Computer Vision-Based Non-Magnetic Object Detection on Moving Conveyors in Steel Industry through Differential Techniques and Performance Evaluation

Intelligent process control technology in various manufacturing industries is important. Vision-based non-magnetic object detection on moving conveyor in the steel industry will play a vital role for intelligent processes and raw material handling. This chapter presents an approach for a vision-based system that performs the detection of non-magnetic objects on raw material moving conveyor in a secondary steel-making industry. At single camera level, a vision-based differential algorithm is applied to recognize an object. Image pixels-based differential techniques, optical flow, and motion-based segmentations are used for traffic parameters extraction; the proposed approach extends those futures into industrial applications. The authors implement a smart control system, since they can save the energy and control unnecessary breakdowns in a robust manner. The technique developed for non-magnetic object detection has a single static background. Establishing background and background subtraction from continuous video input frames forms the basis. Detection of non-magnetic materials, which are moving with raw materials, and taking immediate action at the same stage as the material handling system will avoid the breakdowns or power wastage. The authors achieve accuracy up to 95% with the computational time of not more than 1.5 seconds for complete system execution.

Automated Ripeness Assessment System of Tomatoes Using PCA and SVM Techniques

One of the prime factors in ensuring a consistent marketing of crops is product quality, and the process of determining ripeness stages is a very important issue in the industry of (fruits and vegetables) production, since ripeness is the main quality indicator from the customers' perspective. To ensure optimum yield of high quality products, an objective and accurate ripeness assessment of agricultural crops is important. This chapter discusses the problem of determining different ripeness stages of tomato and presents a content-based image classification approach to automate the ripeness assessment process of tomato via examining and classifying the different ripeness stages as a solution for this problem. It introduces a survey about resent research work related to monitoring and classification of maturity stages for fruits/vegetables and provides the core concepts of color features, SVM, and PCA algorithms. Then it describes the proposed approach for solving the problem of determining different ripeness stages of tomatoes. The proposed approach consists of three phases, namely pre-processing, feature extraction, and classification phase. The classification process depends totally on color features (colored histogram and color moments), since the surface color of a tomato is the most important characteristic to observe ripeness. This approach uses Principal Components Analysis (PCA) and Support Vector Machine (SVM) algorithms for feature extraction and classification, respectively.

Automatic Fruit Disease Classification Using Images

Diseases in fruit cause devastating problems in economic losses and production in the agricultural industry worldwide. In this chapter, a method to detect and classify fruit diseases automatically is proposed and experimentally validated. The image processing-based proposed approach is composed of the following main steps: in the first step K-Means clustering technique is used for the defect segmentation, in the second step some color and texture features are extracted from the segmented defected part, and finally diseases are classified into one of the classes by using a multi-class Support Vector Machine. The authors have considered diseases of apple as a test case and evaluated the approach for three types of apple diseases, namely apple scab, apple blotch, and apple rot, along with normal apples. The experimental results express that the proposed solution can significantly support accurate detection and automatic classification of fruit diseases. The classification accuracy for the proposed approach is achieved up to 93% using textural information and multi-class support vector machine.

Evaluating an Evolutionary Particle Swarm Optimization for Fast Fuzzy C-Means Clustering on Liver CT Images

An Evolutionary Particle Swarm Optimization based on the Fractional Order Darwinian method for optimizing a Fast Fuzzy C-Means algorithm is proposed. This chapter aims at enhancing the performance of Fast Fuzzy C-Means, both in terms of the overall solution and speed. To that end, the concept of fractional calculus is used to control the convergence rate of particles, wherein each one of them represents a set of cluster centers. The proposed solution, denoted as FODPSO-FFCM, is applied on liver CT images, and compared with Fast Fuzzy C-Means and PSOFFCM, using Jaccard Index and Dice Coefficient. The computational efficiency is achieved by using the histogram of the image intensities during the clustering process instead of the raw image data. The experimental results based on the Analysis of Variance (ANOVA) technique and multiple pair-wise comparison show that the proposed algorithm is fast, accurate, and less time consuming.

Fingers' Angle Calculation Using Level-Set Method

In the current age, use of natural communication in human-computer interaction is a known and well-installed thought. Hand gesture recognition and gesture-based applications have gained a significant amount of popularity amongst people all over the world. They have a number of applications ranging from security to entertainment. These applications generally are real time applications and need fast, accurate communication with machines. On the other end, gesture-based communications have few limitations, but bent finger information is not provided in vision-based techniques. In this chapter, a novel method for fingertip detection and for angle calculation of both hands' bent fingers is discussed. Angle calculation has been done before with sensor-based gloves/devices. This study has been conducted in the context of natural computing for calculating angles without using any wired equipment, colors, marker, or any device. The pre-processing and segmentation of the region of interest is performed in a HSV color space and a binary format, respectively. Fingertips are detected using level-set method and angles are calculated using geometrical analysis. This technique requires no training for the system to perform the task.

Detecting Corner Features of Planar Objects

Corner points or features determine significant geometrical locations of the digital images. They provide important clues for shape representation and analysis. Corner points represent important features of an object that may be useful at subsequent levels of processing. If the corner points are identified properly, a shape can be represented in an efficient and compact way with sufficient accuracy in many shape analysis problem. This chapter reviews some well referred algorithms in the literature together with empirical study. Users can easily pick one that may prove to be superior from all aspects for their applications and requirements.

An Efficient System for Blocking Pornography Websites

The Internet is a powerful source of information. However, some of the information that is available on the Internet cannot be shown to every type of public. For instance, pornography is not desirable to be shown to children; pornography is the most harmful content affecting child safety and causing many destructive side effects. A content filter is one of more pieces of software that work together to prevent users from viewing material found on the Internet. In this chapter, the authors present an efficient content-based software system for detecting and filtering pornography images in Web pages. The proposed system runs online in the background of Internet Explorer (IE) for the purpose of restricting access to pornography Web pages. Skin and face detection techniques are the main components of the proposed system. Because the proposed filter works online, the authors propose two fasting techniques that can be used to speed up the filtering system. The results obtained using the proposed system are compared with four commercial filtering programs. The success rate of the proposed filtering system is better than the considered filtering programs.

Magnitude and Phase of Discriminative Orthogonal Radial Moments for Face Recognition

It is well known that the careful selection of a set of features, with higher discrimination competence, may increase recognition performance. In general, the magnitude coefficients of some selected orders of ZMs and PZMs have been used as invariant image features. The authors have used a statistical method to estimate the discrimination strength of all the coefficients of ZMs and PZMs. For classification, only the coefficients with estimated higher discrimination strength are selected and are used in the feature vector. The performance of these selected Discriminative ZMs (DZMs) and Discriminative PZMs (DPZMs) features are compared to that of their corresponding conventional approaches on YALE, ORL, and FERET databases against illumination, expression, scale, and pose variations. In this chapter, an extension to these DZMs and DPZMs is presented by exploring the use of phase information along with the magnitude coefficients of these approaches. As the phase coefficients are computed in parallel to the magnitude, no additional time is spent on their computation. Further, DZMs and DPZMs are also combined with PCA and FLD. It is observed from the exhaustive experimentation that with the inclusion of phase features the recognition rate is improved by 2-8%, at reduced dimensions and with less computational complexity, than that of using the successive ZMs and PZMs features.

Use of Bi-Camera and Fusion of Pairwise Real Time Citrus Fruit Image for Classification Application

In this chapter, the use of two images, the near infrared image and the color image, from a bi-camera machine vision system is investigated to improve the detection of the citrus fruits in the image. The application has covered the design of the bi-camera vision system to align two CCD cameras, the online acquisition of the citrus fruit tree image, and the fusion of two aligned images. In the system, two cameras have been registered with alignment to ensure the fusion of two images. A fusion method has been developed based on the Multiscale Decomposition Analysis (MSD) with a Discrete Wavelet Transform (DWT) application for the two dimensional signal. In the fusion process, two image quality issues have been addressed. One is the detail noise from the background, which is bounded with the envelope spectra and with similar spectra to orange citrus fruit and spatial variance property. The second is the enhancement of the fundamental envelope spectra using two source images. With level of MSD estimated, the noise is reduced by zeroing the high pass coefficients in DWT while the fundamental envelope spectra from the color image are enhanced by an arithmetic pixel level fusion rule. To evaluate the significant improvement of the image quality, some major classification methods are applied to compare the classified results from the fused image with the results from the types of color image. The misclassification error is measured by the empirical type errors using the manual segmentation reference image.

Online User Interaction Traits in Web-Based Social Biometrics

During the Internet era, millions of users are using Web-based Social Networking Sites (SNSs) such as MySpace, Facebook, and Twitter for communication needs. Social networking platforms are now considered a source of big data because of real-time activities of a large number of users. In addition to idiosyncratic personal characteristics, web-based social data may include person-to-person communication, profiles, patterns, and spatio-temporal information. However, analysis of social interaction-based data has not been studied from the perspective of person identification. In this chapter, the authors introduce for the first time the concept of using interaction-based features from online social networking platforms as a novel biometric. They introduce the concept of social behavioral biometric from SNSs to aid the identification process. Analysis of these novel biometric features and their potential use in various security and authentication applications are also presented. Such applications would pave the way for new directions in biometric research.