Active Shape Model Research Articles

Automatic optical phase identification of micro-drill bits based on improved ASM and bag of shape segment in PCB production

This paper addresses the problem of automatic optical phase identification of micro-drill bits for micro-drilling tool inspection in printed circuit board production. To overcome the limitations of conventional active shape model (ASM) on shape modeling of micro-drill bits, six key landmarks are defined for the initialization and optimization of ASM, and a novel method based on projection profiles is also proposed for these key landmarks detection. In addition, to involve the local shape feature, a bag of shape segment (BoSS) model is developed. Based on the improved ASM and BoSS, a new shape representation of micro-drill bits is proposed for phase identification. Experimental results show that the proposed method outperforms the conventional ASM and can improve the phase identification accuracy of micro-drill bits.

Cardiac image processing techniques

Heart disease is the leading cause of death in the modern world. Cardiac image processing is now routinely applied for detecting, classification and diagnosis of heart diseases. One of the most common uses of processing methods that are now widely applied are cardiac segmentation [1] and registration methods [2], that are used in order to extract the detailed anatomy and function of the heart. Automatic segmentation plays a central role when inspecting reconstructed 3D cardiac images from CT or MR scanners. An accurate classification of the different cardiac regions is usually the first step of tasks like: cardiac visualization, coronary artery inspection, measurement of the ejection fraction for the left and right ventricles and wall motion analysis. In a clinical context, physicians often mentally integrate image information from different modalities. Automatic registration, based on computer programs, might, however, offer better accuracy and repeatability and save time [3]. Cardiac image registration remains a challenge because of the numerous specific problems mainly related to the different motion sources (patient, respiration, heart) and to the specificity of each imaging modality. Up to now, no general method could automatically register any modality with any other modality so far. This paper presents a survey of shape modeling applications to cardiac image analysis from MRI, CT, echocardiography, PET, and SPECT and aims to introduce new methodologies in this field, classify major contributions in image-based cardiac modeling, provide a tutorial to beginners to initiate their own studies, and introduce the major challenges of registration and segmentation and provide practical examples. Image-driven processing methods, such as thresholding, region-based or edge-based techniques, or else pixel classification [4-6], provide a limited framework for further medical image analysis. They can include geometrical information, as well as high level information, in the so-called shape prior based segmentation framework, or through active shape models and active appearance models. At last, atlas guided segmentation also make use of a set of manually segmented images. By using different analysis software of cardiac images, CAD prototypes can be used in clinical routines in order to provide a computer output as a second reader to assist physicians in the detection of abnormalities, quantification of disease progression and differential diagnosis of lesions [7]. Computerized analysis of cardiac images in combination with artificial intelligence can be used in clinical practice and may contribute to more efficient diagnosis.

TH‐A‐9A‐01: Active Optical Flow Model: Predicting Voxel‐Level Dose Prediction in Spine SBRT

Purpose:To predict voxel‐level dose distribution and enable effective evaluation of cord dose sparing in spine SBRT.Methods:We present an active optical flow model (AOFM) to statistically describe cord dose variations and train a predictive model to represent correlations between AOFM and PTV contours. Thirty clinically accepted spine SBRT plans are evenly divided into training and testing datasets. The development of predictive model consists of 1) collecting a sequence of dose maps including PTV and OAR (spinal cord) as well as a set of associated PTV contours adjacent to OAR from the training dataset, 2) classifying data into five groups based on PTV's locations relative to OAR, two “Top”s, “Left”, “Right”, and “Bottom”, 3) randomly selecting a dose map as the reference in each group and applying rigid registration and optical flow deformation to match all other maps to the reference, 4) building AOFM by importing optical flow vectors and dose values into the principal component analysis (PCA), 5) applying another PCA to features of PTV and OAR contours to generate an active shape model (ASM), and 6) computing a linear regression model of correlations between AOFM and ASM.When predicting dose distribution of a new case in the testing dataset, the PTV is first assigned to a group based on its contour characteristics. Contour features are then transformed into ASM's principal coordinates of the selected group. Finally, voxel‐level dose distribution is determined by mapping from the ASM space to the AOFM space using the predictive model.Results:The DVHs predicted by the AOFM‐based model and those in clinical plans are comparable in training and testing datasets. At 2% volume the dose difference between predicted and clinical plans is 4.2±4.4% and 3.3±3.5% in the training and testing datasets, respectively.Conclusion:The AOFM is effective in predicting voxel‐level dose distribution for spine SBRT.Partially supported by NIH/NCI under grant #R21CA161389 and a master research grant by Varian Medical System.

SU‐F‐BRF‐02: Automated Lung Segmentation Method Using Atlas‐Based Sparse Shape Composition with a Shape Constrained Deformable Model

Purpose:To develop an automated lung segmentation method, which combines the atlas‐based sparse shape composition with a shape constrained deformable model in thoracic CT for patients with compromised lung volumes.Methods:Ten thoracic computed tomography scans for patients with large lung tumors were collected and reference lung ROIs in each scan was manually segmented to assess the performance of the method. We propose an automated and robust framework for lung tissue segmentation by using single statistical atlas registration to initialize a robust deformable model in order to perform fine segmentation that includes compromised lung tissue. First, a statistical image atlas with sparse shape composition is constructed and employed to obtain an approximate estimation of lung volume. Next, a robust deformable model with shape prior is initialized from this estimation. Energy terms from ROI edge potential and interior ROI region based potential as well as the initial ROI are combined in this model for accurate and robust segmentation.Results:The proposed segmentation method is applied to segment right lung on three CT scans. The quantitative results of our segmentation method achieved mean dice score of (0.92–0.95), mean accuracy of (0.97,0.98), and mean relative error of (0.10,0.16) with 95% CI. The quantitative results of previously published RASM segmentation method achieved mean dice score of (0.74,0.96), mean accuracy of (0.66,0.98), and mean relative error of (0.04, 0.38) with 95% CI. The qualitative and quantitative comparisons show that our proposed method can achieve better segmentation accuracy with less variance compared with a robust active shape model method.Conclusion:The atlas‐based segmentation approach achieved relatively high accuracy with less variance compared to RASM in the sample dataset and the proposed method will be useful in image analysis applications for lung nodule or lung cancer diagnosis and radiotherapy assessment in thoracic computed tomography.

Fully Automated Ultrasound Common Carotid Artery Segmentation Using Active Shape Model

B-mode measurement of the contour of the common carotid artery (CCA) has an important clinical value. The purpose of this study was to develop a fully automated ultrasound common carotid artery segmentation method using active shape model (ASM). An image database with 90 images was used to train the ASM model during the offline training phase of ASM. When it came to the online segmentation phase, a knowledge-based seed point detection method was first used to locate the centroid of the CCA. Then the trained ASM model automatically produced an exact contour of the CCA. The proposed method yielded a Dice Metric of 90.5% ± 4.35% and a Hausdorff Distance of 9.28 ± 5.2 pixels in a database of 40 ultrasound images. The segmentation result of upper and bottom part of the CCA was better than that of lateral part of the CCA. The proposed method eliminates the need of manual initialization, and identifies the contour of the CCA with high precision. It has the potential to be a suitable replacement for manual segmentation of the CCA.

Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM

In this paper, we propose an automatic method for constructing an active shape model (ASM) to segment the complete cardiac left ventricle in 3D ultrasound (3DUS) images, which avoids costly manual landmarking. The automatic construction of the ASM has already been addressed in the literature; however, the direct application of these methods to 3DUS is hampered by a high level of noise and artefacts. Therefore, we propose to construct the ASM by fusing the multidetector computed tomography data, to learn the shape, with the artificially generated 3DUS, in order to learn the neighbourhood of the boundaries. Our artificial images were generated by two approaches: a faster one that does not take into account the geometry of the transducer, and a more comprehensive one, implemented in Field II toolbox. The segmentation accuracy of our ASM was evaluated on 20 patients with left-ventricular asynchrony, demonstrating plausibility of the approach.

ASM기반 (2D)2하이브리드 전처리 알고리즘을 이용한 얼굴인식 시스템 설계

본 연구에서는 ASM기반 <TEX>$(2D)^2$</TEX> 하이브리드 전처리 알고리즘을 이용한 얼굴인식 분류기와 그것의 설계방법론을 소개한다. 얼굴인식을 위한 이미지는 외부 환경에 쉽게 영향을 받기 때문에, 전처리 단계로 이러한 문제를 해결하기 위해서 ASM을 사용하였다. 특히 사람 얼굴의 특징 추출을 목적으로 널리 이용되고 있다. ASM을 이용해 얼굴영역을 추출 한 뒤 PCA와 LDA를 이용한 <TEX>$(2D)^2$</TEX> 하이브리드 전처리 알고리즘을 이용하여 차원을 축소한다. 전처리 알고리즘을 통한 얼굴데이터는 제안된 다항식 기반 방사형 기저함수 신경회로망의 입력으로 사용된다. 기존의 신경회로망과는 달리 제안된 지능형 패턴 분류기는 강인한 네트워크 특성을 가지며, 예측능력이 우수할 뿐만 아니라 다차원 입출력에 대한 문제도 해결했다. 분류기의 중요한 필수 설계 파라미터(행의 고유벡터의 수, 열의 고유벡터의 수, 클러스터의 수, 퍼지화 계수)는 ABC알고리즘에 의해 최적화 되어진다. 얼굴인식에 많이 사용되는 Yale과 AT&T를 사용하여 인식률을 평가하였다. In this study, we introduce ASM-based face recognition classifier and its design methodology with the aid of 2-dimensional 2-directional hybird preprocessing algorithm. Since the image of face recognition is easily affected by external environments, ASM(active shape model) as image preprocessing algorithm is used to resolve such problem. In particular, ASM is used widely for the purpose of feature extraction for human face. After extracting face image area by using ASM, the dimensionality of the extracted face image data is reduced by using <TEX>$(2D)^2$</TEX>hybrid preprocessing algorithm based on LDA and PCA. Face image data through preprocessing algorithm is used as input data for the design of the proposed polynomials based radial basis function neural network. Unlike as the case in existing neural networks, the proposed pattern classifier has the characteristics of a robust neural network and it is also superior from the view point of predictive ability as well as ability to resolve the problem of multi-dimensionality. The essential design parameters (the number of row eigenvectors, column eigenvectors, and clusters, and fuzzification coefficient) of the classifier are optimized by means of ABC(artificial bee colony) algorithm. The performance of the proposed classifier is quantified through yale and AT&T dataset widely used in the face recognition.

1.2. A novel approach to automated bloodstain pattern analysis using an active bloodstain shape model

Objectives Conventional blood pattern analysis is a tedious and time- consuming process due to the many actions that must be performed by the pattern analyst. Digital photographs can now be employed to aid in the process of scene analysis, by letting computer programs perform some of the required steps. However, current computerized methods are all based upon the assumption that any stain can be approximated by a simple ellipse, while manual work is still required. Materials and methods This work presents a novel approach, employing a regressed active shape model to approximate bloodstains. This Active Bloodstain Shape Model (ABSM) uses a regression to correlate the shape of a stain׳s approximation to its impact angle. This model is then deployed in a software pipeline, aiming to eliminate any user-input from the process. Fiducial markers are positioned in a crime scene, allowing for fully automated pattern analysis. Images are cleaned of any perspective distortions, after which stains are segmented and analyzed using said model. A robust principal component analysis (PCA) is then used to analyze the intersections of the reconstructed flight paths. Results Experimental results have demonstrated that the ABSM is able to better approximate stains, while accuracy on predicted impact angles is increased. Both simulated as well as real crimes scenes have confirmed the working of the automated pipeline. Conclusion Because the ABSM learns from experimental data, it is able to better approximate stains, resulting in an increased accuracy. The addition of the software pipeline removed the need for almost all user-input.

Book inner boundary extraction with modified active shape model

This paper proposes one modified active shape model (MASM) method to extract book inner boundaries in the scanned book images. It assumes that both pages are included in the scanned image and the book page corners are provided. The MASM method introduces the “book shape” idea and represents the book shape as one set of landmark points which are sampled from book boundary. It utilizes one iterative part-to-whole strategy to recognize the landmark points of inner boundary: at the part level, dynamic programming is used to incorporate into the specific properties of book boundary to locate the landmark points for each piece of boundary; at the whole level, one book shape model is used to constrain the shape composed by the landmarks. Finally, it extracts the inner boundary according to the located landmark points. In addition, one “expanding training shapes” strategy is proposed to learn one shape model with better generalization ability. The proposed method is evaluated on the collected datasets and shows the impressive result.

Using Active Shape Modeling Based on MRI to Study Morphologic and Pitch-Related Functional Changes Affecting Vocal Structures and the Airway

The shape of the vocal tract and associated structures (eg, tongue and velum) is complicated and varies according to development and function. This variability challenges interpretation of voice experiments. Quantifying differences between shapes and understanding how vocal structures move in relation to each other is difficult using traditional linear and angle measurements. With statistical shape models, shape can be characterized in terms of independent modes of variation. Here, we build an active shape model (ASM) to assess morphologic and pitch-related functional changes affecting vocal structures and the airway. Using a cross-sectional study design, we obtained six midsagittal magnetic resonance images from 10 healthy adults (five men and five women) at rest, while breathing out, and while listening to, and humming low and high notes. Eighty landmark points were chosen to define the shape of interest and an ASM was built using these (60) images. Principal component analysis was used to identify independent modes of variation, and statistical analysis was performed using one-way repeated-measures analysis of variance. Twenty modes of variation were identified with modes 1 and 2 accounting for half the total variance. Modes 1and 9 were significantly associated with humming low and high notes (P<0.001) and showed coordinated changes affecting the cervical spine, vocal structures, and airway. Mode 2 highlighted wide structural variations between subjects. This study highlights the potential of active shape modeling to advance understanding of factors underlying morphologic and pitch-related functional variations affecting vocal structures and the airway in health and disease.

ASM-Based Objectionable Image Detection in Social Network Services

This paper presents a method for detecting harmful images using an active shape model (ASM) in social network services (SNS). For this purpose, our method first learns the shape of a woman's breast lines through principal component analysis and alignment, as well as the distribution of the intensity values of the corresponding control points. This method then finds actual breast lines with a learned shape and the pixel distribution. In this paper, to accurately select the initial positions of the ASM, we attempt to extract its parameter values for the scale, rotation, and translation. To obtain this information, we search for the location of the nipple areas and extract the location of the candidate breast lines by radiating in all directions from each nipple position. We then locate the mean shape of the ASM by finding the scale and rotation values with the extracted breast lines. Subsequently, we repeat the matching process of the ASM until saturation is reached. Finally, we determine objectionable images by calculating the average distance between each control point in a converged shape and a candidate breast line.

적응형 결정 트리를 이용한 국소 특징 기반 표정 인식

This paper proposes the method of facial expression recognition based on decision tree structure. In the image of facial expression, ASM(Active Shape Model) and LBP(Local Binary Pattern) make the local features of a facial expressions extracted. The discriminant features gotten from local features make the two facial expressions of all combination classified. Through the sum of true related to classification, the combination of facial expression and local region are decided. The integration of branch classifications generates decision tree. The facial expression recognition based on decision tree shows better recognition performance than the method which

Implementation of 2D Active Shape Model-based Segmentation on Hippocampus

Hippocampus is an important part of brain which is related with early memory storage and spatial navigation. By observing the anatomy of hippocampus, some brain diseases effecting human memory (e.g. Alzheimer, schizophrenia, etc.) can be diagnosed and predicted earlier. The diagnosis process is highly related with hippocampus segmentation. In this paper, hippocampus segmentation using Active Shape Model, which not only works based on image intensity, but also by using prior knowledge of hippocampus shape and intensity from the training images, is proposed. The results show that ASM is applicable in segmenting hippocampus from whole brain MR image. It also shows that adding more images in the training set results in better accuracy of hippocampus segmentation.

Hierarchical multi-resolution decomposition of statistical shape models

Active shape models (ASMs) are some of the most actively used model-based segmentation approaches, whose usefulness has been successfully demonstrated in a wide variety of applications. However, they suffer from two important drawbacks: (1) the large number of training samples required to adequately model the object of interest and (2) their dependence on the initialization. Partial solutions for both of these problems have been proposed but come at the expense of a significant increase in computation time, which is of great importance in current applications. Based on the wavelet transform, the present paper proposes a new full multi-resolution framework that allows not only to hierarchically decompose any type of shape into a set of bands of information, but also to create instances of the shape with different degrees of detail. This is a multi-resolution decomposition of the shape space. Combining this new approach with a multi-resolution Gaussian pyramid of the image, the result is a new full multi-resolution hierarchical ASM that reduces both the size of the training set required and the initialization dependence while improving the classical segmentation algorithms accuracy and computational complexity. The advantages of this new algorithm have been successfully verified over two different databases.

The lumbar spine has an intrinsic shape specific to each individual that remains a characteristic throughout flexion and extension

We have previously shown that the lumbar spine has an intrinsic shape specific to the individual and characteristic of sitting, standing and supine postures. The purpose of this study was to test the hypothesis that this intrinsic shape is detectable throughout a range of postures from extension to full flexion in healthy adults. Sagittal images of the lumbar spine were taken using a positional MRI with participants (n = 30) adopting six postures: seated extension, neutral standing, standing with 30, 45 and 60° and full flexion. Active shape modelling (ASM) was used to identify and quantify 'modes' of variation in the shape of the lumbar spine. ASM showed that 89.5% of the variation in the shape of the spine could be explained by the first two modes; describing the overall curvature and the distribution of curvature of the spine. Mode scores were significantly correlated between all six postures (modes 1-9, r = 0.4-0.97, P < 0.05), showing that an element of intrinsic shape was maintained when changing postures. The spine was most even in seated extension (P < 0.001) and most uneven between 35 and 45° flexion (P < 0.05). This study shows that an individual's intrinsic lumbar spine shape is quantifiable and detectable throughout lumbar flexion and extension. These findings will enable the role of lumbar curvature in injury and low back pain to be assessed in the clinic and in the working and recreational environments.

BPN Based Likelihood Ratio Score Fusion for Audio-Visual Speaker Identification in Response to Noise

This paper deals with a new and improved approach of Back-propagation learning neural network based likelihood ratio score fusion technique for audio-visual speaker Identification in various noisy environments. Different signal preprocessing and noise removing techniques have been used to process the speech utterance and LPC, LPCC, RCC, MFCC, ΔMFCC and ΔΔMFCC methods have been applied to extract the features from the audio signal. Active Shape Model has been used to extract the appearance and shape based facial features. To enhance the performance of the proposed system, appearance and shape based facial features are concatenated and Principal Component Analysis method has been used to reduce the dimension of the facial feature vector. The audio and visual feature vectors are then fed to Hidden Markov Model separately to find out the log-likelihood of each modality. The reliability of each modality has been calculated using reliability measurement method. Finally, these integrated likelihood ratios are fed to Back-propagation learning neural network algorithm to discover the final speaker identification result. For measuring the performance of the proposed system, three different databases, that is, NOIZEUS speech database, ORL face database and VALID audio-visual multimodal database have been used for audio-only, visual-only, and audio-visual speaker identification. To identify the accuracy of the proposed system with existing techniques under various noisy environment, different types of artificial noise have been added at various rates with audio and visual signal and performance being compared with different variations of audio and visual features.

Facial Feature Localization Using Robust Active Shape Model and POEM Descriptors

Active Shape Model (ASM) has been shown to be a powerful tool for image interpretation, especially in feature points localization for face image. The original ASM model parameter estimation is based on the assumption that the profiles follow a Gaussian distribution. Its performance is always vulnerable to distortion due to pose, illumination and expression variations. In this paper, the improvement of ASM model concerns the following two aspects. Firstly, an adaptive parameter estimation method are proposed by defining a rotation factor. Secondly, local appearances of landmarks are originally represented by Patterns of Oriented Edge Magnitudes (POEM) descriptors, which can provide more robust and accurate guidance for searching than intensity profiles. The simulations are carried out using the IMM dataset, which contains 240 face images. Experimental results show that the proposed method significantly outperforms the original ASM and ASM plus LBP method under exterior variations.

Face recognition of Pose and Illumination changes using Extended ASM and Robust sparse coding

Face recognition system is an application that is used to identifying or verifying a person from a digital image, which can be done by comparing selected facial features from the image and a facial database, but robust commercial applications are still lacking. Face images used present variations in pose, illumination, image quality, and resolution. The benefits of using image quality and reliability is to improve the accuracy. Face recognition (principal component analysis (PCA) to assess the feasibility of real world face recognition, but the system performance are low when the image in uncontrolled poses. Active shape models (ASMs) are statistical model, which iteratively deform to fit to a new image. The shapes are constrained by the PDM (Point Distribution Model) which is statistical shape model, to vary only in training set of labelled examples. Then weighted matching will be applied between the input image and database images. This method provide the better recognition performance when compare to the Existing methods. Here we detect the face by the Active shape model Algorithm. It is reliable to uncontrolled pose images.

Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach.

Model-based segmentation methods have the advantage of incorporating a priori shape information into the segmentation process but suffer from the drawback that the model must be initialized sufficiently close to the target. We propose a novel approach for initializing an active shape model (ASM) and apply it to 3D lung segmentation in CT scans. Our method constructs an atlas consisting of a set of representative lung features and an average lung shape. The ASM pose parameters are found by transforming the average lung shape based on an affine transform computed from matching features between the new image and representative lung features. Our evaluation on a diverse set of 190 images showed an average dice coefficient of 0.746 ± 0.068 for initialization and 0.974 ± 0.017 for subsequent segmentation, based on an independent reference standard. The mean absolute surface distance error was 0.948 ± 1.537 mm. The initialization as well as segmentation results showed a statistically significant improvement compared to four other approaches. The proposed initialization method can be generalized to other applications employing ASM-based segmentation.

Feature Fusion Based Audio-Visual Speaker Identification Using Hidden Markov Model under Different Lighting Variations

The aim of the paper is to propose a feature fusion based Audio-Visual Speaker Identification (AVSI) system with varied conditions of illumination environments. Among the different fusion strategies, feature level fusion has been used for the proposed AVSI system where Hidden Markov Model (HMM) is used for learning and classification. Since the feature set contains richer information about the raw biometric data than any other levels, integration at feature level is expected to provide better authentication results. In this paper, both Mel Frequency Cepstral Coefficients (MFCCs) and Linear Prediction Cepstral Coefficients (LPCCs) are combined to get the audio feature vectors and Active Shape Model (ASM) based appearance and shape facial features are concatenated to take the visual feature vectors. These combined audio and visual features are used for the feature-fusion. To reduce the dimension of the audio and visual feature vectors, Principal Component Analysis (PCA) method is used. The VALID audio-visual database is used to measure the performance of the proposed system where four different illumination levels of lighting conditions are considered. Experimental results focus on the significance of the proposed audio-visual speaker identification system with various combinations of audio and visual features.