A computer vision approach for weeds identification through Support Vector Machines

This paper outlines an automatic computer vision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the Support Vector Machines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the Support Vector Machines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies.     

Image segmentation by a contrario simulation

Segmenting an image into homogeneous regions generally involves a decision criterion to establish whether two adjacent regions are similar. Decisions should be adaptive to get robust and accurate segmentation algorithms, avoid hazardous a priori and have a clear interpretation. We propose a decision process based on a contrario reasoning: two regions are meaningfully different if the probability of observing such a difference in pure noise is very low. Since the existing analytical methods are intractable in our case, we extend them to allow a mixed use of analytical computations and Monte-Carlo simulations. The resulting decision criterion is tested experimentally through a simple merging algorithm, which can be used as a post-filtering and validation step for existing segmentation methods.     

SOFM模型在杂草图像识别中的应用

针对在杂草图像分割方面存在使用阈值分割需要选择分割阈值、图像分割精度不高等不足,本文结合超绿特征分割算法和SOFM网络,构造出一种杂草图像识别模型——G-SOFM空间聚类模型。该方法是一种无监督学习方式,不需要指定阈值,利用网络自组织、自竞争的特性,实现对杂草图像的分割。在对图像进行超绿特征处理之后,使用超绿特征的灰度和归一化两个特征向量,实现SOFM空间聚类。实验结果表明,改进的G-SOFM方法相比其他三种杂草图像分割算法的分割结果都有一定的提高,分别比HIS阈值分割、超绿特征分割、双阈值分割提高28%、20%、21%。本算法结合后期形态学去噪后,识别正确率可达94%。     

Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

An algorithm using the unsupervised Bayesian online learning process is proposed for the segmentation of object-based video images. The video image segmentation is solved using a classification method. First, different visual features (the spatial location, colour and optical-flow vectors) are fused in a probability framework for image pixel clustering. The appropriate modelling of the probability distribution function (PDF) for each feature-cluster is obtained through a Gaussian distribution. The image pixel is then assigned a cluster number in a maximum a posteriori probability framework. Different from the previous segmentation methods, the unsupervised Bayesian online learning algorithm has been developed to understand a cluster's PDF parameters through the image sequence. This online learning process uses the pixels of the previous clustered image and information from the feature-cluster to update the PDF parameters for segmentation of the current image. The unsupervised Bayesian online learning algorithm has shown satisfactory experimental results on different video sequences.     

Image Parsing: Unifying Segmentation,Detection, and Recognition

In this paper we present a Bayesian framework for parsing images into their constituent visual patterns. The parsing algorithm optimizes the posterior probability and outputs a scene representation as a parsing graph, in a spirit similar to parsing sentences in speech and natural language. The algorithm constructs the parsing graph and re-configures it dynamically using a set of moves, which are mostly reversible Markov chain jumps. This computational framework integrates two popular inference approaches—generative (top-down) methods and discriminative (bottom-up) methods. The former formulates the posterior probability in terms of generative models for images defined by likelihood functions and priors. The latter computes discriminative probabilities based on a sequence (cascade) of bottom-up tests/filters. In our Markov chain algorithm design, the posterior probability, defined by the generative models, is the invariant (target) probability for the Markov chain, and the discriminative probabilities are used to construct proposal probabilities to drive the Markov chain. Intuitively, the bottom-up discriminative probabilities activate top-down generative models. In this paper, we focus on two types of visual patterns—generic visual patterns, such as texture and shading, and object patterns including human faces and text. These types of patterns compete and cooperate to explain the image and so image parsing unifies image segmentation, object detection, and recognition (if we use generic visual patterns only then image parsing will correspond to image segmentation (Tu and Zhu, 2002. IEEE Trans. PAMI, 24(5):657–673). We illustrate our algorithm on natural images of complex city scenes and show examples where image segmentation can be improved by allowing object specific knowledge to disambiguate low-level segmentation cues, and conversely where object detection can be improved by using generic visual patterns to explain away shadows and occlusions.     

基于Gabor 变换的GrabCut 纹理图像分割

多数自然图像都包含纹理信息, 它相对颜色特征而言具有描述方向性与尺度差异的特性. 因此, 可以利用半交互式的GrabCut 的图像分割方式对图像前景区域与背景区域进行有效的分割, 通过建立前景和背景所对应的高斯混合模型(GMM), 结合最大流最小割的图像分割方式实现全局优化, 并利用前景和背景的KL 测度, 自适应地终止分割过程. 实验对比分析表明, 所提出的方法对于合成纹理图像与自然纹理图像具有较好的整体分割效果及较高的分割准确率.

     

Parallel implementation of simulated annealing to reproduce multiple-point statistics

This paper shows an innovative implementation of simulated annealing in the context of parallel computing. Details regarding the use of parallel computing through a cluster of processors, as well as the implementation decisions, are provided. Simulated annealing is presented aiming at the generation of stochastic realizations of categorical variables reproducing multiple-point statistics.The procedure starts with the use of a training image to determine the frequencies of occurrence of particular configurations of nodes and values. These frequencies are used as target statistics that must be matched by the stochastic images generated with the algorithm. The simulation process considers an initial random image of the spatial distribution of the categories. Nodes are perturbed randomly and after each perturbation the mismatch between the target statistics and the current statistics of the image is calculated. The perturbation is accepted if the statistics are closer to the target, or conditionally rejected if not, based on the annealing schedule.The simulation was implemented using parallel processes with C++ and MPI. The message passing scheme was implemented using a speculative computation framework, by which prior to making the decision of acceptance or rejection of a proposed perturbation, processes already start calculating the next possible perturbation at a second level; one as if the perturbation on level one is accepted, and another process as if the proposed perturbation is rejected. Additional levels can start their calculation as well, conditional to the second level processes. Once a process reaches a decision as to whether accept or reject the suggested perturbation, all processes within the branch incompatible with that decision are dropped. This allows a speed up of up to log_n(p+1), where n is the number of categories and p the number of processes simultaneously active.Examples are provided to demonstrate improvements and speed ups that can be achieved.     

Performance Modeling and Algorithm Characterization for Robust Image Segmentation

This paper presents a probabilistic framework based on Bayesian theory for the performance prediction and selection of an optimal segmentation algorithm. The framework models the optimal algorithm selection process as one that accounts for the information content of an input image as well as the behavioral properties of a particular candidate segmentation algorithm. The input image information content is measured in terms of image features while the candidate segmentation algorithm’s behavioral characteristics are captured through the use of segmentation quality features. Gaussian probability distribution models are used to learn the required relationships between the extracted image and algorithm features and the framework tested on the Berkeley Segmentation Dataset using four candidate segmentation algorithms.     

基于万有信息定律的图像阈值分割方法

提出基于万有信息定律的图像阈值分割方法。针对熵阈值法仅利用图像灰度概率信息，导致它对有些图像的分割无效，该文从万有引力定律中得到启发，提出信息场中万有信息定律，将其用于图像分割的最佳阈值选取。实验结果表明，该方法是可行的，且对有些图像的分割效果要好于传统的Kapur熵方法。     

高分辨率极化SAR图像水平集分割

目的 传统的极化SAR图像分割方法中,由于采用的统计分布模型不能较好地描述高分辨率的图像纹理特征,导致高分辨率极化SAR图像分割效果较差。针对这个问题,本文将具有广泛适用性的KummerU分布嵌入到水平集极化SAR图像分割方法中,提出了一种新的极化SAR图像分割算法。方法 将KummerU分布作为高分辨率极化SAR图像的统计模型,定义一种适用于极化SAR图像分割的能量泛函;利用最大似然法对各个区域的KummerU分布进行参数估计,并通过数值偏微分方程的方法求解水平集函数,实现极化SAR图像的区域分割。结果 分别对仿真全极化数据,真实全极化数据进行分割实验,结果表明本文提出的方法其分割精度高于传统方法,分割精度高于95%,从而验证了新方法的有效性。结论 本文算法能够对各向同质区和各向异质区的极化SAR图像都能取得良好的分割效果,并适应于多种场景,有效地分割出背景和目标。     

Shape ultimate attribute opening

The ultimate opening (UO) is a powerful segmentation operator recently introduced by Beucher [1]. It automatically selects the most contrasted regions of an image. However, in the presence of nested structures (e.g. text in a signboard or windows in a contrasted facade), interesting structures may be masked by the containing region. In this paper we focus on ultimate attribute openings and we propose a method that improves the results by favoring regions with a predefined shape via a similarity function. An efficient implementation using a max-tree representation of the image is proposed. The method is validated in the framework of three applications: facade analysis, scene-text detection and cell segmentation. Experimental results show that the proposed method yields better segmentation results than UO.     

Global–local optimizations by hierarchical cuts and climbing energies

Hierarchical segmentation is a multi-scale analysis of an image and provides a series of simplifying nested partitions. Such a hierarchy is rarely an end by itself and requires external criteria or heuristics to solve problems of image segmentation, texture extraction and semantic image labelling. In this theoretical paper we introduce a novel framework: hierarchical cuts, to formulate optimization problems on hierarchies of segmentations. Second we provide the three important notions of h-increasing, singular, and scale increasing energies, necessary to solve the global combinatorial optimization problem of partition selection and which results in linear time dynamic programs. Common families of such energies are summarized, and also a method to generate new ones is described. Finally we demonstrate the application of this framework on problems of image segmentation and texture enhancement.     

Optimization in multi‐scale segmentation of high‐resolution satellite images for artificial feature recognition

Multi‐resolution segmentation, as one of the most popular approaches in object‐oriented image segmentation, has been greatly enabled by the advent of the commercial software, eCognition. However, the application of multi‐resolution segmentation still poses problems, especially in its operational aspects. This paper addresses the issue of optimization of the algorithm‐associated parameters in multi‐resolution segmentation. A framework starting with the definition of meaningful objects is proposed to find optimal segmentations for a given feature type. The proposed framework was tested to segment three exemplary artificial feature types (sports fields, roads, and residential buildings) in IKONOS multi‐spectral images, based on a sampling scheme of all the parameters required by the algorithm. Results show that the feature‐type‐oriented segmentation evaluation provides an insight to the decision‐making process in choosing appropriate parameters towards a high‐quality segmentation. By adopting these feature‐type‐based optimal parameters, multi‐resolution segmentation is able to produce objects of desired form to represent artificial features.     

Multiscale Bayesian texture segmentation using neural networks and Markov random fields

This paper presents a wavelet-based texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields (MRF) in a multi-scale Bayesian framework. Inputs and outputs of MLP networks are constructed to estimate a posterior probability. The multi-scale features produced by multi-level wavelet decompositions of textured images are classified at each scale by maximum a posterior (MAP) classification and the posterior probabilities from MLP networks. An MRF model is used in order to model the prior distribution of each texture class, and a factor, which fuses the classification information through scales and acts as a guide for the labeling decision, is incorporated into the MAP classification of each scale. By fusing the multi-scale MAP classifications sequentially from coarse to fine scales, our proposed method gets the final and improved segmentation result at the finest scale. In this fusion process, the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. Our texture segmentation method was applied to segmentation of gray-level textured images. The proposed segmentation method shows better performance than texture segmentation using the hidden Markov trees (HMT) model and the HMTseg algorithm, which is a multi-scale Bayesian image segmentation algorithm.     

A universal texture segmentation and representation scheme based on ant colony optimization for iris image processing

This paper proposes a novel scheme for texture segmentation and representation based on Ant Colony Optimization (ACO). Texture segmentation and texture characteristic expression are two important areas in image pattern recognition. Nevertheless, until now, how to find an effective way for accomplishing these tasks is still a major challenge in practical applications such as iris image processing. We propose a framework for ACO based image processing methods. Considering the specific characteristics of various tasks, such a framework possesses the flexibility of only defining different criteria for ant behavior correspondingly. By defining different kinds of direction probability and movement difficulty for artificial ants, an ACO based image segmentation algorithm and a texture representation method are then presented for automatic iris image processing. Experimental results demonstrated that the ACO based image processing methods are competitive and quite promising, with excellent effectiveness and practicability especially for images with complex local texture situations.     

一种基于纹理特征融合的SAR图像分割方法

在由若干灰度共生矩阵纹理统计量进行特征融合后所生成的图像上,定义多分辨双Markov-GAR模型,采用多分辨MPM参数估计方法及相应的无监督分割算法,对SAR图像进行纹理分割。该方法既利用了像素的灰度信息,也利用了像素的空间位置信息,削弱了斑点噪声对分割的影响。实验表明对于一些高分辨SAR图像,该方法与单纯基于灰度图像上的多分辨双Markov-GAR模型纹理分割相比,分割精度得以提高。     

基于改进HVS的水稻杂草图像分割算法

研究水稻杂草图像分割问题,提高分割的准确性。水稻在颜色和形态上与杂草像素差异很小,造成二维图像像素重叠。传统的基于颜色和形态模型的分割算法,在这种情况下,很难准确的对混合杂草的水稻图像进行准确分割。针对分割效果不准确的问题,提出一种基于改进HVS模型的水稻杂草分割算法。通过在传统模型中加入图像亮度特性、像素频率特性、颜色的感知特性,以改进传统的水稻视觉图像模型。避免了传统分割算法对颜色和形态特征过度依赖的弊端。实验证明,利用改进后的图像视觉模型能够在重叠、间隔的水稻图像中,准确的分割杂草图像,取得了令人满意的结果。     

Order Parameters for Detecting Target Curves in Images: When Does High Level Knowledge Help?

Many problems in vision can be formulated as Bayesian inference. It is important to determine the accuracy of these inferences and how they depend on the problem domain. In this paper, we provide a theoretical framework based on Bayesian decision theory which involves evaluating performance based on an ensemble of problem instances. We pay special attention to the task of detecting a target in the presence of background clutter. This framework is then used to analyze the detectability of curves in images. We restrict ourselves to the case where the probability models are ergodic (both for the geometry of the curve and for the imaging). These restrictions enable us to use techniques from large deviation theory to simplify the analysis. We show that the detectability of curves depend on a parameter K which is a function of the probability distributions characterizing the problem. At critical values of K the target becomes impossible to detect on average. Our framework also enables us to determine whether a simpler approximate model is sufficient to detect the target curve and hence clarify how much information is required to perform specific tasks. These results generalize our previous work (Yuille, A.L. and Coughlan, J.M. 2000. Pattern Analysis and Machine Intelligence PAMI, 22(2):160–173) by placing it in a Bayesian decision theory framework, by extending the class of probability models which can be analyzed, and by analysing the case where approximate models are used for inference.     

基于灰度共生矩阵纹理特征的SAR图像分割

同时考虑SAR图像局部灰度均值和方差及像素空间分布特征等统计量,在以灰度共生矩阵产生的纹理统计量为特征所生成的图像上,建立多分辨双Markov-GAR模型,采用多分辨MPM的参数估计方法及相应的无监督分割算法,对SAR图像进行纹理分割。该方法用于一些高分辨SAR图像,其分割精度及分割边缘的平滑度均优于基于灰度图像上的多分辨双Markov-GAR模型纹理分割。