Image Capture System Research Articles

A Tool for Interactive Data Visualization: Application to Over 10,000 Brain Imaging and Phantom MRI Data Sets.

In this paper we propose a web-based approach for quick visualization of big data from brain magnetic resonance imaging (MRI) scans using a combination of an automated image capture and processing system, nonlinear embedding, and interactive data visualization tools. We draw upon thousands of MRI scans captured via the COllaborative Imaging and Neuroinformatics Suite (COINS). We then interface the output of several analysis pipelines based on structural and functional data to a t-distributed stochastic neighbor embedding (t-SNE) algorithm which reduces the number of dimensions for each scan in the input data set to two dimensions while preserving the local structure of data sets. Finally, we interactively display the output of this approach via a web-page, based on data driven documents (D3) JavaScript library. Two distinct approaches were used to visualize the data. In the first approach, we computed multiple quality control (QC) values from pre-processed data, which were used as inputs to the t-SNE algorithm. This approach helps in assessing the quality of each data set relative to others. In the second case, computed variables of interest (e.g., brain volume or voxel values from segmented gray matter images) were used as inputs to the t-SNE algorithm. This approach helps in identifying interesting patterns in the data sets. We demonstrate these approaches using multiple examples from over 10,000 data sets including (1) quality control measures calculated from phantom data over time, (2) quality control data from human functional MRI data across various studies, scanners, sites, (3) volumetric and density measures from human structural MRI data across various studies, scanners and sites. Results from (1) and (2) show the potential of our approach to combine t-SNE data reduction with interactive color coding of variables of interest to quickly identify visually unique clusters of data (i.e., data sets with poor QC, clustering of data by site) quickly. Results from (3) demonstrate interesting patterns of gray matter and volume, and evaluate how they map onto variables including scanners, age, and gender. In sum, the proposed approach allows researchers to rapidly identify and extract meaningful information from big data sets. Such tools are becoming increasingly important as datasets grow larger.

Color Correction Meets Blind Validation for Image Capture: Are We Teaching to the Test?

It is common practice for digital image capture systems to use a small number of de-facto-standard test targets. Unfortunately, however, color (spectral-) characteristics of the colorants used may differ from those for the population of object/scenes to be captured. This can lead to poor color calibration of the system. A second limitation of current color-capture evaluation arises when the same set of color stimuli (color patches) are used to calibrate the color capture and to evaluate the residual color errors. When the same color-target is used, the reported color-encoding errors will usually be lower than those observed in normal image capture. This is because we are, in effect, 'teaching to the test', as when a student is prepared for test taking, rather than subject mastery. We can approach this under-reporting of color error as a measurement bias. We can treat color-correction (e.g. by a color-profile) as being a statistical model relating the detected image values and their intended ('correct') pixel values. Using a statistical approach we adopt a validation method aimed at determining the extent to which this model relationship between variables (the regression model) provides an acceptable description of the data. For our color-imaging case, the equivalent step would be to test the computed color-correction (ICC profile) with color patches that are independent of those used to build the profile. We demonstrate a candidate strategy for selecting these test colors, and an example of a validation set of colors chosen to be distinct from the calibration set in the popular ColorChecker SG.

The Impact of Orthognathic Surgery on Facial Expressions

The aim of this study was to evaluate the impact of orthognathic surgical correction of facial asymmetry and maxillary hypoplasia on the magnitude and pattern of facial expressions. This study was carried out on 2 cohorts of patients: in group 1, 10 patients had surgical correction of facial asymmetry; in group 2, 13 patients had Le Fort I osteotomy to correct maxillary hypoplasia. The patients were asked to perform 3 facial expressions (maximal smile, lip purse, and cheek puff) that were recorded using the Di4D image-capture system before and after surgery. The capture of each expression generated 180 3-dimensional (3D) facial images. Twenty-seven facial soft tissue landmarks were digitized on the first frame of the 3D image of each expression and a mathematical generic mesh was applied on the 3D model to clone each patient's face. The cloned mesh was superimposed automatically on each sequence of the 3D images to evaluate the pattern of facial expressions. The digitization of facial landmarks was satisfactorily accurate and reproducible. In group 1, the asymmetry of facial expressions was significantly decreased after surgical correction (P= .0458). In group 2, Le Fort I osteotomy decreased the magnitude of facial expressions (P= .0267). This study confirmed that orthognathic surgery affects the dynamics of facial expressions; this should be considered when planning the surgery and informing patients about the surgical correction of dentofacial deformities.

Experimental setup proposed to measure the quality of a spherical surface using deflectometry and a Hartmann screen

Currently there are a variety of techniques to determine the quality of optical surfaces, which must provide quantitative information of the deformation or the shape of the surface under test. This paper proposes to use the deflectometry technique using a Hartmann screen to test a spherical surface of the diameter and radius of curvature known. For this, the proposed experimental setup is presented, highlighting the importance of alignment and the measures distances, location between the screen and image capture system, measured from the center of curvature of the analyzed surface. Subsequently, by using these distances, the positions of the reflected rays and the positions of location of points on the screen, you can find the equation of the line associated with these two points and given this equation, we can deduce the value of the normal surface. With this result of normalsand using the general equation of deflectometry, we will obtain the shape of the surface under test.

Root growth of irrigated summer crops in cotton-based farming systems sown in Vertosols of northern New South Wales

Root penetration and proliferation are directly related to enhanced nutrient and water uptake, and thus to increased crop growth and yield. However, few studies have reported root growth and its seasonal variation in irrigated summer crops in fine-textured soils such as Vertosols. The objective of this study was to quantify the effects of tillage methods and the summer crops cotton (Gossypium hirsutum L.), maize (Zea mays L.) and sorghum (Sorghum bicolor (L.) Moench.) on root density in the non-sodic surface and subsurface soil (0–0.5 m) and sodic subsoil (0.6–0.9 m) of irrigated Vertosols in northern New South Wales (NSW). Root growth of cotton, maize and sorghum was evaluated using a combination of core sampling, and minirhizotrons and an image capture system, in several experiments conducted from 2004 to 2012, near Narrabri, northern NSW. The experimental sites had Vertosol soils with average clay contents of 65 g 100 g–1 in the surface 1 m, with sodic horizons present at depth. Rooting depth of cotton was relatively shallow, with most roots in the surface 0.6 m. Subsoil (0.6–0.9 m) root growth of cotton was sparse under continuous cotton but was greater with a cotton–wheat rotation. Among cotton genotypes, surface root length density of a Bollgard® cotton variety was less than that of its non-Bollgard counterpart. Subsoil root growth of sorghum and maize ranged from moderate to high, and accounted for a significant proportion of the total length of their root systems. This may be because maize and sorghum were able to tolerate the waterlogged conditions in the sodic subsoils of these Vertosols.

Comparative cytomorphometric analysis of oral mucosal cells in normal, tobacco users, oral leukoplakia and oral squamous cell carcinoma.

Background:Squamous cell carcinoma (SCC) is the third most common cause of oral morbidity in India despite the numerous advances made in the treatment protocol.Aim:To compare the cytomorphometric changes of oral mucosal cells in normal subjects (Group I) with that of tobacco users without any lesion (Group II), tobacco users with oral leukoplakia (Group III), and tobacco users with oral SCC (Group IV) through a semi-automated image analysis system.Materials and Methods:Oral mucosal cells collected from study subjects (n = 100) stained using rapid Papanicolaou stain. Photomicrograph of 50 nonoverlapping cells captured at 50× magnification with a digital image capture system. Cytomorphometric analysis of cells in the captured images was performed with Image-Pro image analysis software. Image analysis was performed to obtain cell diameter (CD), cytoplasmic area (CyA), nuclear diameter (ND), nuclear area (NA), and nuclear-to-cytoplasmic ratio. These values were statistically compared among the groups using one-way analysis of variance (ANOVA) and Mann-Whitney U test.Results:The ND, NA, and nuclear-to-cytoplasmic ratio values were found to be increased in the samples collected from leukoplakia and oral SCC. The CD and CyA decreased compared to the normal mucosa in oral SCC samples.Conclusion:The cytomorphometric changes observed in samples from oral SCC and oral leukoplakia were consistent with the current diagnostic features. Hence, the semi-automated cytomorphometric analysis of oral mucosal cells can be used as an objective adjunct diagnostic tool in the diagnosis of these lesions.

Fine root production and mortality in irrigated cotton, maize and sorghum sown in vertisols of northern New South Wales, Australia

Fine root (<2mm diameter) turnover (production and mortality) drives soil processes such as nutrient fluxes, carbon cycling and sequestration, activity of soil biota and structural stabilisation. Research on fine root dynamics has been focussed primarily on rainfed perennial and annual ecosystems in coarse and medium-textured soils with few studies conducted in irrigated fine-textured soils such as the vertisols. The objective of this study was to quantify the effects of tillage methods and the summer crops of cotton (Gossypium hirsutum L.), maize (Zea mays L.) and sorghum (Sorghum bicolor (L.) Moench.) on fine root number density in the non-sodic sub-surface (0.1–0.5m) and sodic subsoil (0.6–0.9m) of irrigated vertisols (average clay concentration 65g 100g−1 in the surface 1m) in northern New South Wales. It was hypothesised that fine root number density of cotton would be lower than that of maize and sorghum in the subsoil due to cotton's poor tolerance of anaerobic conditions. Fine root production, mortality and root number density of cotton, maize and sorghum, measured with a minirhizotron and a Bartz ICAP® image capture system, were evaluated for the 0.1–0.5m and 0.6–0.9m depth intervals in several irrigated experiments near Narrabri, NSW, Australia. Fine root density of cotton was low, with most occurring in the surface 0.5m. Subsoil (0.6–0.9m) root number densities of cotton were very low in continuous cotton under conventional tillage and on permanent raised beds (PRBs) but were greater with a cotton-wheat (Triticum aestivum L.) rotation sown on PRBs. Averaged over the two seasons, 2004–2005 and 2006–2007, and depth intervals, there were 3.4 roots×100mm−2 in continuous cotton sown after conventional tillage, 1.2 roots×100mm−2 in continuous cotton sown on PRBs and 6.0 roots×100mm−2 in cotton–wheat sown on PRBs. Between cotton genotypes, root number density during boll production and filling of a Bollgard®-Roundup-Ready® cotton variety was less than that of its corresponding non-Bollgard variant. Maize live root numbers did not differ significantly between continuous maize and a cotton-maize rotation but differed between depth intervals. Averaged over years and rotations, during tasselling maize had 21.5 roots×100mm−2 in the 0.1–0.5m depth interval and 5.3 roots×100mm−2 in the 0.6–0.9m depth interval. Root number density of sorghum was greater with no-tillage than with tillage in wetter seasons but generally similar or lower during a drier season. Average root numbers in the 0.1–0.5m depth interval during the “wet” seasons of 2010–2011 and 2011–2012 were 4.4 roots.100mm−2 with tillage and 9.3 roots×100mm−2 with no-tillage, and in the 0.6–0.9m depth interval were 4.5 roots×100mm−2 with tillage and 10.5 roots×100mm−2 with no-tillage. During the “dry” season of 2012–2013, however, root numbers in the 0.1–0.5m depth interval were 16.6 roots×100mm−2 with tillage and 11.8 roots×100mm−2 with no-tillage, and in the 0.6–0.9m depth interval were 13.8 roots×100mm−2 with tillage and 9.0 roots×100mm−2 with no-tillage. Fine root density of cotton was low, whereas those of sorghum and maize were high with relatively large values occurring in the deeper subsoil. Maize and sorghum were able to tolerate the waterlogged conditions in the sodic subsoils of these vertisols and may, therefore, be more suitable rotation crops for irrigated cotton farming systems than the more commonly sown wheat. These results, while relevant to other fine-textured soils that are irrigated or are periodically inundated, should not be extrapolated to medium and coarse-textured soils.

Exquisite CCD camera design for an optical computed tomography scanner

The OCT (Optical Computed Tomography) in order to obtain the precise dose distribution relies on high accuracy (low noise) and high spatial resolution of the image capture system. Therefore, this study proposes a high-resolution CCD-based camera systems design. Part of the low noise, we propose a variety of CCD signal processing to eliminate noise, such as bias clamp, random noise and pixel response non-uniformity. According to the experiment results, our CCD signal processing algorithm can guarantee low noise output. At exposure time of 150ms, the coefficient of variation of the pixel is reduced from 12.37% to 0.51% by flat-field correction, in the same measurement standards, our system SNR (30.12dB) better than other brand CCD camera (25.31dB) and other brand CMOS camera (29.53dB). Part of the high spatial resolution, we propose high-performance camera design (optical lens, image sensor, image processing) to ensure high spatial resolution output. In MTF50 (Modulation Transfer Function 50%), our camera (1024×1024) get the 745LW/PH (Line Width/Picture Height), close to 73% of the limited resolution; another brand CCD camera (1024×768) of 358 LW/PH, about 46.6% of the limited resolution; another brand CMOS camera (3648×2736) of 1628 LW/PH, about 59.5% of the limited resolution. Therefore, our camera with a high precision and high spatial resolution design, it can to meet in OCT and increase accuracy of the dose distribution.

LED transceivers with beehive-shaped reflector for visible light communication

This paper proposes a novel beehive-shaped reflector for application to light-emitting diode (LED) transceivers for illumination and bi-directional visible light communication (VLC). By using a diffuse propagation model extended to line-of-sight and direct signals, the distribution of illuminance and the path loss of the transceiver are investigated to evaluate the performance of the beehive-shaped reflector. To verify bi-directional communication, a VLC-based image capture system, comprising a complementary metal-oxide semiconductor (CMOS) image sensor and video processor unit, is demonstrated. Real-time images captured by the CMOS camera are successfully transmitted to the monitoring system via a free-space channel at a rate of 115.2 kbps.

Design of Remote Crops Image Capture and Expert System in the Yellow River Delta

The Yellow River Delta National Agricultural Science and Technology Park proposed the concept of "One Zone One Hundred Parks", namely the Yellow River Delta National Agricultural Science and Technology Park consists of a hundred geographically dispersed agricultural technology demonstration park. In order to effectively provide intellectual support for these geographically dispersed agricultural technology demonstration parks, this paper presents the design and the idea of remote crop image capture and expert systems. The core idea is to set up image collection terminals in a decentralized agricultural technology demonstration park. Crop samples are collected by the terminals, using GPRS network to transfer the captured image data to the Key Laboratory of Agricultural Bioengineering. Agricultural experts make an analysis to image samples, and propose treatment advice. And then, the experts feedback the advice to the various agricultural technology demonstration parks. After a year of testing, the entire system is reliable, excellent performance in real-time transmission of images. This system has played a very important role in the prevention and control of crop pests and crop growth guidance.

Qualitative Study on Mechanical Environment Affecting the Degradation of the Magnesium Alloys

Objective Explore the degradation rule of the magnesium alloys in simple mechanical environment. Methods Select a kind of magnesium alloy of better degradation by experiment and prepare screws. The experiment totally contains five groups, they are control group one with no specific conditions, experimental group two with 0.1Mpa external pressure, experimental group three with 0.2Mpa external pressure, pig femoral experimental group four with 0.2N shear force, pig femoral experimental group five with 0.3N shear force. Record the volume of hydrogen every certain time interval and observe the surface morphology of magnesium alloy screws through Object Deformation Image Capture System when the experiment is over to reflect the degradation rate of magnesium alloys. And the experiment would be repeated once to ensure the test results. Results Compared to group one, when external pressure exists, the volume of hydrogen significantly increases. Group two and group three have no significant difference in results, but group three has a greater degree of degradation than group two by observing the surface morphology. The volume of hydrogen of group four and group five is smaller than that of the first group in that smaller volume of screws exposes in SBF. The volume of hydrogen of the fifth group is greater than that of group four. Group five has a greater degree of degradation than the fourth group by observing the surface morphology. The repeated experiment basically keeps the same conditions, but the volume of hydrogen of group three is greater than that of group two.Conclusion Mechanical environment has an impact on the degradation rate of magnesium alloys. The pressure of the environment affects the degradation rate of magnesium alloys. The greater the pressure, the faster the degradation rate. The external force affects degradation rate of magnesium alloys. The greater the shear force, the faster the degradation rate.

Morphological and morphometric evaluation of prepubertal gilt ovaries, uterine tubes and uterus at different oestrus cycle stages

Studies are performed in developing techniques/procedures that provide greater reproductive performance in farm animals, including pigs. In this sense, the study of gilts reproductive organs at different oestrus cycle stages for assessing the presence of abnormalities and/or other parameters that may affect the future animal fertility is important. In order to evaluate the morphological, morphometric and histomorphometric features of ovaries, uterus and uterine tubes (UTs) characteristics of prepubertal gilts at different oestrus cycle stages, reproductive tracts from 48 animals immediately after slaughter were obtained. After, the structures were dissected and removed, and the ovaries were used for classification of oestrus cycle stage of each gilt in follicular phase (FP) and luteal phase (FL). Then, morphometric evaluations of ovaries, UTs, uterine horns and uterine body were performed. Besides that, medial segments of UTs and uterus were fixed in Bouin solution, processed and included in paraffin, when histological sections of 5.0 micrometers (µm) were obtained and stained with Hematoxylin and Eosin. Histomorphometric analyzes using image capture system and specific software were performed. Afterwards, data were submitted to Student's t test for assessment the statistical differences (P&lt;0.05) between the two different oestrus cycle stages (FP × LP) and between the placement of reproductive structures (right × left antimer). Among the gilts evaluated, 35 were in the FP and 13 in LP. There was no difference (P&gt;0.05) between morphometric parameters of ovaries, UTs and uterus of gilts in FP and LP. Likewise, in respect to the placement of reproductive structures, both in the oestrus cycle stages, as in the general average, there was no difference (P&gt;0.05). Regarding the histomorphometric variables, gilts classified in FP presented a higher (P&lt;0.05) height of glandular and UT epithelium compared to animals in LP. On the other hand, the diameter of endometrial glands was higher (P&lt;0.05) in gilts at LP compared to FP. Furthermore, gilts in LP presented a higher (P&lt;0.05) proportion of endometrium occupied by glands, whereas animals in FP had a higher (P&lt;0.05) proportion of connective tissue and blood vessels. In conclusion, in prepubertal gilts, the histomorphometric parameters as endometrial glands diameter, the height of glandular epithelium and of UT epithelium and the proportion of endometrium occupied by connective tissue, besides the glands and blood vessels varies through the oestrus cycle, possibly under the influence of ovarian steroids.

Arc Behavior and Droplet Transfer Process of VP CMT

Cold metal transfer (CMT) is widely used in thin sheets welding, owing to its low heat input and freedom of spatter. An evolutionary technology, called CMT Adv, combines CMT and variable polarity (VP) process. Arc behavior analysis and droplet transfer analysis were performed by image capture system synchronized with current and voltage sensor. Checker calibration method was used to get dimensions of droplets. The results show that motion of filler wire, current and voltage waveform and droplet transfer of VP CMT (CMT Adv) are coordinated to maintain welding stability. And through precise energy control, droplets of same dimensions can be got in EP and EN period, which are similar to diameter of filler wire. To from droplets with same dimensions, lower power was supplied and melt efficiency is higher in EN period.

Clinical performance evaluation of the CellaVision Image Capture System in the white blood cell differential on peripheral blood smears

IntroductionDifferential counting and morphological analysis of peripheral blood smears is of great diagnostic importance to the clinician. For economic and time-saving reasons, automated imaging processes have been successfully introduced over...

Stereo one-shot six-band camera system for accurate color reproduction

For accurate color reproduction of motion pictures or still pictures of moving objects, we developed a different one-shot six-band image-capturing and visualization system that combines multiband and stereo imaging techniques. The proposed system consists of two consumer-model digital cameras and an interference filter whose spectral transmittance is comb-shaped. Subpixel correspondence search between the stereo image pairs is conducted and image transformation whose parameters are estimated from the correspondence is used to correct the geometric relationship between the images. The Wiener estimation method is used for color reproduction. For experiments, we have constructed two six-band camera systems to evaluate the quality of resultant images. One is for capturing high-resolution images using digital single-lens reflex cameras. The other is for capturing motion pictures using digital video cameras, for which all image processing steps after image capture are implemented on graphics processing units and the frame rate of the system is 30 fps when image size is XGA. For both systems, the average color difference between the measurement data and estimation results for 24 color patches of the Macbeth ColorChecker™ is dEa ∗ b ∗ =1.21 at maximum.

Simulation of the Photodetection in the PPS CMOS Sensors

The paper contains an analysis and simulation of passive pixel based sensors. The passive pixel CMOS image acquisition sensor (PPS) is the key part of a visible image capture systems. The PPS is a complex circuit composed by an optical part and an electrical part, both analog and digital. The goal of this paper is to simulate the functionality of the photodetection process that happens in the PPS sensor. The photodetector is responsible with the conversion from photons to electrical charges and then into current. In the optical part, the sensor is analyzed by a spectral image processing algorithm which uses as input data: the lenses array transmittance, the red, green and blue filters and the quantum efficiency of the PPS. In the electrical part of simulation, the program is computing the signal to noise ratio of the sensor taking into account the photon shot, white and fixed pattern noises. Our basic analysis is based on camera equation to which we add the noises.

3D imaging for bite mark analysis

This work describes the investigation into a new 3D capture method for acquisition and subsequent forensic analysis of bite mark injuries on human skin. When documenting bite marks with standard 2D cameras, errors in photographic technique can occur if best practice is not followed. Subsequent forensic analysis of the mark is problematic when a 3D structure is recorded in a 2D space. A 3D image capture and processing system might avoid the problems resulting from the 2D reduction process, simplifying the guidelines and reducing errors. This paper reviews current 2D and three 3D capture methods and proposes a series of benchmarks for system assessment. This is followed by a series of performance evaluations of the existing current 2D and two 3D methods. Further proposed solutions include the design of a system specification for the practical reproducible acquisition of bite mark injuries and a review of the validation process for forensic evidence presented to the courts. The result of this work is that a 3D system is required to produce the correct 3D data of a bite mark and suspect dentition for forensic analysis. Such a system should be practical and consistent if it is to replace the current de facto 2D systems. The MAVIS hardware, for example, can be considered a practical and consistent solution for producing the required 3D image of a bite mark for analysis; however, the MAVIS hardware cannot produce a satisfactory 3D image of a dental cast. At present, a laser scanner is required to produce satisfactory results of a dental cast. Angular distortion and errors created by the user in 2D image capture can hinder the digital measurement process. 3D capture therefore introduces less operator error in the form of angular distortion.

Pseudobrânquia do guaru Poecilia reticulata (Peter, 1859): análise estrutural, morfométrica e histoquímica para detecção de glicoconjugados

A morfologia, os parâmetros citomorfométricos e os glicoconjugados presentes na pseudobrânquia de guaru, Poecilia reticulata Peter, 1859 (Cyprinodontiformes: Poeciliidae), foram investigados por microscopia de luz acoplada ao sistema de captura e análise de imagens, juntamente por histoquímica com lectinas. A anatomia microscópica indicou que P. reticulata possui pseudobrânquia glandular formada por dois lóbulos, a qual se localiza abaixo do epitélio faringiano. O órgão é constituído por parênquima vascularizado e rico em células pseudobranquiais. Esse tipo celular exibe estado citofisiológico ativo, com abundante sistema de biomembranas e ausência de óstio na superfície apical,que por sua vez é encontrado nas células ricas em mitocôndrias das holobrânquias. Assim, indica-se que as células da pseudobrânquia se distinguem das células das holobrânquias em relação à morfologia, histoquímica e fisiologia. Em decorrência dessas características intrínsecas, a pseudobrânquia de alevinos do guaru pode desempenhar funções não respiratórias nas fases iniciais do desenvolvimento. Além disso, a caracterização da pseudobrânquia do guaru possibilitará estudos futuros sobre o efeito de poluentes aquáticos em espécies biomonitoras, como P. reticulata.

Composite Target for Camera-Based Document/Object Capture System*

The use of mobile phone camera technology in systems for capture of documents or three-dimensional objects is becoming increasingly popular. Compared to conventional flatbed or sheetfed scanner technology, such systems pose special image quality concerns due to the fact that the underlying camera and illumination technologies are inherently low-cost. Thus, each unit is designed to operate closer to the threshold of acceptable quality. So there are higher levels of noise and greater non-uniformity across the image plane, as well as greater unit-to-unit variability. Consequently, there is a need for a solution that can provide a detailed assessment of the spatial non-uniformity of key image quality metrics within the field of view of the image capture system, and which can be robustly and efficiently computed. This article proposes a specially designed composite target and an automatic analysis tool for image quality inspection of camera-based document/object capture systems. The target and analysis tool can be used during product development, as well as on the manufacturing line for real-time inspection.

Visual Servo Tracking Control for Slider Robot Using CMAC Neural Network Recognition Approach

This paper describes an image-based visual servo tracking control scheme using CMAC neural network as object recognition feedback methodology. A web camera based image capture system is mounted on the slider robot to capture the desired object and a CMAC (Cerebellar Model Articulation Controller) based object recognition scheme is developed to recognize the captured object image. Comparing the relative location of the recognized object and the web camera, then the position feedback signal can be obtained. Using the feedback signal, a PID (Proportional-Integral-Derivative) controller is designed to track the desired object by moving a single-axis slider robot, such that the captured object image located on the center of the captured frame always.