSC). CDSC has good ability to capture discriminative features from hand shape and can well deal with the inexact correspondence problem of hand landmark points. Particularly, it can extract features mainly from the contour of fingers. Thus, it is very robust to different hand poses or elastic deformations of finger valleys. In order to verify the effectiveness of CDSC, we create a new hand image database containing 4000 grayscale left hand images of 200 subjects, on which CDSC has achieved the accurate identification rate of 99.60% for identification and the Equal Error Rate of 0.9% for verification, which are comparable with the state-of-the-art hand shape recognition methods.