基于最近邻搜索耦合近邻损耗聚类的图像伪造检测算法

目的为了解决当前图像伪造检测算法在对图像进行伪造检测时,主要依靠全局搜索的方式来完成特征点匹配,导致其检测效率较低,且在对复杂伪造图像进行检测时,易出现检测精度不高和检测错误的不足。方法提出基于最近邻搜索耦合近邻损耗聚类的图像伪造检测算法。首先引入积分图像的方法,对图像进行预处理,借助Hessian矩阵行列式来提取特征点。利用特征点构建圆形区域,通过求取圆形区域内Haar小波响应获取特征点的特征描述符。然后通过特征描述符建立KD树索引,利用最近邻搜索方法代替SURF中全局搜索的方法,对SURF进行改进,完成特征点的匹配。最后,利用特征点间的近邻关系求取近邻函数值,通过近邻函数值对特征点进行聚类,完成图像的伪造检测。结果实验结果显示,与当前图像伪造检测算法相比,所提算法具有更高的检测效率以及更高的检测正确度。结论所提算法具备较高的检测精度,在印刷防伪与信息安全等领域具有较好的应用价值。     

An Image Mosaic Method for Defect Inspection of Steel Rotary Parts

According to the features of the inspection images for the steel rotary parts with defects, a novel image mosaic method, using Scale Invariant Feature Transform (SIFT) feature tracking with purifying feature points based on slope probability measure and RANSAC algorithm, is proposed. First, the method preprocesses the captured sequence images, and then implements projection transformation for these images. Then, the registration parameters for two adjacency images, using the SIFT algorithm and removal algorithm of the pseudo matching feature point pairs based on slope probability measure and RANSAC algorithm, can be solved to mosaic the defect inspection images of the parts with enough characteristic information. On this basis, a hardware-based method is used to perform image stitching of the measured parts. Experimental results show that the method can produce a large number of the correct matching feature point pairs, and can get a seamless, clear surface image of the parts, which will settle the foundation for automatic accurate inspection of the surface defects on metal parts.     

基于灰度相关特征点的图像拼接算法

提出了一种基于特征点的图像拼接算法,首先利用Harris角点检测提取两幅图像中的特征点,用特征点邻域灰度相关性将特征点进行匹配,并在此基础上根据变换参数向量的欧式距离对误匹配进行剔除,进而实现图像拼接.实验表明,这种算法能有效的排除误匹配的干扰,降低误匹配率,拼接效果良好.     

Image retrieval using wavelet-based salient regions

Abstract

A content-based image retrieval system normally returns the retrieval results according to the similarity between features extracted from the query image and candidate images. In certain circumstances, however, users may concern more about salient regions in an image of their interest and only wish to retrieve images containing the relevant salient regions while ignoring those irrelevant (such as the background or other regions and objects). Although how to represent the local image properties is still one of the most active research issues, much previous work on image retrieval does not examine salient regions in an image. In this paper, we propose an improved salient point detector based on wavelet transform; it can extract salient points in an image more accurately. Then salient points are segmented into different salient regions according to their spatial distribution. Colour moments and Gabor features of these different salient regions are computed and form a feature vector to index the image. We test the proposed scheme using a wide range of image samples from the Corel Image Library. The experimental results indicate that the method has produced promising results.     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

A feature extraction method for galvanized steel sheet powdering rates classification

Abstract

This paper describes a feature extraction method for classifying galvanized steel sheet powdering rates. By combining machine vision with statistics, and using the standard deviation's difference between powdered and normal regions, the range of powdered areas is recognized. The method exhibits a number of interesting features: it uses mathematical statistics for image feature analysis, and develops an effective method for analyzing particle size which cannot be measured by manual detection. The experiment result shows that the correction rate of this method to acquire galvanized steel sheet powdered regions is up to 99%, which satisfies the requirements of the application.     

Multimodal region-consistent saliency based on foreground and background priors for indoor scene

Visual saliency is a very important feature for object detection in a complex scene. However, image-based saliency is influenced by clutter background and similar objects in indoor scenes, and pixel-based saliency cannot provide consistent saliency to a whole object. Therefore, in this paper, we propose a novel method that computes visual saliency maps from multimodal data obtained from indoor scenes, whilst keeping region consistency. Multimodal data from a scene are first obtained by an RGB+D camera. This scene is then segmented into over-segments by a self-adapting approach to combine its colour image and depth map. Based on these over-segments, we develop two cues as domain knowledge to improve the final saliency map, including focus regions obtained from colour images, and planar background structures obtained from point cloud data. Thus, our saliency map is generated by compounding the information of the colour data, the depth data and the point cloud data in a scene. In the experiments, we extensively compare the proposed method with state-of-the-art methods, and we also apply the proposed method to a real robot system to detect objects of interest. The experimental results show that the proposed method outperforms other methods in terms of precisions and recall rates.     

基于角点检测的图像镶嵌算法

由于采用普通照相机拍摄的照片可能出现图像扭曲、交叠和倾斜,现有的图像镶嵌算法仍不能有效的进行处理,而且在这方面的研究也相对甚少.本文针对此问题,提出了一种适用于图像发生任意角度的旋转变换下仍可实现精确镶嵌的算法.即首先是采用Harris算子进行角点提取,使提取的精度达到亚像素级;然后根据这些角点信息建立图像间的角点对应关系,并由此得到投影变换矩阵;接下来采用图像变形技术,通过逆向映射重建发生空间变换的图像,由此得到的变形图像与源图像再进行无缝拼合.实验证明,该算法是有效的,具有较高的镶嵌精度.     

A study of the feature‐based digital image stabilization system

Abstract

This article presents a digital image stabilization scheme that uses image processing techniques to compensate for undesirable image jitter due to vehicle or platform vibration to obtain a stabilized image display. The developed digital image stabilization system is based on the image combination approach combined with advanced image selection, feature detection, feature matching and pre‐rotation processing to produce crisp images. Using the Sobel edge detector, we calculate the magnitude of edge response as the judgment criteria for image transformation. To demonstrate the validity of the proposed technique, experimental results are given for some synthetic images.     

Hierarchical secret image sharing using phase modulation based on the Fresnel transform

ABSTRACT

In idealized secret image sharing (SIS), all of the shared images (shadows) play the same role, but in real life, the shared images are often hierarchical. This paper proposes a hierarchical secret image sharing (HSIS) method by means of optical imaging. To implement the scheme, a generalized single-phase modulation algorithm is proposed in Fresnel transform domain. Its features that multiple secret images can be recovered through combination of some shared images though each participant only holds one share of images. Theoretically, the secret images are divided into multiple phase encodings (shared images) by phase modulation, each secret image can be directly captured by the intensity detector when illuminating some of the shared images orderly displayed with parallel light. Experimental simulation shows that the shared images and the restored secret images do not have any size distortion, and further verifies the feasibility of the proposed scheme.     

Grating mosaic based on image processing of far-field diffraction intensity patterns in two wavelengths

A practical grating mosaic method is proposed based on quantitative image processing of three far-field diffraction intensity patterns in two wavelengths. This method aims at making a perfect mosaic of two planar gratings that can substitute for a single and larger grating without introducing wavefront aberration at any wavelength. The zeroth-order and first-order far-field patterns of one wavelength are analyzed for separating and eliminating the angular mosaic errors. The first-order far-field patterns of two wavelengths are applied for separation of the lateral and longitudinal phase errors. Then the three patterns are considered together to enlarge the target range of coarse adjustment required for further fine adjustment in longitudinal position. Experimentally, angular and positional detection sensitivities of less than 6 microrad and 14 nm were achieved, respectively, and the periodicity in positional adjustment was checked, which departed less than 1.8% from the theoretical period. The performance of the perfect mosaic grating was diagnosed with the far-field diffraction intensity pattern in a third wavelength, and the necessity for a perfect mosaic was verified.     

数字化无人机航空像片拼接技术研究

本文阐述了基于特征匹配的无人机航空像片拼接技术。从对影像匹配技术、拼接算法的深入研究,结合影像特征提取方法,着重分析解决了拼接解算控制点精度和可靠识别问题。     

摄像机旋转运动下的快速目标检测算法

论文提出了一种摄像机旋转运动下的快速目标检测算法。首先为图像的全局运动建立旋转参数模型,然后基于运动预测在相邻帧之间建立SIFT特征点对,利用RANSAC去除外点的影响,结合最小二乘法求解全局运动参数进行运动补偿,基于残差图像的更新策略实时更新特征点集,以适应背景的变化,最后使用帧差法获得运动目标。该算法不仅保持了SIFT本身的优越性能,而且极大地提高了检测速度。实验结果表明该算法可以实时准确的检测出运动目标。     

Video object inpainting: a scale-robust method

Abstract

Video inpainting is the process of reconstructing damaged regions of corrupted frames. In this research, we raise a few issues in existing video inpainting systems. They are usually not robust to the change in the object scale and cannot handle large missing regions behind the moving object. In this attempt, we will address the above issues as following: first, we extract moving objects from the background and construct two mosaic images for each object, a small mosaic and a large mosaic image. The small mosaic is used to detect the amount of scale changes in the moving objects and the large one is used to inpaint partially or completely corrupted objects. We next place the inpainted moving foreground in its location and rescale the objects to their original scale. Finally, we combine the inpainted moving foreground and the background to obtain the corrected video. To speed up the process, we have utilised a multi-resolution approach so that the patch are initially matched in a coarse resolution and later are refined in a fine resolution. The results confirm the robustness of our method in handling the scale change of moving objects and large missing regions.     

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.     

基于Harris与Sift算法的图像匹配方法

采用 Harris 角点检测算法进行图像特征检测, 采用 Sift 算法中的特征描述方法进行图像特征描述, 之后将图像特征点划分为多对多匹配对, 根据特征描述值的支持强度不同建立精确的一对一匹配关系. 该算法有效地避免了图像特征分布均匀时的 Sift 匹配效率较低的问题.     

Glioma brain tumor detection and segmentation using weighting random forest classifier with optimized ant colony features

The uncontrolled growth of cells in brain regions leads to the tumor regions and these abnormal tumor regions are scanned by magnetic resonance imaging (MRI) technique as an image. This paper proposes random forest classifier based Glioma brain tumor detection and segmentation methodology using feature optimization technique. The texture features are derived from brain MRI image and these derived feature set are now optimized by ant colony optimization algorithm. These optimized set of features are trained and classified using random forest classification method. This classifier classifies the brain MRI image into Glioma or non-Glioma image based on the optimized set of features. Furthermore, energy-based segmentation method is applied on the classified Glioma image for segmenting the tumor regions. The proposed methodology for Glioma brain tumor stated in this paper achieves 97.7% of sensitivity, 96.5% of specificity, and 98.01% of accuracy.     

A content-based image retrieval system based on object-moment feature

The last decade has witnessed great interest in research on content-based image retrieval (CBIR). In 2009, Lin et al. proposed a smart CBIR system based on colour and texture feature. Their system has a high detection rate except the cases where image objects have similar shapes. To enhance the detection rate a shape-based image feature called object-moment is proposed in this paper. Object-moment uses the moment of force to compute the object edge feature by calculating the distance from each edge pixel to the axis, and adding them up as a feature. Besides, we integrate the colour features (NSOM, CSOM) and the texture features (CCM, DBPSP) to enhance image detection rate and simplify computation of image retrieval. A series of analyses and comparisons are performed in our experiments to demonstrate that our proposed method improves the retrieval accuracy significantly.     

Hybrid retinal image registration using phase correlation

Abstract

This paper deals with registration of retinal images, which were taken by high-resolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps — global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1·13 and 0·93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus pairs is presented.