Classification of MAG weld pool image based on moment invariants and fisher

In order to discover characteristics of various kinds of weld pool image and identify a single image, seven image features are extracted to describe the corresponding surface formation quality by the moment iavariants method. An image feature matrix is composed by the seven characteristics. Then the matrix is projected on a line through the Fisher criterion in order to entirely distinguish various kinds of image features. And finally, transforming a seven-dimensional problem into a one-dimensional problem has been done. Compared with the three kinds of samples included in the arc welding process and quality weld pool visual image database, the images are classified into the three kinds such as superior weld formation in the condition of optimal gas flow, poor weld formation image in the condition of insuffwient gas flow, inferior weld formation in the condition of too low gas flow. Experiments show that the Fisher classification method based on moment invariants can recognize various weld pool images effectively, and it achieves a correct recognizable rate of 100%.

Automatic Identification of Axis Orbit Based on Both Wavelet Moment Invariants and Neural Network

Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are introduced in detail. It gives simulation results of automatic identification for three typical axis orbits. It is proved that the method is effective and practicable.

AN EFFECTIVE IMAGE RETRIEVAL METHOD BASED ON KERNEL DENSITY ESTIMATION OF COLLAGE ERROR AND MOMENT INVARIANTS

In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The proposed method is called CHK (KDE of Collage error and Hu moment) and it is tested on the Vistex texture database with 640 natural images. Experimental results show that the Average Retrieval Rate (ARR) can reach into 78.18%, which demonstrates that the proposed method performs better than the one with parameters respectively as well as the commonly used histogram method both on retrieval rate and retrieval time.

A Normalization Method of Moment Invariants for 3D Objects on Different Manifolds

3D objects can be stored in computer of different describing ways, such as point set, polyline, polygonal surface and Euclidean distance map. Moment invariants of different orders may have the different magnitude. A method for normalizing moments of 3D objects is proposed, which can set the values of moments of different orders roughly in the same range and be applied to different 3D data formats universally. Then accurate computation of moments for several objects is presented and experiments show that this kind of normalization is very useful for moment invariants in 3D objects analysis and recognition.

Mosaic of Printed Circuit Board Image Based on Gaussian-Hermite Moment Invariants

Quality inspection of a PCB （Printed Circuit Board） always requires us to stitch some separated images into an integral one. However, during image acquisition, some environmental influences such as vibration, noise and illumination will cause image degradation. An efficient image mosaic method has been urgently required to obtain a high-quality PCB panorama. Hence, an image mosaic method based on Gaussian-Hermite moments is presented in this paper. The characteristic points in the neighborhood of a PCB are represented by Gaussian-Hermite moment in- variants. They are characterized by independence to translation or rotation transformations. Meanwhile, such feature representation shows better noise robustness. Experimental results show that the proposed method produces a qualified mosaic of PCB image.

Automated visual inspection of surface defects based on compound moment invariants and support vector machine

The traditional inspection methods are mostly based on manual inspection which is very likely to make erroneous judgments due to personal subjectivity or eye fatigue, and can＇t satisfy the accuracy. To overcome these difficulties, we develop a machine vision inspection system. We first compare several kinds of methods for feature extraction and classification, and then present a real-time automated visual inspection system for copper strips surface （CSS） defects based on compound moment invariants and support vector machine （SVM）. The proposed method first processes images collected by hardware system, and then extracts feature characteristics based on grayscale characteristics and morphologic characteristics （Hu and Zernike compound moment invariants）. Finally, we use SVM to classify the CSS defects. Furthermore, performance comparisons among SVM, back propagation （BP） and radial basis function （RBF） neural networks have been involved. Experimental results show that the proposed approach achieves an accuracy of 95.8% in detecting CSS defects.

Information Moment for Chinese Character Recognition

Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of information moments and demonstrate its invariance to translation,rotation and scaling.Also they perform the experiment in which information moments compared with moment invaiants for the effects of similar Chinese characters and font recognition.At last they show the recognition rate of 88% by information moments,with 70% by moment inariants.

Robust Image Watermarking Using LWT and Stochastic Gradient Firefly Algorithm

Watermarking of digital images is required in diversified applicationsranging from medical imaging to commercial images used over the web.Usually, the copyright information is embossed over the image in the form ofa logo at the corner or diagonal text in the background. However, this formof visible watermarking is not suitable for a large class of applications. In allsuch cases, a hidden watermark is embedded inside the original image as proofof ownership. A large number of techniques and algorithms are proposedby researchers for invisible watermarking. In this paper, we focus on issuesthat are critical for security aspects in the most common domains like digitalphotography copyrighting, online image stores, etc. The requirements of thisclass of application include robustness (resistance to attack), blindness (directextraction without original image), high embedding capacity, high Peak Signalto Noise Ratio (PSNR), and high Structural Similarity Matrix (SSIM). Mostof these requirements are conflicting, which means that an attempt to maximizeone requirement harms the other. In this paper, a blind type of imagewatermarking scheme is proposed using Lifting Wavelet Transform (LWT)as the baseline. Using this technique, custom binary watermarks in the formof a binary string can be embedded. Hu’s Invariant moments’ coefficientsare used as a key to extract the watermark. A Stochastic variant of theFirefly algorithm (FA) is used for the optimization of the technique. Undera prespecified size of embedding data, high PSNR and SSIM are obtainedusing the Stochastic Gradient variant of the Firefly technique. The simulationis done using Matrix Laboratory (MATLAB) tool and it is shown that theproposed technique outperforms the benchmark techniques of watermarkingconsidering PSNR and SSIM as quality metrics.

NEW APPROACH TO COPYRIGHT PROTECTION OF IMAGE AGAINST GEOMETRICAL ATTACKS

To protect the copyright of the image as well as the image quality, a kind of image zero-watermark method based on the Krawtchouk moment invariants and timestamp is proposed. A method is used to protect the image, in which features are drawn out from the image as the watermarking. The main steps of the method are presented. Firstly, some low-order moment invariants of the image are extracted. Secondly, the moment invariants and the key are registered to a fair third party to gain the timestamp. Finally, the timestamp can be used to prove who the real owner is. The processing method is simple, only with a few low-order moment invariants to be computed. Experimental results are obtained and compared with those of the method based on geometric moment invariants. Results show that the scheme can well withstand such geometrical attacks as rotating, scaling, cropping, combined attack, translating, removing lines, filtering, and JPEG lossy compression.

A reliable algorithm for image matching based on SIFT

A novel algorithm is presented to make the results of image matching more reliable and accurate based on SIFT (Scale Invariant Feature Transform). SIFT algorithm has been identified as the most resistant matching algorithm to common image deformations; however, if there are similar regions in images, SIFT algorithm still generates some analogical descriptors and provides many mismatches. This paper examines the local image descriptor used by SIFT and presents a new algorithm by integrating SIFT with two-dimensional moment invariants and disparity gradient to improve the matching results. In the new algorithm, decision tree is used, and the whole matching process is divided into three levels with different primitives. Matching points are considered as correct ones only when they satisfy all the three similarity measurements. Experiment results demonstrate that the new approach is more reliable and accurate.

Method to generate training samples for neural network used in target recognition

Training neural network to recognize targets needs a lot of samples.People usually get these samples in a non-systematic way,which can miss or overemphasize some target information.To improve this situation,a new method based on virtual model and invariant moments was proposed to generate training samples.The method was composed of the following steps：use computer and simulation software to build target object＇s virtual model and then simulate the environment,light condition,camera parameter,etc.;rotate the model by spin and nutation of inclination to get the image sequence by virtual camera;preprocess each image and transfer them into binary image;calculate the invariant moments for each image and get a vectors＇ sequence.The vectors＇ sequence which was proved to be complete became the training samples together with the target outputs.The simulated results showed that the proposed method could be used to recognize the real targets and improve the accuracy of target recognition effectively when the sampling interval was short enough and the circumstance simulation was close enough.

Modified Moment-based Image Watermarking Method Robust to Cropping Attack

Developing a watermarking method that is robust to cropping attack is a challenging task in image watermarking. The moment-based watermarking schemes show good robustness to common signal processing attacks and some geometric attacks but are sensitive to cropping attack. In this paper, we modify the moment-based approach to deal with cropping attack. Firstly, we find the probability density function （PDF） of the pixel value distribution from the original image. Secondly, we reshape and normalize the pdf of the pixel value distribution （PPVD） to form a two dimensional image. Then, the moment invariants are calculated from the PPVD image. Since PPVD is insensitive to cropping, the proposed method is robust to cropping attack. Besides, it also has high robustness against other common attacks. Theoretical analysis and experimental results demonstrate the effectiveness of the proposed method.

Smart Objects Identification System for Robotic Surveillance

Video surveillance is an active research topic in computer vision.In this paper,humans and cars identifcation technique suitable for real time video surveillance systems is presented.The technique we proposed includes background subtraction,foreground segmentation,shadow removal,feature extraction and classifcation.The feature extraction of the extracted foreground objects is done via a new set of afne moment invariants based on statistics method and these were used to identify human or car.When the partial occlusion occurs,although features of full body cannot be extracted,our proposed technique extracts the features of head shoulder.Our proposed technique can identify human by extracting the human head-shoulder up to 60%–70%occlusion.Thus,it has a better classifcation to solve the issue of the loss of property arising from human occluded easily in practical applications.The whole system works at approximately 16 29 fps and thus it is suitable for real-time applications.The accuracy for our proposed technique in identifying human is very good,which is 98.33%,while for cars identifcation,the accuracy is also good,which is 94.41%.The overall accuracy for our proposed technique in identifying human and car is at 98.04%.The experiment results show that this method is efective and has strong robustness.

Zero-bit watermarking resisting geometric attacks based on composite-chaos optimized SVR model

The problem to improve the performance of resisting geometric attacks in digital watermarking is addressed in this paper.Based on the optimized support vector regression（SVR）,a zero-bit watermarking algorithm is presented.The proposed algorithm encrypts the watermarking image by using composite chaos with large key space and capacity against prediction,which can strengthen the safety of the proposed algorithm.By using the relationship between Tchebichef moment invariants of detected image and watermarking characteristics,the SVR training model optimized by composite chaos enhances the ability of resisting geometric attacks.Performance analysis and simulations demonstrate that the proposed algorithm herein possesses better security and stronger robustness than some similar methods.

An Algorithm to Recognize the Target Object Contour Based on 2D Point Clouds by Laser-CCD-Scanning

For a vision measurement system consisted of laser-CCD scanning sensors, an algorithm is proposed to extract and recognize the target object contour. Firstly, the two-dimensional（2D） point cloud that is output by the integrated laser sensor is transformed into a binary image. Secondly, the potential target object contours are segmented and extracted based on the connected domain labeling and adaptive corner detection. Then, the target object contour is recognized by improved Hu invariant moments and BP neural network classifier. Finally, we extract the point data of the target object contour through the reverse transformation from a binary image to a 2D point cloud. The experimental results show that the average recognition rate is 98.5% and the average recognition time is 0.18 s per frame. This algorithm realizes the real-time tracking of the target object in the complex background and the condition of multi-moving objects.