一种基于视图和支持向量机的三维物体识别方法

为提高三维物体识别系统性能并减少计算复杂性,本文提出了一种基于视图的方法.首先从三维物体的二维视图中提取颜色矩、纹理特征和仿射不变矩.颜色矩对于物体的大小和姿态不敏感且性能稳健.纹理特征可区别形状相似但外观不同的物体.仿射不变矩在物体发生仿射形变下具有不变性.本文将上述各种特征组合为23个分量的特征向量,送入支持向量机进行训练并识别.基于两种公开的三维物体数据库COIL-100和ALOI测试了本文方法性能.当每物体训练视角为36个(视角间隔10°)时,在两个数据库上的实验都达到了100%的识别率.进一步减少训练视角数量也达到较满意的识别性能,优于文献中的方法.     

Shift-, scale-, rotation- and pose-invariant object recognition using centroid wedge sampling and a feature space trajectory classifier

Abstract

We propose a new shift-, scale-, rotation- and pose-invariant method for three-dimensional object recognition. The method is based on angular scanning about the centroid of two-dimensional images of the objects yielding features invariant under changes in position, orientation and scale and a modified feature space trajectory classifier for pose invariance. Experimental results are shown and optical implementation is discussed.     

基于不变特征的标志识别技术研究

标志识别是近距离空间交会对接中的一项重要的关键技术.在空间交会对接过程中,太阳和月球等各种天体以及飞行器上零部件的辐射与反射都会影响CCD的成像,形成大量杂散光干扰.为此,本文首先设计了具有不变特征的标志系统,然后根据标志系统固有的不变特征,详细设计了左右像点匹配、远场像平面不变特征识别、近场像平面预测识别以及像空间模型匹配全等识别等一套完整算法,可以保证彻底消除杂散光的干扰,正确可靠地完成各个标志灯像点的辨识.模拟图像仿真实验和真实图像仿真实验结果验证了算法的正确性和可靠性.     

Recognition of motion-blurred images by use of the method of moments

Image motion causes a blur that changes features of objects and therefore complicates the task of automatic recognition. In this work we develop two recognition methods for motion-blurred images. For the first method we assume that the motion function and direction during the exposure are given. We develop the relation between the blurred-image moments and the original-image moments based on the motion function only. The recognition is carried out by comparing the moments of the restored image against the moments of the image database. In the second method the motion function is not known. In this case image moments that are invariant with respect to the motion blur are identified, and only these moments are used for recognition. The advantage of the suggested methods is that no time-consuming image restoration is required prior to recognition.     

A methodology for recognizing features in two-dimensional cylindrical part designs

The interfacing of computer-aided design (CAD) to computer-aided manufacturing (CAM) is a vital step in automated manufacturing. An essential operation is the recognition of features from the part design. This paper presents a methodology for the recognition of features from two-dimensional rotational objects. First, this work defines the term ‘feature’ as a set of connected lines in the profile of the object, which satisfy certain geometric properties. Then, the task of feature recognition is decomposed into a set of distinct functions. These recognize, classify, decompose and reconstruct, and identify face sets which satisfy the definition of features. A prototype is developed which implements these functions. The important characteristics of this methodology are: (1) all cylindrical features are recognized, and most of them identified according to the input formats of a desired CAPP system; and (2) the system is modular and flexible and its functions can be easily modified.     

Invariants under image perspective transformations: Theory and examples

The objective of this work is to develop automated techniques for recognizing the same objects in images that differ in scale, tilt, and rotation. Such perspective transformations of images are produced when aerial images of the same scene are taken from different vantage points. The algebraic methods developed previously do not utilize the intensity values of the images, i.e., their pixel gray levels. Since image features essential for object recognition, such as edges and local image textures, may be described in terms of derivatives and integrals of the image intensity, it is necessary to investigate whether certain differential and integral operators applied to different perspective views of the same object are also invariant under the perspective transformation. We proceed to derive new differential operators and their corresponding integral invariants for curves and planar objects. We introduce a variant form of Fourier expansion specially adapted to the projective transformation. Extensions to three dimensions are discussed, as well as applications to other image formation models such as synthetic aperture radar (SAR). These results are steps toward a computational model for perspective-independent object recognition.     

Occlusion invariant face recognition using mean based weight matrix and support vector machine

In this paper, a novel occlusion invariant face recognition algorithm based on Mean based weight matrix (MBWM) technique is proposed. The proposed algorithm is composed of two phases—the occlusion detection phase and the MBWM based face recognition phase. A feature based approach is used to effectively detect partial occlusions for a given input face image. The input face image is first divided into a finite number of disjointed local patches, and features are extracted for each patch, and the occlusion present is detected. Features obtained from the corresponding occlusion-free patches of training images are used for face image recognition. The SVM classifier is used for occlusion detection for each patch. In the recognition phase, the MBWM bases of occlusion-free image patches are used for face recognition. Euclidean nearest neighbour rule is applied for the matching. GTAV face database that includes many occluded face images by sunglasses and hand are used for the experiment. The experimental results demonstrate that the proposed local patch-based occlusion detection technique works well and the MBWM based method shows superior performance to other conventional approaches.     

综合PHOG和LWT的图像检索算法

目的研究物体的形状特征在图像描述及图像检索中的区分度和检索性能。方法设计一种综合PHOG形状和提升小波变换的图像检索算法。算法首先对原始图像进行极坐标系方向归一化,提取图像旋转不变特征;其次提取分层图像的PHOG形状特征;然后提取分层图像低频变换系数均值和方差作为提升小波变换特征;最后将各种特征进行融合并用于图像检索,并定义距离衡量公式。结果通过文中设计算法提取的图像形状特征可使各标准测试图像间距离均值为0.2352。结论在Corel图像集上的检索实验结果优于RIM算法和FWTH算法,表明文中算法图像检索领域具有一定的应用前景。     

Neural-network classifiers for automatic real-world aerial image recognition

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.     

基于视觉词袋模型提取胶痕特征的卷烟真伪鉴别

目的 为快速准确地鉴别多品牌卷烟真伪,提出一种基于视觉词袋模型提取烟盒胶痕图像特征的鉴别方法。方法 首先,利用自主设计的多光源胶痕采集装置获取烟盒内部的胶痕图像,通过图像处理技术去除原始图像的部分背景后得到胶痕图像样本;然后,从胶痕图像样本中提取尺度不变特征转换（SIFT）特征,并用K-Means算法对特征聚类生成视觉词典;再依据视觉词典的视觉单词直方图特征集对胶痕图像进行训练分类,从而达到鉴别卷烟真伪的目的。结果 以10种真品包装机型生产的烟盒胶痕图像以及假冒烟盒胶痕图像为对象,烟盒样品涉及64个卷烟品牌,对360张胶痕图像分类测试,得到真伪识别率为97.22%,每个样本平均鉴别时间为0.05s。结论 提出的方法采集胶痕图像简便、真伪鉴别效率和准确率高,并适用于多种卷烟品牌。为提高真伪卷烟鉴别效率、准确率和通用性提供了技术支持。     

Probabilistic approach to face recognition

Faces are highly deformable objects which may easily change their appearance over time. Not all face areas are subject to the same variability. Therefore, decoupling of the information from independent areas of the face is of paramount importance to improve the robustness of any face recognition technique. The aim of this article is to present a robust face recognition technique based on the extraction and matching of probabilistic graphs drawn on scale invariant feature transform (SIFT) features related to independent face areas. The face matching strategy is based on matching individual salient facial graphs characterized by SIFT features as connected to facial landmarks such as the eyes and the mouth. In order to reduce the face matching errors, the Dempster–Shafer decision theory is applied to fuse the individual matching scores obtained from each pair of salient facial features. The proposed algorithm is evaluated with the Olivetti Research Lab (ORL) and the Indian Institute of Technology Kanpur (IITK) face databases. The experimental results demonstrate the effectiveness and potential of the proposed face recognition technique, even in the case of partially occluded faces.     

Image scale determination for optimal texture classification using coordinated clusters representation

The efficiency of texture image classification is certainly influenced by image scale when a feature space or a classification method is not scale invariant. An alternative approach to the scale-invariant techniques is proposed that first estimates an effective image scale and then uses it to adjust texture features to get the best possible texture image recognition and classification. We use the correlation distance between pixels as a measure of the scale of texture images. We study the performance of classification of texture images in the coordinated cluster representation (CCR) versus an image scale and the size of the scanning window used for the coordinated cluster transform. Given the number of classes to be classified in, we find that an optimal (up to 100%) classification efficiency in the CCR feature space is obtained by changing an image scale and/or the size of the scanning window in the coordinated cluster transform.     

Efficient object detection and tracking in video sequences

One of the most important problems in computer vision is the computation of the two-dimensional projective transformation (homography) that maps features of planar objects in different images and videos. This computation is required by many applications such as image mosaicking, image registration, and augmented reality. The real-time performance imposes constraints on the methods used. In this paper, we address the real-time detection and tracking of planar objects in a video sequence where the object of interest is given by a reference image template. Most existing approaches for homography estimation are based on two steps: feature extraction (first step) followed by a combinatorial optimization method (second step) to match features between the reference template and the scene frame. This paper has two main contributions. First, we detect both planar and nonplanar objects via efficient object feature classification in the input images, which is applied prior to performing the matching step. Second, for the tracking part (planar objects), we propose a fast method for the computation of the homography that is based on the transferred object features and their associated local raw brightness. The advantage of the proposed schemes is a fast matching as well as fast and robust object registration that is given by either a homography or three-dimensional pose.     

A multiple feature/resolution approach to handprinted digit and character recognition

This article outlines the philosophy, design, and implementation of the Gradient, Structural, Concavity (GSC) recognition algorithm, which has been used successfully in several document reading applications. The GSC algorithm takes a quasi-multiresolution approach to feature generation; that is, several distinct feature types are applied at different scales in the image. These computed features measure the image characteristics at local, intermediate, and large scales. The local-scale features measure edge curvature in a neighborhood of a pixel, the intermediate features measure short stroke types which span several pixels, and the large features measure certain concavities which can span across the image. This philosophy, when coupled with the k-nearest neighbor classification paradigm, results in a recognizer which has both high accuracy and reliable confidence behavior. The confidences computed by this algorithm are generally high for valid class objects and low for nonclass objects. This allows it to be used in document reading algorithms which search for digit or character strings embedded in a field of objects. Applications of this paradigm to off-line digit string recognition and handwritten word recognition are discussed. Tests of the GSC classifier on large data bases of digits and characters are reported. © 1996 John Wiley & Sons, Inc.     

Optimal Deep Convolutional Neural Network for Vehicle Detection in Remote Sensing Images

Object detection (OD) in remote sensing images (RSI) acts as a vital part in numerous civilian and military application areas, like urban planning, geographic information system (GIS), and search and rescue functions. Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions. The latest advancements in deep learning (DL) approaches permit the design of effectual OD approaches. This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection (AEODCNN-VD) model on Remote Sensing Images. The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly. To detect vehicles, the presented AEODCNN-VD model employs single shot detector (SSD) with Inception network as a baseline model. In addition, Multiway Feature Pyramid Network (MFPN) is used for handling objects of varying sizes in RSIs. The features from the Inception model are passed into the MFPN for multiway and multiscale feature fusion. Finally, the fused features are passed into bounding box and class prediction networks. For enhancing the detection efficiency of the AEODCNN-VD approach, AEO based hyperparameter optimizer is used, which is stimulated by the energy transfer strategies such as production, consumption, and decomposition in an ecosystem. The performance validation of the presented method on benchmark datasets showed promising performance over recent DL models.     

基于小波计算的平面物体射影不变性的识别

利用非均匀有理B样条从单幅图像中提取平面物体在射影变换下的几何不变特征,建立经典框架。讨沦用小波计算框架的一维和二维特征不变矩的方法以减少计算量。实验结果表明所选取的特征不变量和算法有较小的计算量,对二维平面物体的识别有很好的性能,特别是允许景物中有部分的遮挡物存在。     

3D model-based pose invariant face recognition from multiple views

A 3D model-based pose invariant face recognition method that can recognise a human face from its multiple views is proposed. First, pose estimation and 3D face model adaptation are achieved by means of a three-layer linear iterative process. Frontal view face images are synthesised using the estimated 3D models and poses. Then the discriminant `waveletfaces' are extracted from these synthesised frontal view images. Finally, corresponding nearest feature space classifier is implemented. Experimental results show that the proposed method can recognise faces under variable poses with good accuracy     

基于连通域的图像中场景文本定位

提出了一种基于连通域的自动定位图像中场景文本的方法.该方法充分利用了场景文本的两类特征--字符特征和文本区域特征,同时对一些字符特征进行组合,组合得到的新字符特征能够对字符的大小、字体等有很好的不变性.该方法利用级联弱分类器将所有的特征组合到一个框架中,提高了处理速度.实验结果显示,该方法对字符的大小、颜色、语言等具有很好的鲁棒性,并具有较高的召回率.