Image Segmentation of Cattle Muzzle Using Region Merging Statistical Technic

A Landsat image of the multispectral scanner system covering an area lying between the Aqabah Gulf and the southern margin of the Dead Sea was analyzed by digital image processing techniques to delineate various geological and structural features of southwest Jordan area. Two major techniques in digital image processing were employed. They are preprocessing and enhancement, and their constituent treatment processes. Types of lithology, lineaments and topographic contrasts of southwest Jordan were used as test criteria. Results of comparison indicate that the combination of images processed by first principal component, second principal component and filtered first principal component as assigned to the hue, saturation and intensity system coordinates, respectively, provided better results than products of other digital techniques. Such good results enable geologists to map major lithologies, lineaments and other structural features effectively, as well as to assess topographic variations.

Diversity on durian varieties makes it difficult to distinguish between durian varieties. In addition, some durian varieties also have similarities which further complicate the classification process, and are known as typical tropical fruits, these fruits are native to Southeast Asia and have been introduced throughout the world. The ability to recognize objects is needed by humans. Recognition can facilitate human daily activities. Pattern recognition is often applied to a variety of objects, one of which is pattern recognition on fruit. There is some limitations of human memory in remembering object features. Based on this problem, research was conducted to identify fruit plants based on its features using digital image processing techniques, Learning Vector Quantization (LVQ) algorithm and Gray Level Co-occurrence Matrix (GLCM). Each type of plant has different shapes, colors, and textures; this is what makes the durian unique to other durians. The program was created using Microsoft Visual C # 2010 software. The test results achieved an 89% success rate in recognizing fruit plants based on the fruit.

At present, pattern recognition technology has been widely used in the fields of objects, faces, fingerprints, military target recognition, etc. However, pattern recognition method still has obvious shortcomings when applied to the above fields. It is currently restricted to the use of image information for identification. When the image features of the research object are highly similar, the accuracy of pattern recognition is low and cannot meet the actual application requirements. For example, in the case of mixed true and false targets, it is difficult to obtain satisfactory recognition results using only image information. Aiming at the above problems, a pattern recognition method integrating image information and spectral information is proposed in this paper. Firstly, the image recognition model based on the convolutional neural network model is built to identify object categories based on the semantic features of objects and obtain preliminary recognition results. Then, on the basis of the preliminary recognition results, the measured spectral data of the object (spectrum range 400-1 000 nm, spectral resolution 2 nm) is used to perform true and fake identification of the object based on the back propagation (BP) neural network model. The principle of true and false recognition is that the true and false targets are different in material, causing significant difference in their hyperspectral information. Finally, recognition results are obtained. In order to verify the accuracy of the proposed method, true and fake apples and grapes are used as experimental subjects and the result is that:The recognition accuracy obtained by using only image information is 38.50%, and the recognition accuracy obtained by using only spectral information is 63.00%, however, the recognition accuracy obtained by the method proposed in this paper is 95.00%. Compared with the existing pattern recognition method without spectral information participation, the pattern recognition method using image information and spectral information proposed in this paper improves the pattern recognition accuracy under the mixed condition of true and false targets, and can be widely applied to object recognition, face recognition, fingerprint recognition, military target recognition and other fields.

<p>Pattern recognition has over past decades become a fast growing area of chemometrics. Accurate, user-friendly, and fast pattern recognition methods are desired to accommodate the increased capacity of automated instruments to obtain large-scale data under complex circumstances. It has found significant applications in diverse fields such as environmental monitoring and biomedical diagnostics. In this dissertation, the capabilities of pattern recognition methods in case studies related to environmental remote sensing and biomedical sensing are investigated.</p> <p>For remote sensing applications, two types of airborne spectroscopic data, passive Fourier transform infrared (FTIR) and gamma-ray, are subject to analysis in order to develop automated classifiers for either ammonia vapor or the radioisotope cesium-137 in the open-air. Support vector machine (SVM) classification is the primary pattern recognition method used in this work. In order to overcome the limitation of available representative patterns associated with airborne data, and provide sufficient patterns presenting the analyte-active class for use in the training set, a spectral simulation protocol is employed to generate abundant patterns bearing both the signature of the target analyte and the background spectral profile. Signal processing procedures including segment selection and digital filtering are further used to extract the information most relevant to the target analyte out the acquired raw data. Also, to ease the computational demand from the SVM, an alternative pattern recognition method, piecewise linear discriminant analysis (PLDA) is applied to optimize signal processing conditions for final SVM classification. Process control techniques are applied to the SVM score profiles of prediction sets to improve pattern recognition performance by incorporating probabilities associated with every SVM score. Ammonia classifiers developed from this methodology result in classification performance with high sensitivity and selectivity, and the cesium-137 classifiers developed from the same concepts exhibit excellent sensitivity to test data with very low signal strengths. Under the case of ammonia classification, the relationship between the concentration profile of the active patterns in the training set and the limit of detection of the corresponding classifier is investigated. Classifiers built to detect low concentrations of ammonia are developed and tested through this work.</p> <p>For a glucose sensing application, studies are conducted to provide sound performance diagnostics for an established calibration model for glucose from near infrared spectroscopic data. Six-component aqueous matrixes of glucose in the presence of five other interfering species, all spanning physiological levels, serve as samples to be analyzed. A novel residual modeling protocol is proposed to retrieve the residual glucose concentrations, the concentration not being predicted by the calibration model, from the residual spectra, the portion of the raw spectra not being used by the calibration model. The recovered glucose concentration from the residual modeling can be used as a means, combined with process control techniques, to evaluate the performance of the established calibration model. Several modeling techniques are used for residual modeling, including PLS, support vector regression (SVR), a hybrid method, PLS-aided SVR, and an amplified version of the hybrid, amplified PLS-aided SVR. Through this work, a calibration updating strategy is developed which provides an effective way to monitor the established calibration model.</p>

This paper presents a method for dynamic pattern recognition and classification of one dangerous caterpillar species to allow for its control in maize crops. The use of dynamic pattern recognition supports the identification of patterns in digital image data that change over time. In fact, identifying fall armyworms (Spodoptera frugiperda) is critical in maize production, i.e., in all of its growth stages. For such pest control, traditional agricultural practices are still dependent on human visual effort, resulting in significant losses and negative impacts on maize production, food security, and the economy. Such a developed method is based on the integration of digital image processing, multivariate statistics, and machine learning techniques. We used a supervised machine learning algorithm that classifies data by finding an optimal hyperplane that maximizes the distance between each class of caterpillar with different lengths in N-dimensional spaces. Results show the method’s efficiency, effectiveness, and suitability to support decision making for this customized control context.

We have been implemented simple statistical pattern recognition methods for harmful gases classification using gas sensors array fabricated by MEMS (Micro Electro Mechanical System) technology. The performance of pattern recognition method as a gas classifier is highly dependent on the choice of pre-processing techniques for sensor and sensors array signals and optimal classification algorithms among the various classification techniques. We carried out pre-processing for each sensor's signal as well as sensors array signals to extract features for each gas. We adapted simple statistical pattern recognition algorithms, which were PCA (Principal Component Analysis) for visualization of patterns clustering and MLR (Multi-Linear Regression) for real-time system implementation, to classify harmful gases. Experimental results of adapted pattern recognition methods with pre-processing techniques have been shown good clustering performance and expected easy implementation for real-time sensing system.

The morphological characteristics of brick-concrete recycled coarse aggregate based on the digital image processing technique

The present report is devoted to the study of distinct ionization waves in terms of temporally-, spatially-, and wavelength-resolved analyses. The study is based on the technique of two-dimension fast imaging. However, appropriately selected ultraviolet to near infrared optical filters are employed to capture the propagation of specific species and digital image processing techniques are applied to explore the recorded snapshots. N2(SPS), (FNS), He I, OH(A–X), and O I, i.e., emissive neutral and ionic species, are investigated. On the other hand, the propagation of the NO γ species is studied by means of laser-induced fluorescence spectroscopy, since the light intensity due to spontaneous emission of this species was not readily detectable. Digital image processing techniques are also applied for the NO γ case. The crucial role of the above species in fields like plasma biomedicine and material processing is extensively recognized, and the present work: (i) provides gathered information on the propagation of these species within the atmospheric air; and (ii) introduces image processing algorithms to extract information which otherwise would remain hidden or uncorrelated with other plasma parameters. The present results unveil specific emission patterns due to the propagation of the N2(SPS), (FNS), He I, OH(A–X), and O I species. The intensity patterns consist of a first peak located in the vicinity of the reactor orifice, a second peak moving away from the reactor orifice, and a continuum which couples the two peaks. However, the detailed features of each pattern depend on the type of species considered. The fluorescence of the NO γ species also suggests the division of the area downstream of the reactor orifice into two regions where distinct ionization-excitation effects take place. Propagation speeds of the species up to about 2 × 105 m s−1 were measured. Finally, qualitative correlation between the species propagation (as it is pronounced by the emission patterns) and the local electric field (as it was numerically calculated in a similar setup) is demonstrated.

Kinetic data and mechanisms of the thermal degradation of an epoxy/amine system were investigated by dynamic thermogravimetry in a nitrogen atmosphere over the temperature range 25°C-500°C and at a constant heating rate of 10°C/min. One sample without metallic filler and three composites with 30% of various metallic fillers (Zn. Cu and Zn Cu alloy) were selected. The thermogravimetric curves were analysed by digital image processing techniques. The kinetic data and the mechanisms were evaluated according to the methods of Freeman and Carroll, Schlomilch. and Krevelen el al. The study showed: (a) a high correlation among the kinetic data and also among the reaction mechanisms: (b) a decrease in the activation energy of the thermal degradation of the epoxy amine materials in the presence of metallic fillers: (c) the material with Zn/Cu alloy had the lowest activation energy in comparison to those of the respective pure metals: and (d) high reproducibility and reliability of the results obtained by the digital technique used.

Neurotransmitters (NTs) are substances in the brain which are responsible for the transmission of neurological impulses. Changes in their concentrations are associated with numerous behavioral and physiological processes and neurological disorders. As opposed to the traditional chromatographic and capillary electrophoresis, using electrochemical sensors is a fast and inexpensive way to determine concentrations of NTs. In this study we measure the combination of dopamine (DA) and serotonin (SE) with glassy carbon electrodes and differential pulse voltammetry. The major challenge using this method is to differentiate between different NTs, since the signal obtained from the electrode represents the interactive effect of both NTs present. We address this problem through methods of pattern recognition which relate the voltammetric measurements provided by the sensor to the concentration of individual NTs. Two methods of pattern recognition were applied (PCR and PLS-regression). The best rates of correct classification for the validation sets ranged at 42-62% (DA) and 33-50% (SE). When the ranges for correct prediction were extended to include one level above and below the true concentration level, the rates values ranged at 81-91% (DA) and 91-100%(SE). These findings suggest that pattern recognition can be used to model the interaction between different neurotransmitters to predict actual concentrations of neurotransmitters using voltammetry.

This study proposes a diagnosis system for liver masses based on the improved radial basis function (RBF) neural networks. In this article, RBF networks are improved by sigmoid function and the growing and pruning algorithm. The proposed improved RBF networks adopt the sigmoid function as their kernel due to its increased flexibility over the Gaussian kernel. Furthermore, the growing and pruning algorithm is used to adjust the network size dynamically according to the neuron's significance. This investigation formulates discriminating among cysts, hepatoma, cavernous hemangioma, and normal tissue as a supervised learning problem. The current work calculates several texture and gray-level features derived from regions of interest as input in the proposed classifier. Receiver operating characteristic (ROC) curves evaluate the diagnosis performance, and demonstrate the proposed method's good performance.

Early warning of floods is an essential part of disaster management. Various automatic detectors have been developed in flood mitigation, including cameras. But reliability and accuracy have not been improved. Besides, the use of monitoring devices has been employed to monitor water levels in various water building facilities. The early warning flood detector was carried out with a sensor camera using an orange ball that floats near the water level gauge in a bounding box. This approach uses the integration of computer vision and image processing, namely digital image processing techniques, with Sobel Canny edge detection (SCED) algorithms to detect quickly and accurately water levels in real-time. After the water level is measured, a flood detection process is carried out based on the specified water level. According to the results of experiments in the laboratory, it has been shown that the proposed approach can detect objects accurately and fast in real-time. Besides, from the water level detection experiment, good results were obtained. Therefore, the object detection system and water level can be used as an efficient and accurate early detection system for flood disasters.

In this paper, a non-destructive and efficient method for identifying gemstones of the same species based on Raman spectroscopy and pattern recognition algorithms was developed. Tianhuang stones from different origins (Shoushan (SS), Changhua (CH), and Laos (LA)) with similar composition and structure were investigated and analyzed. Raman spectra were collected by a self-developed portable Raman spectrometer. Combined with pattern recognition methods, the subtle differences between the three types of Tianhuang stones were comprehensively analyzed. Principal component analysis–latent Dirichlet allocation was used to predict the feasibility of distinguishing SS, CH, and LA Tianhuang stones by Raman spectra. Random forest analysis method was applied to establish SS/CH and SS/LA models to distinguish SS from CH and LA. The selection of characteristic variables and determination of the number of growing trees was discussed. Also, the accuracy, sensitivity, and specificity of the two models were calculated. The potential of this method for rapid and non-destructive identification of Tianhuang stones was proved. The feasibility and effectiveness of Raman spectroscopy combined with the pattern recognition method in identifying gemstones of the same species with similar composition were proved.

Developments in optical experimental techniques have helped in elucidating how blood flows through microvessels. Although initial developments were encouraging, studies on the flow properties of blood in microcirculation have been limited by several technical factors, such as poor spatial resolution and difficulty obtaining quantitative detailed measurements at such small scales. Recent advances in computing, microscopy, and digital image processing techniques have made it possible to combine a particle tracking velocimetry (PTV) system with a confocal microscope. We document the development of a confocal micro-PTV measurement system for capturing the dynamic flow behavior of red blood cells (RBCs) in concentrated suspensions. Measurements were performed at several depths through 100-mum glass capillaries. The confocal micro-PTV system was able to detect both translational and rotational motions of individual RBCs flowing in concentrated suspensions. Our results provide evidence that RBCs in dilute suspensions (3% hematocrit) tended to follow approximately linear trajectories, whereas RBCs in concentrated suspensions (20% hematocrit) exhibited transversal displacements of about 2% from the original path. Direct and quantitative measurements indicated that the plasma layer appeared to enhance the fluctuations in RBC trajectories owing to decreased obstruction in transversal movements caused by other RBCs. Using optical sectioning and subsequent image contrast and resolution enhancement, the system provides previously unobtainable information on the motion of RBCs, including the trajectories of two or more RBCs interacting in the same focal plane and RBC dispersion coefficients in different focal planes.

Bone feature analysis using image processing techniques