Contour Points Research Articles

Circle Views Signature: A Novel Shape Representation for Shape Recognition and Retrieval

An important problem in computer vision is object recognition, which has received considerable attention in the literature. The performance of any object recognition system depends on the shape representation used and on the matching algorithm applied. In this paper, we propose a novel circle views (CVs) shape signature for recognizing 2-D object silhouettes. Many views from one circular orbit (or more) centered at the shape centroid are defined based on the distances from each viewing point on the circular orbit to a fixed number of sampled shape contour points. One compact and robust shape descriptor is obtained by applying the Fourier transform to the proposed signature. The obtained descriptor is translation, rotation, and scale invariant. Two popular shape benchmarks have been used for testing: 1) MPEG-7 and 2) Kimia’s-99 databases. The proposed CVs signature provides a promising retrieval rate (83.71% on MPEG-7 database). A further increase in the retrieval rate (90.35%) has been achieved by applying a shape context learning technique. A slight modification to the learning technique has been proposed that reduces its computational cost significantly. An attractive feature of the proposed CVs signature is its simplicity and computational efficiency, which makes the CVs signature more practical for different application areas.

Shape Retrieval Using ECPDH with Dynamic Programming

The matching and retrieval of the 2D shapes are challenging issues in object recognition and computer vision. In this paper, we propose a new object contour descriptor termed ECPDH (Elliptic Contour Points Distribution Histogram), which is based on the distribution of the points on an object contour under the polar coordinates. ECPDH has the essential merits of invariance to scale and translation. Dynamic Programming (DP) algorithm is used to measure the distance between the ECPDHs. The effectiveness of the proposed method is demonstrated using some standard tests on MPEG-7 shape database. The results show the precision and recall of our method over other recent methods in the literature.

Parameter-sparse modification of Fourier methods to analyse the shape of closed contours with application to otolith outlines

Elliptical Fourier descriptors (EFDs) have been used extensively in shape analysis of closed contours and have a range of marine applications, such as automatic identification of fish species and discrimination between fish stocks based on EFDs of otolith contours. A recent method (the ‘MIRR’ method) transforms the two-dimensional contour to a one-dimensional function by mirroring (reflecting) the lower half of the contour around a vertical axis at the right end of the contour. MIRR then applies the fast Fourier transform (FFT) to the vertical contour points corresponding to equidistant coordinate values along the horizontal axis. MIRR has the advantage of reducing the number of Fourier coefficients to two coefficients per frequency component compared with four EFDs. However, both Fourier methods require several frequency components to reproduce a pure ellipse properly. This paper shows how the methods can be easily modified so that a virtually perfect reproduction of a pure ellipse is obtained with only one frequency component. In addition, real otolith examples for cod (Gadus morhua) and Greenland halibut (Reinhardtius hippoglossoides) are used to demonstrate that the modified methods give better approximations to the large-scale shape of the original contour with fewer coefficients than the traditional Fourier methods, with negligible additional computing time.

Image Processing Assisted Tools for Pre- and Post-processing Operations in Additive Manufacturing

Additive Manufacturing (AM) or 3D printing (3DP) process is a layer by layer manufacturing approach for manufacturing parts with complex geometries. The STL (Stereolithography) file format is the de-facto industry standard for manufacturing parts by AM/3DP. The STL file is a triangular mesh representation of CAD geometry in non-uniform rational B-spline (NURBS) surface format and thus is an approximation of actual part geometry. During the conversion of a complex CAD geometry to an STL file, geometric errors are introduced in the model. These drawbacks associated with the STL file may translate into a faulty or inaccurate final manufactured part. This paper presents a novel Image Processing (IP) based Direct CAD Slicer, IPSlicer, which can be used to manufacture components directly from CAD geometry (without converting to STL file). Using sectional image snapshots of a part, captured normal to the build direction and sectional 2D bounding box data, contour points for each section are identified by performing boundary tracing operation followed by application of Contour Mapping Algorithm (CMA). The method slices the actual NURBS geometry and thus parts manufactured by this method have reduced GD&T errors such as flatness, cylindricity, and profile error. In addition, a support removability analysis tool is developed by performing color-based segmentation on sectional image snapshots in conjunction with a pixel traversal approach. Using the segmented images and sectional bounding box, a sintering area and time calculation tool for each layer is also developed. The effectiveness of IPSlicer is verified by virtually manufacturing test components and calculating GD&T errors by the application of computational metrology algorithms on virtually manufactured data. The support removability analysis tool as well as sintering time and area calculator are validated using several test parts.

Stokes–Leibenson problem for Hele-Shaw flow: a critical set in the space of contours

The Stokes–Leibenson problem for Hele-Shaw flow is reformulated as a Cauchy problem of a nonlinear integro-differential equation with respect to functions a and b, linked by the Hilbert transform. The function a expresses the evolution of the coefficient longitudinal strain of the free boundary and b is the evolution of the tangent tilt of this contour. These functions directly reflect changes of geometric characteristics of the free boundary of higher order than the evolution of the contour point obtained by the classical Galin–Kochina equation. That is why we managed to uncover the reason of the absence of solutions in the sink-case if the initial contour is not analytic at at least one point, to prove existence and uniqueness theorems, and also to reveal a certain critical set in the space of contours. This set contains one attractive point in the source-case corresponding to a circular contour centered at the source-point. The main object of this work is the analysis of the discrete model of the problem. This model, called quasi-contour, is formulated in terms of functions corresponding to a and b of our integro-differential equation. This quasi-contour model provides numerical experiments which confirm the theoretical properties mentioned above, especially the existence of a critical subset of co-dimension 1 in space of quasi-contours. This subset contains one attractive point in the source-case corresponding to a regular quasi-contour centered at the source-point. The main contribution of our quasi-contour model concerns the sink-case: numerical experiments show that the above subset is attractive. Furthermore, this discrete model allows to extend previous results obtained by using complex analysis. We also provide numerical experiments linked to fingering effects.

Skeleton based Non rigid Shape Matching

This paper offers a new feature for matching deformable objects based on skeleton. Effectiveness of the skeleton-based methods depends to a large extent on the quality and perfection of the extracted skeleton. When the skeleton is extracted, additional branches of which, with the shape contour segmentation, are omitted by DCE method. The pruned skeleton is robust to the complex deformations and noise. After the pruned skeleton is obtained, minimum distance of contour points of the shape from the skeleton is calculated. This distance almost is constant against the articulated changes which this feature is used for finding the corresponding points. In order to carry out matching, the suggested method is applied on the MPEG7 dataset. Results show that the proposed algorithm is highly effective for matching objects.

A new thresholding approach for automatic generation of polygonal approximations

The present paper proposes a new algorithm for automatic generation of polygonal approximations of 2D closed contours based on a new thresholding method. The new proposal computes the significance level of the contour points using a new symmetric version of the well-known Ramer, Douglas–Peucker method, and then a new Adaptive method is applied to threshold the normalized significance level of the contour points to generate the polygonal approximation. The experiments have shown that the new algorithm has good performance for generating polygonal approximations of 2D closed contours. Furthermore, the new algorithm does not require any parameter to be tuned.

Stability of polarization singularities in disordered photonic crystal waveguides

The effects of short range disorder on the polarisation characteristics of light in photonic crystal waveguides were investigated using finite difference time domain simulations with a view to investigating the stability of polarisation singularities. It was found that points of local circular polarisation (C-points) and contours of linear polarisation (L-lines) continued to appear even in the presence of high levels of disorder, and that they remained close to their positions in the ordered crystal. These results are a promising indication that devices exploiting polarisation in these structures are viable given current fabrication standards.

An Implicit Contour Morphing Framework Applied to Computer-Aided Severe Weather Forecasting

We propose a contour morphing framework that allows large deformations and topological changes while guaranteeing non self-intersecting contours. Instead of explicitly matching contour points, the proposed algorithm combines an implicit contour representation with state-of-the-art deformable image registration. Synthetic and real-life examples from a meteorological application are presented to demonstrate the efficacy of the framework.

Shape matching and object recognition using common base triangle area

Shape matching has always been a key issue in the field of computer vision. To obtain high recognition accuracy with low time complexity and to reduce the influence of contour deformation due to noise in shape matching, a novel shape matching method based on common base triangle area (CBTA) is proposed. First, a CBTA descriptor of each contour point is defined based on the area functions of the triangles formed by its two neighbour points and other contour points. Then, the descriptor is locally smoothed to keep it more compact and robust to noise. Secondly, a match cost matrix is obtained by computing the CBTA descriptors of all the contour points on two shapes. Finally, the similarity between the two shapes is measured on the basis of the match cost matrix by a dynamic programming algorithm. The experimental results on MPEG‐7, Kimia and an articulation shape database indicate that this method is robust to contour deformation, and both the computational efficiency and the retrieval rate are essentially improved.

Study on Initial Gravity Map Matching Technique Based on Triangle Constraint Model

In this paper, a gravity map-matching algorithm is proposed based on a triangle constraint model. A high-accuracy triangle constraint model is constructed by using a short time and high-accuracy-featured inertial navigation system. In this paper, the principle of the gravity map-matching algorithm based on the triangle constraint model and a triangle matching parameter-parsing method are first introduced in detail. It is verified by test that the method is sensitive to the initial error value. By comparison to the commonly used Iterative Closest Contour Point (ICCP) and Sandia Inertial Terrain Aided Navigation (SITAN) algorithms respectively, the results show that this method is perfect in real-time performance and reliability, and its advantages are more obvious especially with a large initial error.

Minimization of contact pressure for hub–shaft friction pair

Based on the minimax criterion, the theoretical definition of displacement function for hub external contour points, providing the minimization of contact pressure in the hub—shaft friction pair, has been executed. A closed system of algebraic equations has been constructed. The obtained system allows minimizing the contact pressure distribution in friction pair depending on the geometrical and mechanical characteristics of its elements.

Automatic muscle and fat segmentation in the thigh from T1-Weighted MRI.

To introduce and validate an automatic segmentation method for the discrimination of skeletal muscle (SM), and adipose tissue (AT) components (subcutaneous adipose tissue [SAT] and intermuscular adipose tissue [IMAT]) from T1-weighted (T1 -W) magnetic resonance imaging (MRI) images of the thigh. Eighteen subjects underwent an MRI examination on a 1.5T Philips Achieva scanner. Acquisition was performed using a T1 -W sequence (TR = 550 msec, TE = 15 msec), pixel size between 0.81-1.28 mm, slice thickness of 6 mm. Bone, AT, and SM were discriminated using a fuzzy c-mean algorithm and morphologic operators. The muscle fascia that separates SAT from IMAT was detected by integrating a morphological-based segmentation with an active contour Snake. The method was validated on five young normal weight, five older normal weight, and five older obese females, comparing automatic with manual segmentations. We reported good performance in the extraction of SM, AT, and bone in each subject typology (mean sensitivity above 96%, mean relative area difference of 1.8%, 2.7%, and 2.5%, respectively). A mean distance between contours pairs of 0.81 mm and a mean percentage of contour points with distance smaller than 2 pixels of 86.2% were obtained in the muscle fascia identification. Significant correlation was also found between manual and automatic IMAT and SAT cross-sectional areas in all subject typologies (p < 0.001). The proposed automatic segmentation approach provides adequate thigh tissue segmentation and may be helpful in studies of regional composition.

Segmentation of Color Overlapping Cells Image Based on Sparse Contour Point Model

Segmentation of Color Overlapping Cells Image Based on Sparse Contour Point Model

Object detection based on scale-invariant partial shape matching

This paper aims at detecting objects via a partial shape matching in unlabeled real images. As both the scale and consistent fragment extraction are troublesome issues in computer vision, we first extract the corresponding parts of pairs of matching fragments generated by the curvature extreme points in object contours. Then, we establish the scale-calculable shape descriptor to keep that the partial shape matching algorithm is scale and rotation invariant. In detection stage, a weighted voting scheme is used to locate candidate object centers and followed by a refinement process to obtain the precise object boundaries. Experiments on ETHZ shape category database validate that using single model shape without training for each category can match (or exceed) the performance of state-of-the-art object detection algorithms.

Recognition of Off-Line Handwritten Devanagari Characters using Combinational Feature Extraction

Handwritten Devanagari off-line characters recognition is a challenging task due to peculiarities involved in the writing styles of different person. We are collected features from 64 dimensional feature extraction techniques and shadow features for the Devanagari character recognition in this proposed scheme. These calculated features are used for further classification. Features which are used here for recognition means histograms of direction chain code of the contour points of the characters [4]. The features are classified using neural network and selected the best result by weighted majority voting technique.

TH‐AB‐BRA‐06: Independent Automatic Catheter Digitization Algorithm for High Dose Rate (HDR) Brachytherapy Quality Improvement (QI) and Quality Assurance (QA)

Purpose:Individual‐user and inter‐user variability during manual catheter digitization for interstitial HDR brachytherapy can be significant since the process can time consuming and error prone. We present an algorithm and workflow for catheter digitization that can be used for independent verification of manual digitization (QA) or automatic digitization (QI).Methods:After DICOM CT images are imported into the TPS, this proximal end of each catheter is located and numbered on a single slice near the needle template. The DICOM RP and CT files are then exported for digitization. Each transverse CT slice is smoothed with a Gaussian filter, then a convolution kernel finds the Laplacian of the CT image. This process highlights regions of rapid density change. A sliding window filter is applied to the image afterwards to locate each catheter center. The catheter is traced and geometry digitized from the needle template to the tip slice by slice, similar to the manual procedure. All the contour points are written into the original DICOM RP file and imported back into the TPS for planning. The difference between the manual digitization and the automatic digitization was quantified with a RMS calculation of the deviation between the manual and automatic catheter geometries for 11 clinical cases.Results:The RMS difference between the automatic and manual digitization was 0.50±0.04mm. Execution time for automatic digitization is ∼3 minutes (analysis ∼2 min; DICOM export/import ∼1 minute).Conclusion:This automatic catheter digitization method can be used as both a QA and QI tool. As a QI it is executed instead of manual catheter digitization. The algorithmic nature ensures reduced individual‐ and intra‐user variability and reduces digitization time. As a QA tool, the algorithm can be used to validate the manually generated catheter pattern to ensure digitization integrity.

SU‐E‐J‐131: Augmenting Atlas‐Based Segmentation by Incorporating Image Features Proximal to the Atlas Contours

Purpose:For facilitating the current automatic segmentation, in this work we propose a narrow‐shell strategy to enhance the information of each contour in the library and to improve the accuracy of the exiting atlas‐based approach.Methods:In setting up an atlas‐based library, we include not only the coordinates of contour points, but also the image features adjacent to the contour. 139 planning CT scans with normal appearing livers obtained during their radiotherapy treatment planning were used to construct the library. The CT images within the library were registered each other using affine registration. A nonlinear narrow shell with the regional thickness determined by the distance between two vertices alongside the contour. The narrow shell was automatically constructed both inside and outside of the liver contours. The common image features within narrow shell between a new case and a library case were first selected by a Speed‐up Robust Features (SURF) strategy. A deformable registration was then performed using a thin plate splines (TPS) technique. The contour associated with the library case was propagated automatically onto the images of the new patient by exploiting the deformation field vectors. The liver contour was finally obtained by employing level set based energy function within the narrow shell. The performance of the proposed method was evaluated by comparing quantitatively the auto‐segmentation results with that delineated by a physician.Results:Application of the technique to 30 liver cases suggested that the technique was capable of reliably segment organs such as the liver with little human intervention. Compared with the manual segmentation results by a physician, the average and discrepancies of the volumetric overlap percentage (VOP) was found to be 92.43%+2.14%.Conclusion:Incorporation of image features into the library contours improves the currently available atlas‐based auto‐contouring techniques and provides a clinically practical solution for auto‐segmentation.This work is supported by NIH/NIBIB (1R01‐EB016777), National Natural Science Foundation of China (No.61471226 and No.61201441), Research funding from Shandong Province (No.BS2012DX038 and No.J12LN23), and Research funding from Jinan City (No.201401221 and No.20120109).

SU-E-J-108: Solving the Chinese Postman Problem for Effective Contour Deformation

Purpose: To develop a practical approach for accurate contour deformation when deformable image registration (DIR) is used for atlas-based segmentation or contour propagation in image-guided radiotherapy. Methods: A contour deformation approach was developed on the basis of 3D mesh operations. The 2D contours represented by a series of points in each slice were first converted to a 3D triangular mesh, which was deformed by the deformation vectors resulting from DIR. A set of parallel 2D planes then cut through the deformed 3D mesh, generating unordered points and line segments, which should be reorganized into a set of 2D contour points. It was realized that the reorganization problem was equivalent to solving the Chinese Postman Problem (CPP) by traversing a graph built from the unordered points with the least cost. Alternatively, deformation could be applied to a binary mask converted from the original contours. The deformed binary mask was then converted back into contours at the CT slice locations. We performed a qualitative comparison to validate the mesh-based approach against the image-based approach. Results: The DIR could considerably change the 3D mesh, making complicated 2D contour representations after deformation. CPP was able to effectively reorganize the points in 2D planes no matter how complicated the 2D contours were. The mesh-based approach did not require a post-processing of the contour, thus accurately showing the actual deformation in DIR. The mesh-based approach could keep some fine details and resulted in smoother contours than the image-based approach did, especially for the lung structure. Image-based approach appeared to over-process contours and suffered from image resolution limits. The mesh-based approach was integrated into in-house DIR software for use in routine clinic and research. Conclusion: We developed a practical approach for accurate contour deformation. The efficiency of this approach was demonstrated in both clinic and research applications. This work was partially supported by Cancer Prevention & Research Institute of Texas (CPRIT) RP110562.

An efficient mesh-based face beautifier on mobile devices

The pursuit of beautiful appearance for human greatly inspires the studies on digital beautifiers especially for the popularity of social networking services (SNS) in this booming era of mobile phones. Unfortunately, existing beautification techniques are not efficient enough for mobile devices that have limited computation and storage resources. In this paper, we propose a beautifier that is efficient on both space and time, and develop a mobile APP available online. We focus on the local beautification of facial chin that has a great effect on facial attractiveness, and simply use an averaged chin shape as the template. We leverage Laplacian as the constraint to remap the original shape to the target, and recursively apply the Laplacian constraint to the contour points from the coarse to fine scales. Thus, we only need to inverse a small matrix for the remap, which requires quite low expenses on space and time. Finally, we apply an efficient warping algorithm based on triangular meshes to generate a beautified face image. The performance of the algorithm is validated by a survey on 70 facial images since no objective metric for beauty exists. Twenty volunteers are invited to grade the results labeled as ‘worse’, ‘unchanged’ and ‘better’. The results show that 81.50% of inputs are believed becoming more beautiful, and another 10.07% of them are considered unchanged. We also provide the comparisons on the beautification quality and time expenses with the algorithm based on radial basis functions (RBF).