Vertical Projection Research Articles

Weed detection using image processing under different illumination for site-specific areas spraying

Large area bold type spraying of chemical herbicide is not only a waste of herbicides and labor, but also leads to environmental pollution and food quality problems. Traditional methods have the problems of high light and sample quality etc requirements. Therefore, accurately identifying weeds and precisely spraying are important strategies for promoting agricultural sustainable development. To avoid the influence of different illumination on images, this paper adopts the color model and then proposes component to gray images; the vertical projection method and the linear scanning method are combined to quickly identify the center line of the crop rows; the classic Weeds Infestation Rate (WIR) is modified to decrease the computational complexity and the improved horizontal scanning method is taken to calculate within cells; finally, Modified Weeds Infestation Rate (MWIR) is used to realize real-time decision through the minimum error ratio of Bayesian decision under normal distribution. The experimental results show that the accuracy of this algorithm is 92.5%, which exceeds the BP algorithm and SVM algorithm.

다중퍼셉트론을 이용한 자동차 번호판의 최적 입출력 노드의 비율 결정에 관한 연구

The Car License Plate Recognition(: CLPR) is required in searching the hit-and-run car, measuring the traffic density, investigating the traffic accidents as well as in pursuing vehicle crimes according to the increasing in number of vehicles. The captured images on the real environment of the CLPR is contaminated not only by snow and rain, illumination changes, but also by the geometrical distortion due to the pose changes between camera and car at the moment of image capturing. We propose homographic transformation and intensity histogram of vertical image projection so as to transform the distorted input to the original image and cluster the character and number, respectively. Especially, in this paper, the Multilayer Perceptron Algorithm(: MLP) in the CLPR is used to not only recognize the charcters and car license plate, but also determine the optimized ratio among the number of input, hidden and output layers by the real experimental result.

The effects of pre-existing discontinuities on the surface expression of normal faults: Insights from wet-clay analog modeling

We use wet-clay analog models to investigate how pre-existing discontinuities (i.e. structures inherited from previous tectonic phases) affect the evolution of a normal fault at the Earth's surface. To this end we first perform a series of three reference experiments driven by a 45° dipping master fault unaffected by pre-existing discontinuities to generate a mechanically isotropic learning set of models. We then replicate the experiment six times introducing a 60°-dipping precut in the clay cake, each time with a different attitude and orientation with respect to an initially-blind, 45°-dipping, master normal fault. In all experiments the precut intersects the vertical projection of the master fault halfway between the center and the right-hand lateral tip. All other conditions are identical for all seven models. By comparing the results obtained from the mechanically isotropic experiments with results from experiments with precuts we find that the surface evolution of the normal fault varies depending on the precut orientation. In most cases the parameters of newly-forming faults are strongly influenced. The largest influence is exerted by synthetic and antithetic discontinuities trending respectively at 30° and 45° from the strike of the master fault, whereas a synthetic discontinuity at 60° and an antithetic discontinuity at 30° show moderate influence. Little influence is exerted by a synthetic discontinuity at 45° and an antithetic discontinuity at 60° from the strike of the master fault. We provide a ranking chart to assess fault-to-discontinuity interactions with respect to essential surface fault descriptors, such as segmentation, vertical-displacement profile, maximum displacement, and length, often used as proxies to infer fault properties at depth. Considering a single descriptor, the amount of deviation induced by different precuts varies from case to case in a rather unpredictable fashion. Multiple observables should be taken into consideration when analyzing normal faults evolving next to pre-existing discontinuities.

3D depth image analysis for indoor fall detection of elderly people

This paper presents a new fall detection method of elderly people in a room environment based on shape analysis of 3D depth images captured by a Kinect sensor. Depth images are pre-processed by a median filter both for background and target. The silhouette of moving individual in depth images is achieved by a subtraction method for background frames. The depth images are converted to disparity map, which is obtained by the horizontal and vertical projection histogram statistics. The initial floor plane information is obtained by V disparity map, and the floor plane equation is estimated by the least square method. Shape information of human subject in depth images is analyzed by a set of moment functions. Coefficients of ellipses are calculated to determine the direction of individual. The centroids of the human body are calculated and the angle between the human body and the floor plane is calculated. When both the distance from the centroids of the human body to the floor plane and the angle between the human body and the floor plane are lower than some thresholds, fall incident will be detected. Experiments with different falling direction are performed. Experimental results show that the proposed method can detect fall incidents effectively.

The effect of weight-bearing asymmetry on dynamic postural stability in healthy young individuals

BackgroundIn people with lateralized disorders, such as stroke, Weight-Bearing Asymmetry (WBA) is common. It is associated with postural instability, however, WBA is one of several abnormalities that may affect postural stability in these disorders. Therefore, we investigated the isolated effects of WBA on dynamic postural stability in healthy individuals. MethodsTen young participants were subjected to multidirectional stance perturbations by support surface translations at three levels of WBA (0, 10 and 20% of body weight unloading of one leg). The stepping threshold was determined iteratively for each condition and in four perturbation directions (forward, backward, leftward and rightward). The stepping threshold was defined as the highest perturbation intensity recovered from with a feet-in-place response. The Margin of Stability (MOS) at the stepping threshold was defined as the smallest distance between the vertical projection of the Extrapolated Center of Mass (XCOM) and the edge of the base of support. ResultsWBA decreased the stepping threshold (stability decreased) for perturbations towards the loaded side (translations towards the unloaded side), whereas it increased stepping thresholds for perturbations towards the unloaded side. No significant effects of WBA were found on the MOS. WBA increased the frequency of stepping with the unloaded leg upon forward and backward perturbations. ConclusionWBA increased dynamic stability towards the unloaded leg following external balance perturbations and resulted in a greater probability of stepping with this leg. Future studies are needed to evaluate the functional significance of these WBA-related effects on postural stability in people with lateralized disorders.

An Improved Method for Handwritten Document Analysis Using Segmentation, Baseline Recognition and Writing Pressure Detection

Handwritten document analysis is a scientific technique for identifying and understanding the personality of a writer through the strokes and patterns revealed by writer's handwriting. This research proposed an off-line handwritten document analysis through segmentation, skew recognition and writing pressure detection for cursive handwritten document. The proposed segmentation method is based on modified horizontal and vertical projection that can segment the text lines and words even if the presence of overlapped and multi-skewed text lines. Proposed work also present orthogonal projection based baseline recognition and normalization method as well as writing pressure detection method that can predict the personality of a writer from the baseline and writing pressure. The proposed method was tested on more than 550 text images of IAM database and sample handwriting image which are written by the different writer on the different background. The proposed method also provides a comparative study of the details analysis of the proposed method with other existing methods.

Libyan Licenses Plate Recognition Using Template Matching Method

License plate recognition (LPR) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. The work presented in this paper aims to create a computer vision system capable of taking real-time input image from a static camera and identifying the license plate from extracted image. This problem is examined in two stages: First the license plate region detection and extraction from background and plate segmentation to sub-images, and second the character recognition stage. The method used for the license plate region detection is based on the assumption that the license plate area is a high concentration of smaller details, making it a region of high intensity of edges. The Sobel filter and their vertical and horizontal projections are used to identify the plate region. The result of testing this stage was an accuracy of 67.5%. The final stage of the LPR system is optical character recognition (OCR). The method adopted for this stage is based on template matching using correlation. Testing the performance of OCR resulted in an overall recognition rate of 87.76%.

A Two Fold Expert System for Yawning Detection

One of the prominent indicators of drowsiness is yawning. The main intention for a real-time application such as detecting the driver's yawning is that the response of the detector must be as quick as possible. A novel yawning detection system is proposed which is based on a two agent expert system. The features of the face have to be extracted to detect yawning in the driver's face. In the proposed system, as the first part of detection we use the face detection algorithm's skin detection part. The skin region is extracted. For all the skin region blocks detected, their boundaries are defined. Then segmented face is divided into two halves. The lower half of the face is considered for the mouth region extraction. The presence of yawning would be indicated by a black blob in the mouth region of the binary image. But, there may be multiple blobs present in the image which may be due to the presence non-skin like regions around the driver's face. So, identifying the exact position of the mouth and checking for its containment inside the face is necessary. The features extracted for yawning detection are the histogram values taken from the vertical projection of the lower part of the face.

Continuous Visible Query for Three-Dimensional Objects in Spatial Databases

Present research of visible query focuses on points and segments in two-dimensional space, while disfigurements occur during processing of visible query in three-dimensional space. In this paper, Continuous Visible Range Query Based on Control Point (CVRQ-CP) is proposed to solve the visible query in a 3D spatial database. Firstly, the horizontal angle (HA) and Vertical Projection Angle (VPA) for 3D objects in a spatial database were used in the visibility testing method. The HA and VPA in the processing of the continuous visible query created visibility changes, defining and confirming the control point. Finally, the algorithm of Continuous Visible Range Query Based on Control Point (CVRQ-CP) was proposed. Verified by experiments, the CVRQ-CP algorithm correctly deals with the visible query of 3D spatial objects. The CVRQ-CP algorithm has better superior accuracy over present visible queries in 3D spatial databases.

An Efficient Segmentation Algorithm for Handwritten Arabic Words

Segmentation is an essential step for many Arabic handwritten Text recognition systems. It has a direct impact on the efficiency of subsequent steps in the recognition process such as feature extraction and classification, which strongly affects overall recognition performance. This paper presents a novel algorithm for off-line handwritten Arabic word segmentation into sub-words. This approach is based on vertical projection and a novel algorithm taking into consideration the characteristics of Arabic script. The proposed method has been successfully tested on the IFN/ENIT database and the results show the effectiveness of our approach in segmenting and isolating sub-words efficiently.

Segmentation of Assamese Handwritten Characters based on Projection Profiles

The most important part of a character recognition system is segmenting the characters properly and selecting the best features from the characters. This paper describes a character segmentation method for an ANN based character recognition system which is used for recognition of optically scanned handwritten Assamese character. The segmentation of characters are done using horizontal and vertical projections of the hand written text document. For feature extraction the system extracts the geometric features of the characters which are consist of basic line types that are used in the formation of the character skeleton. The feature vector of the training set generated by this system is used to train the recognition system using ANN.

Anti-Forensics of JPEG Images using Interpolation

Segmentation of Arabic text is a major challenge that shall be addressed by any recognition system. The cursive nature of Arabic writing makes it necessary to handle the segmentation issue at various levels. Arabic text line can be viewed as a sequence of words which in turn can be viewed as a sequence of sub-words. Sub-words have the frequently encountered intrinsic property of sharing the same vertical space which makes vertical projection based segmentation technique inefficient. In this paper, the task of segmenting handwritten Arabic text at sub-word level is taken up. The proposed algorithm is based on pulling away the connected components to overcome the impossibility of separating them by vertical projection based approach. Graph theoretic modeling is proposed to solve the problem of connected component extraction. In the sequel, these components are subjected to thorough analysis in order to obtain the constituent sub-words where a sub-word may consist of many components. The proposed algorithm was tested using variety of handwritten Arabic samples taken from different databases and the results obtained are encouraging.

Interference and phase structure of the low-frequency vector-scalar field in shallow water for variable reception or transmission depths

Relations for calculating the amplitude and phase characteristics of sound pressure and orthogonal projections of the vibration velocity vector and phase gradient in shallow water have been derived. Dependences of the effective phase velocity of equivalent plane wave, orthogonal projections of the gradient of sound pressure phase, and projections of the vibration velocity vector on the transmitter (or receiver) depth are calculated for different frequencies and location depths of receivers (and transmitters). It is found that the horizontal projections of the vibration velocity vector and phase gradient satisfy the reciprocity principle whereas their vertical projections do not obey this principle. Therefore, the characteristics of the vertical components must be studied independently with variation in their transmission or reception depth. It is shown that, for low frequencies and variable transmitter or receiver depth, the effective phase velocities in interference maxima exceed generally the speed of sound in water by 5-15% or even more. Some recommendations on the use of sound field characteristics in the regions of maximum sound pressure for solving problems of direction finding and signal detection are formulated. The behavior of the characteristics of arrival angles of equivalent plane wave with variation in the transmission or reception depth are investigated.

Effects of Destabilization of Visual Environment Perception on the Maintenance of Upright Stance by Humans on Different Support Surfaces

We compared characteristics of the maintenance of human upright stance under conditions of a real visual environment (VE) and “immersion” into a virtual visual environment (VVE). The foreground of the latter corresponded to the window in the room, while the background was a view of the aqueduct with the adjacent terrain. Destabilization of the VVE was created by “coupling” of the foreground position with oscillations of the subject’s body within the sagittal plane. We measured elementary variables calculated according to the trajectory of the center of feet pressure (CFP); these variables were: (i) displacement of the vertical projection of the center of gravity (CGv) and (ii) difference between the positions of the CFP and CGv (variables CGv and CFP – CGv). When standing on a rigid support surface, the root mean square (RMS) of the spectra of oscillations of both variables decreased in the case of an antiphase relation between displacements of the VE foreground with oscillations of the body and increased in the case of an inphase relation between these variables, as compared with the RMS in the maintenance of upright stance under conditions of an immobile VE (ImVE). Under conditions of the inphase relation, however, there were no dramatic disorders in the vertical stance; maximum oscillations of the body in this case did not exceed values typical of the upright stance with the eyes closed (EC). When the upright stance was maintained on a squeezable support, body oscillations increased significantly under all visual conditions, and the difference between the RMS of the CGv spectra obtained for the conditions of the inphase relation and EC became statistically significant. In the case of standing on a squeezable support, RMSs of the CFP – CGv variable at the antiphase relation of the VVE foreground were greater than those at the inphase relation. At the same time, the RMS of the CGv spectra were, vice versa, greater at the inphase relation. Thus, upon variation of the conditions for the vertical stance maintenance, the amplitude characteristics of elementary variables (CGv and CFP – CGv) determining the CFP on a support can vary in both a parallel and an independent manner. These variables can be controlled not only by coupled but also by independent (uncoupled) mechanisms controlling their amplitude/frequency parameters.

An Arabic Script Recognition System

A system for the recognition of machine printed Arabic script is proposed. The Arabic script is shared by three languages i.e., Arabic, Urdu and Farsi. The three languages have a descent amount of vocabulary in common, thus compounding the problems for identification. Therefore, in an ideal scenario not only the script has to be differentiated from other scripts but also the language of the script has to be recognized. The recognition process involves the segregation of Arabic scripted documents from Latin, Han and other scripted documents using horizontal and vertical projection profiles, and the identification of the language. Identification mainly involves extracting connected components, which are subjected to Principle Component Analysis (PCA) transformation for extracting uncorrelated features. Later the traditional K-Nearest Neighbours (KNN) algorithm is used for recognition. Experiments were carried out by varying the number of principal components and connected components to be extracted per document to find a combination of both that would give the optimal accuracy. An accuracy of 100% is achieved for connected components >=18 and Principal components equals to 15. This proposed system would play a vital role in automatic archiving of multilingual documents and the selection of the appropriate Arabic script in multi lingual Optical Character Recognition (OCR) systems.

IMAGE PROCESSING OF ANDROID-BASED PATROL ROBOT FEATURING AUTOMATIC LICENSE PLATE RECOGNITION

This work develops an Android-based robot featuring automatic license plate recognition and automatic license plate patrolling. The automatic license plate recognition feature combines 4 self-developed novel methods, Wiener deconvolution vertical edge enhancement, AdaBoost plus vertical-edge license plate detection, vertical edge projection histogram segmentation stain removal, and customized optical character recognition. Besides, the automatic license plate patrolling feature also integrates 3 novel methods, HL2-band rough license plate detection, orientated license plate approaching, and Ad-Hoc-based remote motion control. Implementation results show the license plate detection rate and recognition rate of the Android-based robot are over 99% and over 98%, respectively, under various scene conditions. Especially, the execution time of license plate recognition, including license plate detection, is only about 0.7 second per frame on the Android-based robot.

Compensatory mechanisms of balance to the scaling of arm-swing frequency

The present study investigated the contribution of the Hof (2007) mechanism 1 (M1-moving the center of pressure (COP) with respect to the vertical projection of the center of mass (COMTotal)); and mechanism 2 (M2-rotating the trunk and upper limbs around the COMTotal) to postural control and the stability of COP–COMTotal cophase as a function of lateral arm-swing frequency. Young adults were instructed to stand still on a force platform while alternating their arm swinging from above the head to the side of their thigh to create perturbations to postural control. Scaling the frequency of arm-swing (random step changes of 0.2Hz within a bandwidth of 0.2 to 1.6Hz) increased the SD of COP but decreased the SD of COMTotal. Increments in arm-swing frequency induced a progressive increase in M1 and decrease in M2 in terms of their relative contribution to postural stability. The cophase between COP and COMTotal became more tightly in-phase over increments of arm-swing frequency. These findings show an adaptive compensatory role of M1 and M2 within the stability of COP–COMTotal coupling in the regulation of human balance control.

Influence of a light tactile contact on vertical posture maintenance under the conditions of destabilization of visual environment

The influence of a light contact between index finger and a stationary external surface on the maintenance of upright posture in healthy subjects “immersed” in unstable virtual visual environment has been studied. Under these conditions, the subjects saw a screen with a visual scene consisting of a foreground and a background. In the foreground, there was a window of a room with the adjacent walls; in the background, there was an aqueduct with the adjacent terrain. The virtual visual environment was destabilized by setting inphase or antiphase couplings between the foreground and body oscillations. The analysis of upright posture maintenance was focused on the assessment of amplitude–frequency characteristics of two elementary variables calculated from the trajectories of the center of pressure of feet (CoP) in mediolateral and anteroposterior directions: the trajectory of vertical projection of the center of gravity (the CG variable) and the differences between the CoP and CG trajectories (the CoP-CG variable). Both in case of normal posture and the posture with a fingertip contact, the root mean square (RMS) values of the spectra of both variables were the lowest in motionless visual environment with antiphase coupling between the foreground and the body oscillations and the highest with inphase coupling and with eyes closed. In the cases with fingertip contact, the intensity of body oscillations in both directions was considerably lower; the influence of different visual conditions on RMS values of the spectra of both variables decreased. This effect was more significant for the CG variable. The frequency of body oscillations decreased as well. We observed the effect of tactile contact on the frequency of the spectra of both variables. The median frequencies of the spectra of the CoP-CG variable calculated from body oscillations in the anteroposterior and mediolateral directions increased under the conditions of tactile contact. On the contrary, the median frequencies of the spectra of the CG variable increased only for body oscillations in the mediolateral direction. Our results show that a light tactile contact (providing no mechanical support) significantly improves vertical posture maintenance, inter alia, under the conditions of destabilization of virtual visual environment. This improvement is provided by multidirectional and independent effects on the amplitude–frequency characteristics of elementary variables (CG and CoP-CG).

AVALIAÇÃO DO DESENVOLVIMENTO VEGETATIVO DE PEREIRAS ‘HOSUI’ E ‘ROCHA’ EM DIFERENTES ESPAÇAMENTOS NO SISTEMA DE CULTIVO ORGÂNICO

RESUMO O objetivo deste trabalho foi verificar a influência de diferentes espaçamentos de plantio sobre o crescimento vegetativo de pereiras das cvs. Rocha e Hosui, em sistema orgânico de produção. As mudas das pereiras ‘Rocha’ e ‘Hosui’ enxertadas sobre o marmeleiro ‘CP’ foram plantadas em setembro de 2009. Os espaçamentos utilizados foram: 1,0; 0,8; 0,6 e 0,4 m, entre plantas por 3,5 m entre linhas, equivalendo às densidades de plantio de 2.857; 3.571; 4.762 e 7.143 plantas ha-1, respectivamente. Por dois ciclos consecutivos - 2011/2012 e 2012/2013 -, referentes ao terceiro e ao quarto anos após o plantio, respectivamente, foram avaliadas as variáveis diâmetro detronco, diâmetro de ramos e número de ramos. No segundo ciclo, foram avaliados o volume de copa, a área foliar estimada, a cobertura do dossel e os teores de clorofila a, b e total. Considerando as variáveis: projeção vertical de área foliar estimada, volume de copa e diâmetro de tronco e ramos, para a cv. Hosui, observou-se maior vigor vegetativo em relação à cv. Rocha. A cv. Rocha apresentou redução dos teores de clorofila no menor espaçamento entre plantas, enquanto na cv. Hosui os teores de clorofila não variaram com o espaçamento. Ocorreu aumento da área foliar estimada em função do adensamento para as duas cultivares; para o volume de copa, porém, este efeito foi observado apenas para a cv. Hosui, e para o índice de cobertura de dossel, apenas para a cv. Rocha. O maior adensamento de plantio favoreceu as pereiras da cv. Hosui, proporcionando maior volume de copa por área de terreno, sem ocorrer redução dos teores foliares de clorofila, mas com aumento da cobertura do dossel. Para a cv. Rocha, no entanto, adensamentos maiores do que 4.700 plantas ha-1 parecem ser prejudiciais, visto promoverem redução dos teores foliares de clorofila, porém com maior cobertura do dossel, podendo indicar autossombreamento.

Estimating Subsurface Velocities from Surface Fields with Idealized Stratification

AbstractA previously published method by Wang et al. for predicting subsurface velocities and density from sea surface buoyancy and surface height is extended by incorporating analytical solutions to make the vertical projection. One solution employs exponential stratification and the second has a weakly stratified surface layer, approximating a mixed layer. The results are evaluated using fields from a numerical simulation of the North Atlantic. The simple exponential solution yields realistic subsurface density and vorticity fields to nearly 1000 m in depth. Including a mixed layer improves the response in the mixed layer itself and at high latitudes where the mixed layer is deeper. It is in the mixed layer that the surface quasigeostrophic approximation is most applicable. Below that the first baroclinic mode dominates, and that mode is well approximated by the analytical solution with exponential stratification.