Learning to Perceive Objects for Autonomous Navigation

Current machine perception techniques that typically use segmentation followed by object recognition lack the required robustness to cope with the large variety of situations encountered in real-world navigation. Many existing techniques are brittle in the sense that even minor changes in the expected task environment (e.g., different lighting conditions, geometrical distortion, etc.) can severely degrade the performance of the system or even make it fail completely. In this paper we present a system that achieves robust performance by using local reinforcement learning to induce a highly adaptive mapping from input images to segmentation strategies for successful recognition. This is accomplished by using the confidence level of model matching as reinforcement to drive learning. Local reinforcement learning gives rises to better improvement in recognition performance. The system is verified through experiments on a large set of real images of traffic signs.     

Adaptive target recognition

Target recognition is a multilevel process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their performance at the given probability of correct identification (PCI) and probability of false alarm (Pf) is a key challenge in computer vision and pattern recognition research. In this paper, a robust closed-loop system for recognition of SAR images based on reinforcement learning is presented. The parameters in model-based SAR target recognition are learned. The method meets performance specifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targets of different configuration and targets at different depression angles.     

基于纹理分析的指纹图像分割算法

低质量指纹图像处理是近年来自动指纹识别技术的研究重点,对低质量指纹图像的分割是实现后续处理的前提。文中在分析了方差作为分割指标的局限性基础上,从指纹图像的纹理特征出发,研究了指纹图像的灰度分布规律,提出了基于纹理的指纹图像分割算法。实验结果表明,相比于基于灰度方差的指纹图像分割算法,文中算法的分割效果更好,对噪声的抵抗能力更强。     

Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition

Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.     

指纹自动识别中图像分割算法研究

为了可靠、准确地实现指纹的自动识别,提出了一种简便、可行的指纹图像的分割算法。通过合理地运用指纹图像的灰度特性,以较低的计算代价有效地解决了指纹图像的分割问题,从而使算法的处理效果好、运行速度快。实验表明,这种分割算法对于指纹图像的预处理十分有效。     

快速鲁棒核空间模糊聚类分割

目的 传统模糊C-均值聚类应用于图像分割仅考虑像素本身的聚类问题,无法克服噪声干扰对图像分割结果的影响,不利于受到噪声干扰的工业图像、医学影像和高分遥感影像等进行目标提取、识别和解译。嵌入像素空间邻域信息或局部信息的鲁棒模糊C-均值聚类分割算法是近年来图像分割理论研究中的热点课题。为此,针对现有的鲁棒核空间模糊聚类算法非常耗时且抑制噪声能力弱、不适合强噪声干扰下大幅面图像快速分割等问题,提出一种快速鲁棒核空间模糊聚类分割算法。方法 利用待分割图像中像素邻域的灰度信息和空间位置等信息构建线性加权滤波图像,对其进行鲁棒核空间模糊聚类。为了进一步提高算法实时性,引入当前聚类像素与其邻域像素均值所对应的2维直方图信息,构造一种基于2维直方图的鲁棒核空间模糊聚类快速分割最优化数学模型,采用拉格朗日乘子法获得图像分割的像素聚类迭代表达式。结果 对大幅面图像添加一定强度的高斯、椒盐以及混合噪声,以及未加噪标准图像的分割测试结果表明,本文算法比基于邻域空间约束的核模糊C-均值聚类等算法的峰值信噪比至少提高1.5 dB,误分率降低约5%,聚类性能评价的划分系数提高约10%,运行速度比核模糊C-均值聚类和基于邻域空间约束的鲁棒核模糊C-均值聚类算法至少提高30%,与1维直方图核空间模糊C-均值聚类算法具有相当的时间开销,所得分割结果具有较好的主观视觉效果。结论 通过理论分析和实验验证,本文算法相比现有空间邻域信息约束的鲁棒核空间模糊聚类等算法具有更强的抗噪鲁棒性、更优的分割性能和实时性,对大幅面遥感、医学等影像快速解译具有积极的促进作用,能更好地满足实时性要求较高场合的图像分割需要。     

Performance improvement of character recognition in industrial applications using prior knowledge for more reliable segmentation

In industrial applications optical character recognition with smart cameras becomes more and more popular. Since these applications mostly have challenging environments for the systems it is most important to have very reliable character segmentation and classification algorithms. The investigations of several algorithms have shown that character segmentation is one if not the main bottleneck of character recognition. Furthermore, the requirements of robust and fast algorithms related to skew angle estimation and line segmentation, as well as tilt angle estimation, and character segmentation are high. This is the reason for introducing such algorithms that are specifically adapted to industrial applications. Additionally, a method is proposed that is based on the Bayes theorem to take account of prior knowledge for line and character segmentation. The main focus of the investigations of the character recognition system is recognition performance and speed, since real-time constraints are very hard in industrial application. Both requirements are evaluated on an image series captured with a smart camera in an industrial application.     

Automatic performance evaluation of printed Chinese character recognition systems

Performance evaluation is crucial for improving the performance of OCR systems. However, this is trivial and sophisticated work to do by hand. Therefore, we have developed an automatic performance evaluation system for a printed Chinese character recognition (PCCR) system. Our system is characterized by using real-world data as test data and automatically obtaining the performance of the PCCR system by comparing the correct text and the recognition result of the document image. In addition, our performance evaluation system also provides some evaluation of performance for the segmentation module, the classification module, and the post-processing module of the PCCR system. For this purpose, a segmentation error-tolerant character-string matching algorithm is proposed to obtain the correspondence between the correct text and the recognition result. The experiments show that our performance evaluation system is an accurate and powerful tool for studying deficiencies in the PCCR system. Although our approach is aimed at the PCCR system, the idea also can be applied to other OCR systems.     

Real-time hand posture recognition using range data

A hand posture recognition system using 3D data is described. The system relies on a novel 3D sensor that generates a dense range image of the scene. The main advantage of the proposed system, compared to other gesture recognition techniques, is the capability for robust unconstrained recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly utilizing 3D hand geometry. Moreover, the proposed approach does not rely on color information, and guarantees robust segmentation of the hand under varying illumination conditions, and scene content. Several novel 3D image analysis algorithms are presented, covering the complete processing chain: 3D image acquisition, arm segmentation, hand–forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is extensively evaluated.     

Counting eosinophils in bronchoalveolar lavage fluid images with fuzzy methodology

This paper proposes a new fuzzy approach to count eosinophils, as a measure of inflammation, in bronchoalveolar lavage fluid images, provided by digital camera through microscope. We use fuzzy cluster analysis and fuzzy classification algorithm to determine the number of objects in an image. For this purpose, a fuzzy image processing procedure consisting of five main stages is presented. The first stage is pre-highlighting the objects in the images by using an image pre-processing method for enhancement, which is sharpening the image with the Laplaian high pass filter in order to have acceptable contrast in the image. The second stage is segmentation by clustering with fuzzy c-mean algorithm for portioning. In this stage the clustered data are the rough symbols of objects in the image containing noise. In the third step, first, a Gaussian low pass filter is used for noise reduction. Then, a contrast adoption in the image is done by modifying the membership functions in the image [H.R. Tizhoosh, G. Krell, B. Michaelis, Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system, Image and Vision Computing 19(July) (2000) 217–233]. Object recognition, the fourth stage, will be done by using fuzzy labeling for the objects in the image, using a fuzzy classification method. The number of labeled images shows the number of eosinophils in an image which is an index for diagnosing inflammation. The last stage is tuning parameters and verification of the system performance by using a feed forward Neural Network.     

On techniques for angle compensation in nonideal iris recognition.

The popularity of the iris biometric has grown considerably over the past two to three years. Most research has been focused on the development of new iris processing and recognition algorithms for frontal view iris images. However, a few challenging directions in iris research have been identified, including processing of a nonideal iris and iris at a distance. In this paper, we describe two nonideal iris recognition systems and analyze their performance. The word "nonideal" is used in the sense of compensating for off-angle occluded iris images. The system is designed to process nonideal iris images in two steps: 1) compensation for off-angle gaze direction and 2) processing and encoding of the rotated iris image. Two approaches are presented to account for angular variations in the iris images. In the first approach, we use Daugman's integrodifferential operator as an objective function to estimate the gaze direction. After the angle is estimated, the off-angle iris image undergoes geometric transformations involving the estimated angle and is further processed as if it were a frontal view image. The encoding technique developed for a frontal image is based on the application of the global independent component analysis. The second approach uses an angular deformation calibration model. The angular deformations are modeled, and calibration parameters are calculated. The proposed method consists of a closed-form solution, followed by an iterative optimization procedure. The images are projected on the plane closest to the base calibrated plane. Biorthogonal wavelets are used for encoding to perform iris recognition. We use a special dataset of the off-angle iris images to quantify the performance of the designed systems. A series of receiver operating characteristics demonstrate various effects on the performance of the nonideal-iris-based recognition system.     

An approach based on simulated annealing to optimize the performance of extraction of the flower region using mean-shift segmentation

Flower identification and recognition are tedious and difficult tasks even for humans. Image segmentation based on automatic flower extraction is an essential step for computer-aided flower image recognition and retrieval processes. Furthermore, there is a challenge for segmentation of the object(s) from natural complex background in color images. In this study, a novel performance optimization approach for image segmentation, i.e. simulated annealing-based mean-shift segmentation (SAMS), is proposed and implemented. It is based on the simulated annealing solution of quadratic assignment problem model treated as an image segmentation process using feature-based mean-shift (MS) clustering on color images. The proposed approach is designed to realize a global and unsupervised (i.e., fully automatic) segmentation. It is a modified and optimized version of Backprojection-based mean-shift segmentation (BackMS) method. In conducted segmentation experiments, the performance results of SAMS approach are compared with the ones of BackMS method. Comparison of overall performance results and statistical analysis (i.e., Wilcoxon signed rank median test) show that SAMS approach improves the performance of BackMS method. It is measured as 49.33% when using object bounding boxes and as 51.33% when using object pixel regions.     

利用Hough变换和先验知识的车牌字符分割算法

随着科技的发展,车牌识别系统得到了很多应用。车牌识别系统包含三个部分：车牌定位、字符分割和字符识别。车牌字符分割是车牌自动识别系统中的重要步骤。车牌字符分割中存在噪声干扰、边框影响、铆钉和间隔符影响、车牌旋转、光照不均等问题。这些问题容易造成分割不准确,甚至分割错误。针对这些问题,该文提出了一种先分段,再利用Hough变换拟合直线的水平分割方法和基于先验知识约束的垂直分割方法,同时提出目标增强的预处理方法。大量实验表明,该算法较好地解决了以上问题,适用于各种质量的车牌图像,分割的准确率较高。     

Spatial kernel K-harmonic means clustering for multi-spectral image segmentation

The problem of image segmentation using intensity clustering approaches has been addressed in the literature. Grouping pixels of similar intensity to form clusters in an image have been tackled using a number of methods, such as the K-means (KM) algorithm. The K-harmonic means (KHM) was proposed to overcome the sensitivity of KM to centre initialisation. The use of a spatial kernel-based KHM (SKKHM) algorithm on the problem of image segmentation has been investigated. Instead of the original Euclidean intensity distance, a robust kernel-based KHM metric is employed to reduce the effect of outliers and noise. Spatial image information is also incorporated in the proposed clustering scheme, derived from Markov random field modelling. An extension of the proposed algorithm to multi-spectral imaging applications is also presented. Experimental results for both single-channel and multi-channel images demonstrate the robust performance of the proposed SKKHM algorithm.     

Line-based recognition using a multidimensional Hausdorff distance

A line-feature-based approach for model based recognition using a four-dimensional Hausdorff distance is proposed. This approach reduces the problem of finding the rotation, scaling, and translation transformations between a model and an image to the problem of finding a single translation minimizing the Hausdorff distance between two sets of points in a four-dimensional space. The implementation of the proposed algorithm can be naturally extended to higher dimensional spaces to efficiently find correspondences between n-dimensional patterns. The method performance and sensitivity to segmentation problems are quantitatively characterized using an experimental protocol with simulated data. It is shown that the algorithm performs well, is robust to occlusion and outliers, and that it degrades nicely as the segmentation problems increase. Experiments with real images are also presented     

A robust technique based on invariant moments – ANFIS for recognition of human parasite eggs in microscopic images

In this study, we propose a robust technique based on invariant moments – adaptive network based fuzzy inference system (IM-ANFIS). In this technique, some digital image processing methods such as noise reduction, contrast enhancement, segmentation, and morphological process are used for feature extraction stage of IM-ANFIS approach used in this study. Recently, the pattern recognition principles have come into prominence. The pattern recognition includes operation and design of systems that recognize patterns in data sets. Important application areas of pattern recognition techniques are character recognition, speech analysis, image segmentation, man and machine diagnostics and industrial inspection. The technique presented in this study enables to classify 16 different parasite eggs from their microscopic images. This proposed recognition method includes three stages. In first stage, a preprocessing subsystem is realized for obtaining unique features from the same group of patterns. In second stage, a feature extraction mechanism which is based on the invariant moments is used. In third stage, an adaptive network based fuzzy inference system (ANFIS) classifier is used for recognition process. We conduct computer simulations on MATLAB environment. The overall success rate is almost 95%.     

High-resolution SAR images segmentation using NSCT denoising and QIGA based parameters selection of PCNN model

The high-resolution synthetic aperture radar (SAR) images usually contain inhomogeneous coherent speckle noises. For the high-resolution SAR image segmentation with such noises, the conventional methods based on pulse coupled neural networks (PCNN) have to face heavy parameters with a low efficiency. In order to solve the problems, this paper proposes a novel SAR image segmentation algorithm based on non-subsampling Contourlet transform (NSCT) denoising and quantum immune genetic algorithm (QIGA) improved PCNN models. The proposed method first denoising the SAR images for a pre-processing based on NSCT. Then, by using the QIGA to select parameters for the PCNN models, such models self-adaptively select the suitable parameters for segmentation of SAR images with different scenes. This method decreases the number of parameters in the PCNN models and improves the efficiency of PCNN models. At last, by using the optimal threshold to binary the segmented SAR images, the small objects and large scales from the original SAR images will be segmented. To validate the feasibility and effectiveness of the proposed algorithm, four different comparable experiments are applied to validate the proposed algorithm. Experimental results have shown that NSCT pre-processing has a better performance for coherent speckle noises suppression, and QIGA-PCNN model based on denoised SAR images has an obvious segmentation performance improvement on region consistency and region contrast than state-of-the-arts methods. Besides, the segmentation efficiency is also improved than conventional PCNN model, and the level of time complexity meets the state-of-the-arts methods. Our proposed NSCT+QIGA-PCNN model can be used for small object segmentation and large scale segmentation in high-resolution SAR images. The segmented results will be further used for object classification and recognition, regions of interest extraction, and moving object detection and tracking.